docks-kit 0.22.20 → 0.22.22

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/AGENTS.md CHANGED
@@ -87,16 +87,16 @@ omp SoT notes:
87
87
  - `SoT/.omp/AGENTS.md`, `config.yml`, `models.yml`, and `mcp.json` deploy to `~/.omp/agent/`.
88
88
  - `SoT/.omp/intercom.json` deploys to `$PI_CODING_AGENT_DIR/intercom/config.json`. The default root is `~/.pi/agent`. Under a named omp profile (`OMP_PROFILE` or `PI_PROFILE`), it deploys to `<profile agentDir>/intercom/config.json`, because omp exports `PI_CODING_AGENT_DIR` as the profile agent directory.
89
89
  - `ompFileDeploy.ts syncMergedYaml` deep-merges `config.yml` through `ompYaml.ts mergeOmpConfig` and `models.yml` through `mergeOmpModels`. Both wrap one generic mapping merge; only the config wrapper prunes stale `retry.fallbackChains` wildcards and merges `bash.patterns`.
90
- - `SoT/.omp/config.yml` `bash.patterns` holds the destructive-command guards. omp's `CRITICAL_BASH_PATTERNS` check returns a bare safety override before a matching prompt rule, and `tools.approvalMode: yolo` ignores a bare override, so a prompt on a critical command becomes an allow, in subagents too (`omp://approval-mode.md`). Every `rm` shape that check can flag is therefore a deny: recursive `rm`, `sudo` anywhere before `rm` (also by path), any `rm` with an `r` or `f` option before an absolute path, and `--no-preserve-root`. By owner decision (0.20.9), the recursive-`rm` deny also covers any prefix (a `* rm ` copy of each bare cluster rule, so `env X=1 rm -rf b`, `xargs rm -rf`, `find . -exec rm -rf {} +`, and `git rm -r dir` are denied) and the `-ri`, `-ir`, `-Ri`, and `-iR` clusters for bare `rm`, `*/rm`, and `* rm`. By owner decision (0.21.0), 17 more denies cover bulk removal that can empty the home directory: `find -delete` (bare, `*/find`, `* find`), `-exec`, `-execdir`, `-ok`, and `-okdir` with `rm` or `*/rm`, and `xargs rm` in six shapes. No glob can express "inside the temporary directory", so `docks-kit scratch remove` checks that path in code. A `$` or a backtick anywhere after `git push` in the same command is a deny, not a prompt (0.22.5, #120). A variable can expand to a `+` refspec or `--force`, and the matcher reads the text before the shell expands it. The agent reads the refusal and writes the ref literally, so no person is asked. The two rules are `*git push *$*` and ``*git push *`*``. Their leading `*` keeps a shell keyword such as `do`, a wrapper such as `env`, or a path before `git` from hiding the push. By owner decision (0.22.8, #126), the kit ships no omp prompt rule: `bash.patterns` holds only the denies plus the `trash *` allow, so every command that no deny matches runs without a question, in subagents too. Since 0.20.9 this run-without-question behavior covers a non-denied `rm`, `git rm`, `git worktree remove`, and `gio trash`. Since 0.21.0 it also covers `docks-kit scratch remove`. Since 0.22.8 it also covers `git clean`, `git reset --hard`, a hook skip, and every `git push` that no deny matches. The force-push denies match only `git push --force` or `-f` directly before `origin main` or `origin master`, so another spelling, such as `git push origin main --force`, runs. A prompt rule that the user adds survives sync and still asks. `SoT/.omp/AGENTS.md` carries the agent rules for these commands, and it tells the agent to write each `git push` ref literally and to push the current branch with `git push -u origin HEAD`. Claude Code `permissions.ask` and Codex `docks.rules` keep their ask tiers. The list order is deny, then `trash *`. omp takes the first match. `ompYaml.ts mergeBashPatterns, grouped rule merge` keeps user rules and groups all rules as kit deny, user deny, user prompt, kit prompt, other user rules, kit allow, so a user deny or prompt precedes every kit allow. It treats a deployed rule equal to a kit rule (approval case-folded, `match` whitespace collapsed) as the kit copy, so a re-sync is a no-op. A rule the kit stops shipping stays as a user rule, so retire one through `ompRemovals.ts OMP_RETIRED_BASH_RULES`. `cli/test/lib/ompBashPatterns.ts` ports omp 18.17.0's matcher, critical patterns, and yolo resolution; `cli/test/unit/ompBashPatterns.test.ts` asserts each command's final outcome and the merge. omp subagents reject every `prompt`, and the `eval` tool stays unrestricted by owner decision.
90
+ - `SoT/.omp/config.yml` `bash.patterns` holds the destructive-command guards. omp's `CRITICAL_BASH_PATTERNS` check returns a bare safety override before a matching prompt rule, and omp's default `tools.approvalMode: yolo` ignores a bare override, so a prompt on a critical command becomes an allow, in subagents too (`omp://approval-mode.md`). Every `rm` shape that check can flag is therefore a deny: recursive `rm`, `sudo` anywhere before `rm` (also by path), any `rm` with an `r` or `f` option before an absolute path, and `--no-preserve-root`. By owner decision (0.20.9), the recursive-`rm` deny also covers any prefix (a `* rm ` copy of each bare cluster rule, so `env X=1 rm -rf b`, `xargs rm -rf`, `find . -exec rm -rf {} +`, and `git rm -r dir` are denied) and the `-ri`, `-ir`, `-Ri`, and `-iR` clusters for bare `rm`, `*/rm`, and `* rm`. By owner decision (0.21.0), 17 more denies cover bulk removal that can empty the home directory: `find -delete` (bare, `*/find`, `* find`), `-exec`, `-execdir`, `-ok`, and `-okdir` with `rm` or `*/rm`, and `xargs rm` in six shapes. No glob can express "inside the temporary directory", so `docks-kit scratch remove` checks that path in code. A `$` or a backtick anywhere after `git push` in the same command is a deny, not a prompt (0.22.5, #120). A variable can expand to a `+` refspec or `--force`, and the matcher reads the text before the shell expands it. The agent reads the refusal and writes the ref literally, so no person is asked. The two rules are `*git push *$*` and ``*git push *`*``. Their leading `*` keeps a shell keyword such as `do`, a wrapper such as `env`, or a path before `git` from hiding the push. By owner decision (0.22.8, #126), the kit ships no omp prompt rule: `bash.patterns` holds only the denies plus the `trash *` allow, so every command that no deny matches runs without a question, in subagents too. Since 0.20.9 this run-without-question behavior covers a non-denied `rm`, `git rm`, `git worktree remove`, and `gio trash`. Since 0.21.0 it also covers `docks-kit scratch remove`. Since 0.22.8 it also covers `git clean`, `git reset --hard`, a hook skip, and every `git push` that no deny matches. The force-push denies match only `git push --force` or `-f` directly before `origin main` or `origin master`, so another spelling, such as `git push origin main --force`, runs. A prompt rule that the user adds survives sync and still asks. `SoT/.omp/AGENTS.md` carries the agent rules for these commands, and it tells the agent to write each `git push` ref literally and to push the current branch with `git push -u origin HEAD`. Claude Code `permissions.ask` and Codex `docks.rules` keep their ask tiers. The list order is deny, then `trash *`. omp takes the first match. `ompYaml.ts mergeBashPatterns, grouped rule merge` keeps user rules and groups all rules as kit deny, user deny, user prompt, kit prompt, other user rules, kit allow, so a user deny or prompt precedes every kit allow. It treats a deployed rule equal to a kit rule (approval case-folded, `match` whitespace collapsed) as the kit copy, so a re-sync is a no-op. A rule the kit stops shipping stays as a user rule, so retire one through `ompRemovals.ts OMP_RETIRED_BASH_RULES`. `cli/test/lib/ompBashPatterns.ts` ports omp 18.17.0's matcher, critical patterns, and yolo resolution; `cli/test/unit/ompBashPatterns.test.ts` asserts each command's final outcome and the merge. omp subagents reject every `prompt`, and the `eval` tool stays unrestricted by owner decision.
91
91
  - `ompSync.ts` runs `ompRemovals.ts syncOmpRemovals, retired-key inventory` right after the config merge, and that pass force-prunes retired kit-owned keys from `~/.omp/agent/config.yml` on every sync, without `--reconcile`. The pass is required because `mergeOmpConfig` is additive, so removing a key from the SoT alone never removes it from a deployed file. A key retired with a recorded value is pruned only while the deployed value still matches that value, so a user edit survives; a key retired outright, such as `providers.webSearchOrder`, is pruned at any value. The same pass removes each `bash.patterns` rule listed in `OMP_RETIRED_BASH_RULES`: the 39 file-removal rules retired in 0.20.9, the four `git push` prompts for a `$` or backtick word that 0.22.5 replaced with denies, and the 492 prompt rules retired in 0.22.8 (`RETIRED_PROMPT_MATCHES`). It compares with the merge's kit-rule normalization (approval case-folded, `match` whitespace collapsed), so a user rule with a different `match` or `approval` survives.
92
- - `cycleOrder` ends with `astra` as its fifth stop. `modelRoles.astra` is `openai-codex/gpt-6-astra:xhigh`, and `modelTags.astra` is visible. Astra and Fable fall back to each other through concrete selectors. `modelRoles.fable` remains `anthropic/claude-fable-5-1:medium`, with visible `modelTags.fable`. The hidden `switch_fable` role uses the same Fable selector and keeps an empty fallback chain.
93
- - `modelRoles.task` is `anthropic/claude-opus-5-5:high`, and `retry.fallbackChains.task` falls back to `openai-codex/gpt-6.1-sol:high`. `task.enableEffort` is `false`: a caller `effort` outranks the role's level suffix, and `hi` maps to the top of the model ladder, so with the field on, `hi` spawns ran at `task.maxEffort` (`xhigh`) instead of the role level. With the field off, every spawn runs its role level, and `task.maxEffort` bounds only a per-call `model` with a `:level` suffix. `advisor` is `anthropic/claude-opus-5-5:medium` with an empty fallback chain, because a GPT-6 Sol advisor looped on repeated reads under an Opus 5.5 session. Never put any GPT model (`openai-codex/gpt-*`, including GPT-6.1 Sol and GPT-6 Astra) in the advisor role or chain; Astra also costs too much for this role. `smol`, `commit`, and `tiny` use `openai-codex/gpt-6-luna`. The kit-defined hidden `reviewer` role is `openai-codex/gpt-6.1-terra:high`. Its retry fallback is `anthropic/claude-opus-5-5:high`. All four reviewer entries in `task.agentModelOverrides` point to `@reviewer`. `task.agentServiceTierOverrides` sets the same four agents to `inherit`, so they take the live tier of the main session for each provider. The user set the effort `high` and chose to follow the fast toggle (#134); the review benchmark of #130 chose the model. `ompOverlay.ts ROLE_ORDER, FALLBACK_ORDER` list `reviewer`, so a free session also replaces it. omp bundles the `reviewer` and `security-reviewer` agents, and the `plan-lifecycle` plugin ships `code-reviewer` and `plan-reviewer`. The `SoT/toolchain.json` omp floor is 18.4.4, the oldest release the kit tested with `gpt-6.1-sol`. That release lists and serves the model through the `openai-codex` provider. `cli/docs/omp-models.md` records the checks.
94
- - The seven Opus 5.5 roles (`default`, `slow`, `plan`, `designer`, `vision`, `task`, `advisor`) and the `smol`, `tiny`, `commit`, and `reviewer` retry chains use `anthropic/claude-opus-5-5` at the levels the role map records. `cli/docs/omp-models.md` carries the Artificial Analysis capture behind the role map, read 2026-09-29 at Intelligence Index v4.3.2 and Coding Agent Index v1.5 from the AA comparison-page metric tables. The `reviewer` row is the exception: it comes from a v5.0.1 capture read 2026-11-05, and it compares only with other v5.0.1 figures. Opus 5.5 max has the highest index in that topic, at 58. AA has measured speed and latency for Opus 5.5 max and every GPT-6.1 Sol level; GPT-6 Luna medium is the only unmeasured speed and latency row.
92
+ - `cycleOrder` ends with `astra` as its fifth stop. `modelRoles.astra` is `openai-codex/gpt-6-astra:xhigh`, and `modelTags.astra` is visible. Astra and Fable fall back to each other through concrete selectors. `modelRoles.fable` is `anthropic/claude-fable-5-2:medium`, with visible `modelTags.fable`. The hidden `switch_fable` role uses the same Fable selector and keeps an empty fallback chain.
93
+ - `modelRoles.task` is `anthropic/claude-opus-5-5:high`, and `retry.fallbackChains.task` falls back to `openai-codex/gpt-6.1-sol:high`. The kit relies on omp's default `task.enableEffort: false`: a caller `effort` outranks the role's level suffix, and `hi` maps to the top of the model ladder, so with the field on, `hi` spawns ran at `task.maxEffort` (`xhigh`) instead of the role level. With the field off, every spawn runs its role level, and `task.maxEffort` bounds only a per-call `model` with a `:level` suffix. By owner decision (0.22.22), the omp advisor is removed: the SoT has no `advisor` block, `advisor` role, or `advisor` fallback chain. The plan-lifecycle verification loop replaces a second model on every turn. A session that runs `/advisor on` takes its advisor model from the `slow` role. `smol`, `commit`, and `tiny` use `openai-codex/gpt-6-luna`. The kit-defined hidden `reviewer` role is `openai-codex/gpt-6.1-terra:high`. Its retry fallback is `anthropic/claude-opus-5-5:high`. All four reviewer entries in `task.agentModelOverrides` point to `@reviewer`. `task.agentServiceTierOverrides` sets the same four agents to `inherit`, so they take the live tier of the main session for each provider. The user set the effort `high` and chose to follow the fast toggle (#134); the review benchmark of #130 chose the model. `ompOverlay.ts ROLE_ORDER, FALLBACK_ORDER` list `reviewer`, so a free session also replaces it. omp bundles the `reviewer` and `security-reviewer` agents, and the `plan-lifecycle` plugin ships `code-reviewer` and `plan-reviewer`. The `SoT/toolchain.json` omp floor is 18.4.4, the oldest release the kit tested with `gpt-6.1-sol`. That release lists and serves the model through the `openai-codex` provider. `cli/docs/omp-models.md` records the checks.
94
+ - The six Opus 5.5 roles (`default`, `slow`, `plan`, `designer`, `vision`, `task`) and the `smol`, `tiny`, `commit`, and `reviewer` retry chains use `anthropic/claude-opus-5-5` at the levels the role map records. `cli/docs/omp-models.md` carries the Artificial Analysis capture behind the role map, read 2026-09-29 at Intelligence Index v4.3.2 and Coding Agent Index v1.5 from the AA comparison-page metric tables. The `reviewer`, `fable`, and `switch_fable` rows are the exceptions: they come from v5.0.1 captures read 2026-11-05 (GPT-6.1 Terra) and 2026-11-12 (Fable 5.2), and they compare only with other v5.0.1 figures. Opus 5.5 max has the highest v4.3.2 index in that topic, at 58. AA has measured speed and latency for Opus 5.5 max and every GPT-6.1 Sol level; GPT-6 Luna medium is the only unmeasured speed and latency row.
95
95
  - `modelRoles.web` is `web/firecrawl` and `retry.fallbackChains.web` carries the explicit 20-entry provider order. The kit declares both keys because the legacy `providers.webSearchOrder` key is retired: omp expands it in memory into these two keys and then drops it, and never writes that expansion back to disk. An explicit chain replaces omp's built-in web order wholesale, so every entry left out is a provider omp never tries. The owner removed the seven entries that named older models (Gemini 2.5 Flash, Claude Haiku 4.5, GPT-5.6, GPT-5.5, and Grok 4.5); keep every other provider.
96
96
  - `SoT/.omp/models.yml` declares Astra's full `low, medium, high, xhigh, max` ladder with `defaultLevel: xhigh` as the worked provider ladder-override example. The temporary `anthropic.modelOverrides.claude-opus-5-5` block is gone, because the shared catalog now publishes the same limits, ladder, and prices. The removal switches omp from the block's `thinking.mode: effort` (a `budget_tokens` value per level from `ANTHROPIC_THINKING`, no effort value) to the catalog's `anthropic-adaptive` (adaptive thinking with the role's effort level); every kit Opus selector names its level, so the block's bare-selector `defaultLevel: high` is not needed. `ompRemovals.ts syncOmpModelRemovals, retired-block inventory` prunes it from `~/.omp/agent/models.yml` after the models merge, but only while the deployed block still equals the shipped one. `ompYaml.ts mergeOmpModels` preserves deployed-only keys in `~/.omp/agent/models.yml`, because a user file may carry provider credentials. Whole-file replacement is wrong.
97
97
  - `SoT/.omp/AGENTS.md` carries the rule `Please remove all mannered prose.` Anthropic's Fable 5.1 prompting guide documents mannered prose as a Fable 5.1 behavior and gives that sentence as its short-version fix: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1
98
98
  - `cli/docs/omp-models.md` (topic `omp-models`) records the role map rationale and the Artificial Analysis snapshot behind it. Model choices change with published benchmarks, so update that topic in the same commit as a role change.
99
- - `SoT/.omp/config.yml` sets `compaction.thresholdTokens` to `-1`, omp's schema default sentinel selecting reserve-based behavior: the trigger becomes `contextWindow` minus `max(floor(contextWindow * 0.15), 16384)`. The trigger is 425,000 on the 500,000-token windows of GPT-6.1 Sol and Terra, 231,200 on the 272,000-token windows of GPT-6 Luna and Astra, and 850,000 on the 1,000,000-token Anthropic window. The key ships as `-1` rather than being deleted because `ompYaml.ts mergeOmpConfig` is additive, so removing a key from SoT never removes it from a deployed file. `cli/docs/omp-context.md` (topic `omp-context`) carries the derivation and the measured evidence, so update that topic in the same commit as any compaction-setting change.
99
+ - `SoT/.omp/config.yml` carries only keys whose value differs from the omp default. When a kit value equals the omp default, remove the key from the SoT. Add it with its shipped value to `ompRemovals.ts OMP_RETIRED_VALUES`, because `ompYaml.ts mergeOmpConfig` is additive and only that pass prunes the deployed copy. For example, the kit ships no `compaction.thresholdTokens`, and sync prunes a deployed `-1` and the former `231200` pin. `cli/docs/omp-context.md` (topic `omp-context`) carries the reserve-based derivation and the measured evidence, so update that topic in the same commit as any compaction-setting change.
100
100
  - Sync materializes the kit omp plugin `docks-kit-omp` from `SoT/.omp/plugin/` to `~/.docks-kit/omp-plugin` (`ompKitPlugin.ts syncKitPlugin`). It sets directories to 0700, files to 0600, and the `package.json` `version` to the kit version, and it removes stale files. It keeps no backups, because the directory is kit-owned. `ompPlugins.ts syncPlugins, kit plugin link` then runs `omp plugin link <dir>`. It skips the link when the `omp plugin list --json` npm row `docks-kit-omp` already has a `path` that resolves to that directory. `--skip-plugin-refresh` does not skip the link. The `hygiene.ts` extension registers `scratch_new`, `scratch_remove`, and `tidy_report`. It adds a reminder after each bash command that created a resource, and it checks at session stop that those resources are gone. At a main-session start, it claims `~/.cache/docks-kit/tidy.stamp.claim` and runs `docks-kit tidy --apply` in the background at most once per 12 hours. Every extension subprocess runs without a shell. The `pluginUpgrades.ts` extension reads the omp plugin upgrade log. In a tool result of each main session, it adds one reminder for the logged upgrades that the session did not get before. It names only the upgrades that finished after its omp process started. The reminder tells the agent to ask the user to run `/reload-plugins`. It then tells the agent to read each plugin skill again through `skill://` before it runs a skill script. It asks for a restart instead when an upgraded plugin ships hooks, extension modules, or non-MCP tools. omp imports extensions only at startup. An omp process that started before a sync deployed `pluginUpgrades.ts` did not load it, so its sessions get no reminder. The plugin also ships the `workspace-hygiene` skill and the `/cleanup` command. The plugin, the deployed rules, and the sweep call `docks-kit scratch` and `docks-kit tidy`. So a checkout sync must not run before the global `docks-kit` carries those commands.
101
101
  - `task.agentIdleTtlMs` is `120000`, so omp parks an idle subagent after 2 minutes instead of 7. `browser.idleCloseSec` is `600`.
102
102
  - By owner decision (0.21.0), resources on the workstation are always development, so `docks-kit tidy` sweeps them without a question. The omp agent prompt, the `workspace-hygiene` skill, `/cleanup`, and the extension reminders limit the cleanup of a remote resource (reached through SSH or a provider CLI such as `wrangler`, `vercel`, `kubectl`, or a remote Docker host) to targets named local, development, dev, test, homolog, homologation, staging, or preview, the plan-lifecycle non-production definition. A production cleanup needs an `ask` immediately before it, must be rare, and a `yolo` invocation does not answer that ask. Prompt rules cannot force an agent to ask, so this rule has no `bash.patterns` guard.
@@ -16,8 +16,8 @@ ask tier is accepted.
16
16
 
17
17
  omp is the exception: by owner decision (0.22.8, #126), the kit ships no omp
18
18
  prompt rule. The kit's `bash.patterns` holds only deny rules and the `trash *`
19
- allow. Under the kit's `tools.approvalMode: yolo`, omp runs every command
20
- that no deny matches without a question, in the main session and in
19
+ allow. Under omp's default `tools.approvalMode: yolo`, omp runs every
20
+ command that no deny matches without a question, in the main session and in
21
21
  subagents. This includes any `rm` that omp does not deny, `git clean`,
22
22
  `git reset --hard`, a force push that no deny matches, and a git command
23
23
  that skips the repository's hooks. A prompt rule that the user adds to
@@ -175,8 +175,9 @@ omp has a built-in check for critical commands. For example, it flags:
175
175
  - `sudo rm`, also when `sudo` is called by its path.
176
176
 
177
177
  For a critical command, omp returns a bare safety override before it returns
178
- a matching prompt rule. Under the kit's `tools.approvalMode: yolo`, omp
179
- ignores a bare override, so the command runs. This applies in subagents too.
178
+ a matching prompt rule. Under omp's default `tools.approvalMode: yolo`,
179
+ omp ignores a bare override, so the command runs. This applies in subagents
180
+ too.
180
181
  Only a deny rule stops a critical command (`omp://approval-mode.md`).
181
182
 
182
183
  The kit therefore denies every `rm` shape that the check can flag:
@@ -1,7 +1,7 @@
1
1
  # omp context and compaction
2
2
 
3
- This topic records why `SoT/.omp/config.yml` does not pin a compaction
4
- threshold, and what omp's reserve-based default computes on each model lane.
3
+ This topic records why `SoT/.omp/config.yml` ships no compaction threshold,
4
+ and what omp's reserve-based default computes on each model lane.
5
5
 
6
6
  ## How omp resolves the trigger
7
7
 
@@ -62,17 +62,20 @@ No session ran past its window, and omp raised no warning on either lane.
62
62
  Under the reserve-based default none of the 75 Anthropic compactions would
63
63
  have fired, because no session reached 850,000.
64
64
 
65
- ## Why the key ships as -1 rather than being deleted
65
+ ## How sync removes the deployed pin
66
+
67
+ The kit no longer ships `compaction.thresholdTokens`. omp's schema default
68
+ `-1` applies, and that sentinel selects the reserve-based branch.
66
69
 
67
70
  `ompYaml.ts` `mergeOmpConfig` is additive. Its `mergeMappings, deployed-key
68
71
  retention loop` returns every deployed key that the SoT omits to the merged
69
72
  output, and the only drop predicate is `dropFallbackWildcard`, which is scoped
70
- to `retry.fallbackChains`.
73
+ to `retry.fallbackChains`. A key deleted from the SoT therefore stays in every
74
+ already-deployed `~/.omp/agent/config.yml`.
71
75
 
72
- Deleting the key from the SoT would therefore leave the stale `231200` in
73
- every already-deployed `~/.omp/agent/config.yml` permanently. A present key
74
- holding the schema default sentinel `-1` overwrites that stale value on the
75
- next sync.
76
+ `ompRemovals.ts OMP_RETIRED_VALUES` therefore records both values that the kit
77
+ shipped: the former `231200` pin and the later `-1`. Sync prunes the deployed
78
+ key only while it holds one of these values, so a user value survives.
76
79
 
77
80
  Verify the deployed value after a sync:
78
81
 
@@ -80,7 +83,8 @@ Verify the deployed value after a sync:
80
83
  omp config get compaction.thresholdTokens
81
84
  ```
82
85
 
83
- The command must print `-1`.
86
+ The command must print `-1`, the omp default, unless the user set another
87
+ value.
84
88
 
85
89
  ## The clamp hazard a fixed pin carries
86
90
 
@@ -12,13 +12,12 @@ against.
12
12
  | `slow` | `anthropic/claude-opus-5-5` | xhigh | 56 | $3.46 | 136.30 s |
13
13
  | `plan` | `anthropic/claude-opus-5-5` | xhigh | 56 | $3.46 | 136.30 s |
14
14
  | `task` | `anthropic/claude-opus-5-5` | high | 54 | $1.82 | 52.85 s |
15
- | `advisor` | `anthropic/claude-opus-5-5` | medium | 51 | $1.34 | 21.87 s |
16
15
  | `designer` | `anthropic/claude-opus-5-5` | high | 54 | $1.82 | 52.85 s |
17
16
  | `vision` | `anthropic/claude-opus-5-5` | medium | 51 | $1.34 | 21.87 s |
18
17
  | `smol` / `commit` | `openai-codex/gpt-6-luna` | medium | 29 | $0.02 | n/a |
19
18
  | `tiny` | `openai-codex/gpt-6-luna` | low | 21 | $0.0045 | 2.18 s |
20
- | `fable` | `anthropic/claude-fable-5-1` | medium | 49 | $2.98 | 8.00 s |
21
- | `switch_fable` | `anthropic/claude-fable-5-1` | medium | 49 | $2.98 | 8.00 s |
19
+ | `fable` | `anthropic/claude-fable-5-2` | medium | 56 (v5.0.1) | $3.80 (v5.0.1) | 11.23 s (v5.0.1) |
20
+ | `switch_fable` | `anthropic/claude-fable-5-2` | medium | 56 (v5.0.1) | $3.80 (v5.0.1) | 11.23 s (v5.0.1) |
22
21
  | `astra` | `openai-codex/gpt-6-astra` | xhigh | 52 | $2.31 | 126.90 s |
23
22
  | `reviewer` | `openai-codex/gpt-6.1-terra` | high | 42 (v5.0.1) | $0.26 (v5.0.1) | 10.91 s (v5.0.1) |
24
23
  | `web` | `web/firecrawl` | n/a | n/a | n/a | n/a |
@@ -27,10 +26,11 @@ The table reports the measured Artificial Analysis figures for each assigned
27
26
  model and level. It states no motive that the config or omp's own
28
27
  documentation does not establish. AA has not measured output speed or latency
29
28
  for GPT-6 Luna medium, so that row carries `n/a` for TTFT. AA measures no web
30
- search provider, so the `web` row carries no figures. The `reviewer` row comes
31
- from a later capture at Intelligence Index v5.0.1. The 2026-09-29 capture
32
- predates GPT-6.1 Terra. Compare that row only with other v5.0.1 figures (see
33
- GPT-6.1 Terra below). A review benchmark chose the model of that role
29
+ search provider, so the `web` row carries no figures. The `reviewer`, `fable`,
30
+ and `switch_fable` rows come from later captures at Intelligence Index v5.0.1.
31
+ The 2026-09-29 capture predates GPT-6.1 Terra and Fable 5.2. Compare those
32
+ rows only with other v5.0.1 figures (see GPT-6.1 Terra and Claude Fable 5.2
33
+ below). A review benchmark chose the model of the `reviewer` role
34
34
  (DocksDocks/public#130), not these figures. The tier of that role follows the
35
35
  main session (DocksDocks/public#134).
36
36
 
@@ -116,7 +116,7 @@ missed two pre-registered bounds: escaped difference up to 3.26 (bound 2) and
116
116
  recall difference down to -0.07 (bound -0.05). Both intervals include 0, and
117
117
  the user judged the difference as noise.
118
118
 
119
- `retry.fallbackChains.astra` holds `anthropic/claude-fable-5-1:medium`.
119
+ `retry.fallbackChains.astra` holds `anthropic/claude-fable-5-2:medium`.
120
120
  `retry.fallbackChains.fable` holds `openai-codex/gpt-6-astra:xhigh`.
121
121
  Each deliberate cycle stop falls to the other vendor. Without these explicit
122
122
  chains, `retry.fallbackChains.default` would send either stop to
@@ -124,22 +124,21 @@ chains, `retry.fallbackChains.default` would send either stop to
124
124
  Chain entries are concrete selectors, not role aliases, so this pair cannot
125
125
  recurse. The hidden `switch_fable` chain stays empty.
126
126
 
127
- ### Why `advisor` runs Opus 5.5 medium
128
-
129
- `advisor` runs `anthropic/claude-opus-5-5:medium` with an empty fallback
130
- chain. On 2026-09-24, with omp 18.3.0, an Opus 5.5 session with the advisor
131
- on `openai-codex/gpt-6-sol:medium` looped. In one session the advisor made
132
- 1,313 requests for 140 main-agent requests. It issued 1,272 `read` calls on
133
- 248 distinct paths, read one 3-line slice 249 times, and never called
134
- `advise`. The advisor prompt averaged about 317k tokens, above the 272K
135
- window omp lists for GPT-6 Sol. With the advisor on Opus 5.5 medium, the
136
- same kind of session made about one advisor request per main-agent request
137
- and called `advise` normally. The owner excluded GPT-6 Sol from the advisor
138
- role and its fallback chain. On 2026-09-29 the owner extended the exclusion to
139
- every GPT model, including GPT-6.1 Sol and GPT-6 Astra. No GPT model was
140
- tested as the advisor again, and Astra costs too much for this role. Do not
141
- put an `openai-codex/gpt-*` selector in `modelRoles.advisor` or
142
- `retry.fallbackChains.advisor`.
127
+ ### Advisor removed
128
+
129
+ By owner decision (2026-11-12, 0.22.22), the kit sets no omp advisor.
130
+ `SoT/.omp/config.yml` has no `advisor` block, no `modelRoles.advisor`, and no
131
+ `retry.fallbackChains.advisor`. omp keeps the advisor off by default. The
132
+ plan-lifecycle verification loop takes its place: acceptance checks, a fresh
133
+ code review of the diff, and a round limit. Since 2026-11-01, 33 main
134
+ sessions had an advisor log, and no subagent session had one. A session that
135
+ runs `/advisor on` takes its advisor model from the `slow` role, because no
136
+ `advisor` role is set.
137
+
138
+ History: on 2026-09-24, with omp 18.3.0, an advisor on
139
+ `openai-codex/gpt-6-sol:medium` looped and made 1,313 requests for 140
140
+ main-agent requests. The kit then ran the advisor on Opus 5.5 `medium` and
141
+ excluded every GPT model from that role until this removal.
143
142
 
144
143
  `modelRoles.web` is `web/firecrawl`, and `retry.fallbackChains.web` lists the
145
144
  explicit 20-entry provider order that follows it. The two keys replace the
@@ -254,6 +253,34 @@ selector, so no kit role depends on that default. Runs on
254
253
  `anthropic/claude-opus-5-5:high` and `:max` after the prune answered with
255
254
  exit 0.
256
255
 
256
+ ### Claude Fable 5.2 (Anthropic) - `anthropic/claude-fable-5-2`
257
+
258
+ Source: `https://artificialanalysis.ai`, read on 2026-11-12 at Intelligence
259
+ Index v5.0.1, from the metric table of
260
+ `/models/comparisons/<level-slug>-vs-gpt-5-6-sol-high`. AA serves `max` under
261
+ the bare model slug. These figures use another index version than the rest of
262
+ this snapshot, so they do not compare with the v4.3.2 rows above. Compare them
263
+ with GPT-6.1 Terra below.
264
+
265
+ | Level | Index | Cost/task | Tokens/task | Index tokens | Speed t/s | TTFT s | TB 4.0 |
266
+ |---|---:|---:|---:|---:|---:|---:|---:|
267
+ | max | 65 | $26.54 | 274k | 275M | 98 | 262.29 | 60% |
268
+ | xhigh | 62 | $14.83 | 162k | 144M | 102 | 85.87 | 62% |
269
+ | high | 62 | $9.08 | 98k | 85M | 97 | 27.98 | 60% |
270
+ | medium | 56 | $3.80 | 43k | 41M | 93 | 11.23 | 55% |
271
+ | low | 54 | $3.10 | 36k | 35M | 97 | 8.42 | 55% |
272
+
273
+ Price: $8.00 in, $40.00 out, $0.20 cache hit per 1M. The omp catalog lists
274
+ the same prices, a $10.00 cache write, a 1M context, and 128K maximum output.
275
+ All AA levels run with default fallback. On 2026-11-12, omp 18.19.0 listed
276
+ `claude-fable-5-2` at low, medium, high, xhigh, and max, and an
277
+ `omp -p --mode json --model anthropic/claude-fable-5-2:medium` run recorded
278
+ `claude-fable-5-2` as the serving model.
279
+
280
+ `fable` and `switch_fable` moved from Fable 5.1 to Fable 5.2 at the same
281
+ level, `medium`. The Fable 5.1 table below stays as the previous-generation
282
+ baseline at v4.3.2.
283
+
257
284
  ### Claude Fable 5.1 (Anthropic) - `anthropic/claude-fable-5-1`
258
285
 
259
286
  | Level | Index | Cost/task | Tokens/task | Index tokens | Speed t/s | TTFT s | TB 4.0 |
@@ -442,18 +469,18 @@ quick answer.
442
469
  `thinking-level: auto`. It resolves Opus 5.5 high. The `:high` suffix on
443
470
  `modelRoles.task` is an explicit level, so it outranks the agent's `auto`,
444
471
  and the auto classifier does not run for a `task` spawn.
445
- - `task.enableEffort` is `false`, so the task tool has no `effort` field and
446
- every spawn runs the level of its agent's role. When the field is on, a
447
- caller can pass `effort: lo`, `med`, or `hi`, and caller effort outranks the
448
- role suffix. omp maps it onto the model's own ladder, not onto level names:
449
- `lo` selects the lowest level, `med` the lower middle, and `hi` the highest
450
- (`resolveTaskEffortLevel` in omp's `packages/tui/src/thinking.ts`,
451
- omp 18.8.5). Then omp caps the result at `task.maxEffort`. On the
452
- `low, medium, high, xhigh, max` ladder, `hi` gave `xhigh` under the
453
- `xhigh` cap, so many `task` spawns ran Opus 5.5 xhigh despite the `:high`
454
- role suffix. On 2026-11-05, a fresh `omp -p` run on omp 18.16.0 with the
455
- field off had no `effort` field, and its `task` child recorded
456
- `resolvedModel: anthropic/claude-opus-5-5:high`.
472
+ - `task.enableEffort` stays at omp's default `false`, so the task tool has no
473
+ `effort` field and every spawn runs the level of its agent's role. When the
474
+ field is on, a caller can pass `effort: lo`, `med`, or `hi`, and caller
475
+ effort outranks the role suffix. omp maps it onto the model's own ladder,
476
+ not onto level names: `lo` selects the lowest level, `med` the lower middle,
477
+ and `hi` the highest (`resolveTaskEffortLevel` in omp's
478
+ `packages/tui/src/thinking.ts`, omp 18.8.5). Then omp caps the result at
479
+ `task.maxEffort`. On the `low, medium, high, xhigh, max` ladder, `hi` gave
480
+ `xhigh` under the `xhigh` cap, so many `task` spawns ran Opus 5.5 xhigh
481
+ despite the `:high` role suffix. On 2026-11-05, a fresh `omp -p` run on omp
482
+ 18.16.0 with the field off had no `effort` field, and its `task` child
483
+ recorded `resolvedModel: anthropic/claude-opus-5-5:high`.
457
484
  - `task.maxEffort` is `xhigh`. With `task.enableEffort` off, the cap applies
458
485
  only to a per-call `model` with a `:level` suffix.
459
486
  - In the deployed config, `scout` and `sonic` run GPT-6 Luna `medium`. The
@@ -475,10 +502,13 @@ AA's 1M.
475
502
  `docks-kit omp [--model <selector>|--pick] [args...]` starts one interactive
476
503
  omp session with a configuration overlay that selects a free model. The
477
504
  overlay sets the 16 chat-model roles in `ompOverlay.ts ROLE_ORDER` to that
478
- model and empties the 13 retry fallback chains in `ompOverlay.ts
479
- FALLBACK_ORDER`. These roles include `memory` and `judge`. The SoT does
480
- not set them, but omp otherwise uses its built-in priority chain for them,
481
- and that chain can name a paid model. The overlay also empties the retry
505
+ model and empties the 12 retry fallback chains in `ompOverlay.ts
506
+ FALLBACK_ORDER`. These roles include `memory`, `judge`, and `advisor`. The SoT
507
+ does not set them, but omp otherwise uses its built-in priority chain for
508
+ `memory` and `judge`, and that chain can name a paid model. omp resolves the
509
+ `/advisor on` model from `modelRoles.advisor` before the `slow` role. A
510
+ deployed, user, or project `advisor` role could otherwise send it to a paid
511
+ model. The overlay also empties the retry
482
512
  chains keyed by the free model: the bare selector, `<selector>:off`, and
483
513
  `<selector>:<level>` for every level in `ompOverlay.ts THINKING_LADDER`. omp
484
514
  uses a chain keyed by the model before a role chain, so a project or
@@ -491,16 +521,16 @@ stays in the merged config. A retry of the free model does not reach such a
491
521
  chain, because omp uses the empty chain keyed by the free model first.
492
522
  The overlay also sets `defaultThinkingLevel` and `task.maxEffort`, except for
493
523
  a model that publishes no thinking ladder, where both keys are omitted and the
494
- deployed values apply.
524
+ deployed or omp default values apply.
495
525
 
496
526
  The launcher renders a run overlay to
497
527
  `~/.cache/docks-kit/omp-free-<model>-<digest>.yml` at mode 0600 and passes it
498
528
  through omp's repeatable `--config` flag. Each distinct model-and-level
499
529
  combination gets its own file, because omp re-reads a changed overlay during
500
- a live session, and a second launcher must not change the levels of that
530
+ a live session, and a second launcher must not change the level of that
501
531
  session. The name sanitizes the selector for the file system and appends a
502
- digest of the rendered overlay. The digest covers the selector and both
503
- levels, so two selectors that differ only in separator characters stay
532
+ digest of the rendered overlay. The digest covers the selector and the
533
+ level, so two selectors that differ only in separator characters stay
504
534
  apart. A session launch never reads or writes `~/.omp/agent/config.yml` or
505
535
  `models.yml`; only `--fast`, below, edits `config.yml`. It
506
536
  never touches the SoT. The next plain `omp` run uses the paid configuration
@@ -576,11 +606,9 @@ Spark 1.3 Free", 1,048,576-token context) at `xhigh`. `xhigh` is the ceiling
576
606
  of that model ladder: `minimal, low, medium, high, xhigh`. The paid
577
607
  `muse-spark-1.3` sibling also offers `max`. The free variant does not.
578
608
 
579
- Both levels come from the ladder of the chosen model, never from a fixed
580
- list. The session level is the ceiling of that ladder. The advisor level is
581
- the highest level at or below `medium`, because the advisor performs quick
582
- review passes. When every level of a ladder is above `medium`, the advisor
583
- takes the lowest level, so it never becomes the most expensive role.
609
+ The level comes from the ladder of the chosen model, never from a fixed list.
610
+ Every role, `advisor` included, runs the same level. Under `--model`, that
611
+ level is the ceiling of the ladder.
584
612
 
585
613
  Free ladders are not uniform. On 2026-09-11 the 26 free models published six
586
614
  distinct ladders: 21 include `medium`, 3 stop at `low, high, max` or
@@ -590,7 +618,7 @@ fail when the session starts.
590
618
 
591
619
  The choice persists per machine in `~/.docks-kit/kit.db` (table
592
620
  `omp_session`), next to the harness selection. It survives across sessions. It is never
593
- committed. `--model <selector>` records one selector and derives both levels
621
+ committed. `--model <selector>` records one selector and derives the level
594
622
  from the catalog row. `--pick` opens an interactive wizard.
595
623
 
596
624
  The picker lists only models the live `omp models --json` catalog reports at
@@ -598,31 +626,24 @@ zero input and output cost with `pricingStatus` `free` or `unknown` (26
598
626
  entries on 2026-09-11). A zero-cost row with another status, such as
599
627
  `variable` or `included`, is billed outside the token price, so the picker
600
628
  leaves it out. The resulting overlay sets the 16 `ROLE_ORDER` roles to the
601
- chosen free model and empties the 13 `FALLBACK_ORDER` chains and the chains
629
+ chosen free model and empties the 12 `FALLBACK_ORDER` chains and the chains
602
630
  keyed by that model. The `web` role, its chain, and each other deployed chain
603
631
  keep the deployed values. The
604
632
  catalog can advertise a free model that the account cannot call; omp reports
605
633
  that provider error unchanged.
606
634
 
607
- After the model, the wizard asks about thinking levels. `ompOverlay.ts
608
- planEffortChoice` decides which questions apply, because omp accepts a
635
+ After the model, the wizard asks about the thinking level. `ompOverlay.ts
636
+ planEffortChoice` decides whether the question applies, because omp accepts a
609
637
  `:level` suffix only for a level the chosen model publishes:
610
638
 
611
639
  - No ladder: the wizard asks nothing and the overlay omits every level.
612
640
  - One level: the wizard states that level and asks nothing.
613
- - Two or more levels: the wizard asks whether every role uses the same
614
- level. Yes takes the highest level the model offers. No asks one level for
615
- all roles except the advisor, then one level for the advisor.
616
-
617
- The advisor question leads with a recommendation from `ompOverlay.ts
618
- advisorRecommendation`: two steps down the model own ladder, clamped to the
619
- lowest level that model publishes. The recommendation is the first row
620
- because `Prompt.Select` starts on the first entry and accepts no initial
621
- index, so `Enter` takes it. The full ladder follows in ladder order. A
622
- recommendation equal to the chosen level is omitted rather than duplicated.
641
+ - Two or more levels: the wizard asks one question, the thinking level for
642
+ every role. It lists the levels of the model from the highest down, so
643
+ `Enter` keeps the highest level.
623
644
 
624
- A session whose advisor differs from the other roles reports both on the
625
- launch line.
645
+ The launch line names the selector and the level, or the model default level
646
+ for a model without a ladder. It reports no separate advisor level.
626
647
 
627
648
  An omp login is required. The kit owns no login flow. Every launch reads the
628
649
  live free catalog of each candidate profile. A plain launch checks the
@@ -647,9 +668,9 @@ stops the launcher before omp starts.
647
668
 
648
669
  When the catalog renames the free variant, change only the default selector
649
670
  constant. Until then, a plain launch on that default stops with an error. A
650
- ladder change needs no code change. Under `--model` both levels are derived
671
+ ladder change needs no code change. Under `--model` the level is derived
651
672
  from the catalog row of the chosen model, and under `--pick` the user chooses
652
- them from the ladder that same row publishes. Refresh the recorded default
673
+ it from the ladder that same row publishes. Refresh the recorded default
653
674
  and the ladder counts in these docs in the same commit.
654
675
 
655
676
  ## OpenAI fast mode (`docks-kit omp --fast`)
@@ -670,8 +691,8 @@ The four review agents inherit the live tier of the main session
670
691
  and on standard processing when it is `none`. A running session keeps the tier
671
692
  it started with, so its reviewers do not follow a later toggle.
672
693
 
673
- `--fast` never changes the Anthropic tier, and sync sets the deployed
674
- `tier.anthropic` to the SoT value `none`, so each session starts with it. In omp
694
+ `--fast` never changes the Anthropic tier. The SoT leaves `tier.anthropic` at
695
+ omp's default `none`, so each session starts with it. In omp
675
696
  18.16.0, `/fast on` in a session whose current
676
697
  model is Anthropic sets `anthropic: priority` for that session. The reviewers
677
698
  then inherit it, so their Opus 5.5 fallback also runs fast. omp has no
@@ -12,8 +12,6 @@ import {
12
12
  type OmpSessionModel,
13
13
  } from "../engine-native/harnesses";
14
14
  import {
15
- advisorLevelFor,
16
- advisorRecommendation,
17
15
  buildOmpArgs,
18
16
  ladderCeiling,
19
17
  ompChildEnvironment,
@@ -191,71 +189,39 @@ const loadFreeCatalog = (
191
189
  });
192
190
 
193
191
  /**
194
- * Ask for the thinking levels of one model. Every choice comes from that
192
+ * Ask for the thinking level of one model. Every choice comes from that
195
193
  * model own ladder, because omp rejects a `:level` suffix the model does not
196
194
  * publish. A model with no ladder and a model with one level are settled
197
- * without a question.
195
+ * without a question. Every role runs at the chosen level.
198
196
  */
199
- const pickLevels = (catalogModel: CatalogModel) =>
197
+ const pickLevel = (catalogModel: CatalogModel) =>
200
198
  Effect.gen(function* () {
201
199
  const plan = planEffortChoice(catalogModel.thinking);
202
200
  if (plan.kind === "none") {
203
201
  yield* Console.error(
204
202
  `${catalogModel.name} publishes no thinking levels; the model default applies`,
205
203
  );
206
- return { thinking: undefined, advisorThinking: undefined };
204
+ return undefined;
207
205
  }
208
206
  if (plan.kind === "fixed") {
209
207
  yield* Console.error(`${catalogModel.name} publishes one thinking level: ${plan.level}`);
210
- return { thinking: plan.level, advisorThinking: plan.level };
208
+ return plan.level;
211
209
  }
212
- const uniform = yield* Prompt.Select({
213
- message: "Use the same thinking level for every role?",
214
- choices: [
215
- {
216
- title: "Yes",
217
- value: true,
218
- description: `every role runs at ${plan.highest}, the highest this model offers`,
219
- },
220
- { title: "No", value: false, description: "set the advisor apart from the other roles" },
221
- ],
210
+ // Prompt.Select always starts on the first entry and offers no initial
211
+ // index, so the list runs highest first and Enter keeps the ceiling.
212
+ return yield* Prompt.Select({
213
+ message: "Thinking level for every role",
214
+ choices: [...plan.levels].reverse().map((level) => ({
215
+ title: level,
216
+ value: level,
217
+ description:
218
+ level === plan.highest
219
+ ? "highest this model offers"
220
+ : level === plan.levels[0]
221
+ ? "lowest this model offers"
222
+ : "",
223
+ })),
222
224
  });
223
- if (uniform) return { thinking: plan.highest, advisorThinking: plan.highest };
224
- const ladderChoices = plan.levels.map((level) => ({
225
- title: level,
226
- value: level,
227
- description:
228
- level === plan.highest
229
- ? "highest this model offers"
230
- : level === plan.levels[0]
231
- ? "lowest this model offers"
232
- : "",
233
- }));
234
- const thinking = yield* Prompt.Select({
235
- message: "Thinking level for all roles except the advisor",
236
- choices: ladderChoices,
237
- });
238
- const suggested = advisorRecommendation(plan.levels, thinking);
239
- // The list leads with the suggestion, because Prompt.Select always starts
240
- // on the first entry and offers no initial index. The full ladder follows
241
- // in ladder order, so a different level stays one keypress away. A
242
- // suggestion equal to the main level would only duplicate a row.
243
- const advisorChoices =
244
- suggested === undefined || suggested === thinking
245
- ? ladderChoices
246
- : [
247
- {
248
- title: suggested,
249
- value: suggested,
250
- description: `recommended, two levels below ${thinking}`,
251
- },
252
- ...ladderChoices,
253
- ];
254
- const advisorThinking = yield* Prompt.Select({
255
- message: "Thinking level for the advisor role",
256
- choices: advisorChoices,
257
- });
258
- return { thinking, advisorThinking };
259
225
  });
260
226
 
261
227
  /**
@@ -364,7 +330,6 @@ export const ompCommand = Command.make("omp", { model, pick, fast, args }, (conf
364
330
  chosen = {
365
331
  selector: resolved.model.selector,
366
332
  thinking: ladderCeiling(resolved.model.thinking),
367
- advisorThinking: advisorLevelFor(resolved.model.thinking),
368
333
  };
369
334
  }
370
335
 
@@ -387,12 +352,7 @@ export const ompCommand = Command.make("omp", { model, pick, fast, args }, (conf
387
352
  if (match === undefined) {
388
353
  return yield* bail(`Model '${pickedSelector}' is not in the free catalog`);
389
354
  }
390
- const chosenLevels = yield* pickLevels(match);
391
- chosen = {
392
- selector: match.selector,
393
- thinking: chosenLevels.thinking,
394
- advisorThinking: chosenLevels.advisorThinking,
395
- };
355
+ chosen = { selector: match.selector, thinking: yield* pickLevel(match) };
396
356
  }
397
357
 
398
358
  const session: OmpSessionModel =
@@ -427,21 +387,13 @@ export const ompCommand = Command.make("omp", { model, pick, fast, args }, (conf
427
387
  });
428
388
 
429
389
  // A level-free model states the model default so the line never shows
430
- // an undefined level. The advisor appears only when it differs, because
431
- // a uniform session has nothing extra to report.
432
- const level =
433
- typeof session.thinking === "string" && session.thinking.trim() !== ""
434
- ? session.thinking
435
- : undefined;
436
- const advisor =
437
- typeof session.advisorThinking === "string" && session.advisorThinking.trim() !== ""
438
- ? session.advisorThinking
439
- : undefined;
390
+ // an undefined level.
440
391
  const levelText =
441
- level === undefined ? "the model default thinking level" : `${level} thinking`;
442
- const advisorText = advisor !== undefined && advisor !== level ? `, advisor at ${advisor}` : "";
392
+ typeof session.thinking === "string" && session.thinking.trim() !== ""
393
+ ? `${session.thinking} thinking`
394
+ : "the model default thinking level";
443
395
  yield* Console.error(
444
- `Starting omp with ${session.selector} at ${levelText}${advisorText} (session only; deployed config unchanged)`,
396
+ `Starting omp with ${session.selector} at ${levelText} (session only; deployed config unchanged)`,
445
397
  );
446
398
 
447
399
  // An exported model variable would set its role above the overlay, so the
@@ -18,7 +18,6 @@ export type { OmpSessionModel };
18
18
  export const DEFAULT_OMP_SESSION_MODEL: OmpSessionModel = {
19
19
  selector: "opencode-zen/muse-spark-1.3-contributor-free",
20
20
  thinking: "xhigh",
21
- advisorThinking: "medium",
22
21
  };
23
22
 
24
23
  function isHarness(value: unknown): value is Harness {
@@ -104,17 +103,13 @@ export function writeHarnessSelection(home: string, selection: ReadonlyArray<Har
104
103
  export function readOmpSessionModel(home: string): OmpSessionModel | undefined {
105
104
  try {
106
105
  return withKitDb(home, "read", (db) => {
107
- const row = db
108
- .prepare("SELECT selector, thinking, advisor_thinking FROM omp_session WHERE id = 1")
109
- .get();
106
+ const row = db.prepare("SELECT selector, thinking FROM omp_session WHERE id = 1").get();
110
107
  const selector = row?.["selector"];
111
108
  if (!isNonBlankString(selector)) return undefined;
112
109
  const thinking = row?.["thinking"];
113
- const advisorThinking = row?.["advisor_thinking"];
114
110
  const model: OmpSessionModel = {
115
111
  selector,
116
112
  ...(isNonBlankString(thinking) ? { thinking } : {}),
117
- ...(isNonBlankString(advisorThinking) ? { advisorThinking } : {}),
118
113
  };
119
114
  return model;
120
115
  });
@@ -129,16 +124,15 @@ export function writeOmpSessionModel(home: string, model: OmpSessionModel): void
129
124
  if (!isNonBlankString(model.selector)) {
130
125
  throw new Error("Omp session model selector must be a non-empty string");
131
126
  }
132
- // Store blank or absent levels as NULL so a switch to a level-free model
127
+ // Store a blank or absent level as NULL so a switch to a level-free model
133
128
  // leaves no stale level behind.
134
129
  const thinking = nonBlankOrNull(model.thinking);
135
- const advisorThinking = nonBlankOrNull(model.advisorThinking);
136
130
  withKitDb(home, "write", (db) =>
137
131
  db
138
132
  .prepare(
139
- `INSERT INTO omp_session (id, selector, thinking, advisor_thinking) VALUES (1, ?, ?, ?)
140
- ON CONFLICT(id) DO UPDATE SET selector = excluded.selector, thinking = excluded.thinking, advisor_thinking = excluded.advisor_thinking`,
133
+ `INSERT INTO omp_session (id, selector, thinking) VALUES (1, ?, ?)
134
+ ON CONFLICT(id) DO UPDATE SET selector = excluded.selector, thinking = excluded.thinking`,
141
135
  )
142
- .run(model.selector, thinking, advisorThinking),
136
+ .run(model.selector, thinking),
143
137
  );
144
138
  }
@@ -16,6 +16,8 @@ import { p } from "./exec";
16
16
  * because every row can be refetched.
17
17
  */
18
18
  const MIGRATIONS: ReadonlyArray<string> = [
19
+ // omp_session.advisor_thinking has had no use since 0.22.22. It stays only
20
+ // to keep schema 1, which older kits still open; nothing reads or writes it.
19
21
  `CREATE TABLE harness_selection (
20
22
  harness TEXT PRIMARY KEY CHECK (harness IN ('claude','codex','agents','omp'))
21
23
  ) STRICT, WITHOUT ROWID;
@@ -88,7 +90,7 @@ function migrate(db: DatabaseSync): boolean {
88
90
 
89
91
  interface LegacyState {
90
92
  readonly harnesses: ReadonlyArray<string>;
91
- readonly session?: { selector: string; thinking: string | null; advisorThinking: string | null };
93
+ readonly session?: { selector: string; thinking: string | null };
92
94
  }
93
95
 
94
96
  export function isNonBlankString(value: unknown): value is string {
@@ -126,9 +128,6 @@ function parseLegacyState(file: string): LegacyState | undefined {
126
128
  session: {
127
129
  selector,
128
130
  thinking: nonBlankOrNull("thinking" in entry ? entry.thinking : undefined),
129
- advisorThinking: nonBlankOrNull(
130
- "advisorThinking" in entry ? entry.advisorThinking : undefined,
131
- ),
132
131
  },
133
132
  };
134
133
  }
@@ -148,9 +147,10 @@ function importLegacyState(db: DatabaseSync, legacy: string): void {
148
147
  );
149
148
  for (const harness of state.harnesses) insertHarness.run(harness);
150
149
  if (state.session !== undefined) {
151
- db.prepare(
152
- "INSERT INTO omp_session (id, selector, thinking, advisor_thinking) VALUES (1, ?, ?, ?)",
153
- ).run(state.session.selector, state.session.thinking, state.session.advisorThinking);
150
+ db.prepare("INSERT INTO omp_session (id, selector, thinking) VALUES (1, ?, ?)").run(
151
+ state.session.selector,
152
+ state.session.thinking,
153
+ );
154
154
  }
155
155
  });
156
156
  // An invalid file is renamed too, so no later run parses it again.
@@ -1,14 +1,14 @@
1
1
  /**
2
2
  * Run overlay for `docks-kit omp`. The overlay merges over the deployed omp
3
3
  * config for one run only. It sets the 16 roles in ROLE_ORDER to the free
4
- * model and empties the 13 retry chains in FALLBACK_ORDER and the chains keyed
4
+ * model and empties the 12 retry chains in FALLBACK_ORDER and the chains keyed
5
5
  * by the free model. omp merges the overlay key by key, so each deployed retry
6
6
  * chain that is not in FALLBACK_ORDER stays as deployed. The `web` role and
7
7
  * its retry chain are not in the overlay, so the deployed web-search provider
8
8
  * order applies, and that order can include a paid chat model. A deployed
9
- * `plan`, `slow`, or `designer` chain also stays, but a retry of the free
10
- * model uses the empty chain keyed by that model first. Every other key falls
11
- * through to the deployed config.
9
+ * `advisor`, `plan`, `slow`, or `designer` chain also stays, but a retry of
10
+ * the free model uses the empty chain keyed by that model first. Every other
11
+ * key falls through to the deployed config.
12
12
  */
13
13
  import { createHash } from "node:crypto";
14
14
  import { delimiter } from "node:path";
@@ -35,7 +35,7 @@ export const THINKING_LADDER: ReadonlyArray<string> = [
35
35
  * One overlay file per distinct model and level combination, so a second
36
36
  * launcher cannot rewrite the file a running session still reads. omp
37
37
  * reloads a changed overlay mid-session, so the digest covers the exact
38
- * rendered overlay: the selector, both levels, and every rendered key. A
38
+ * rendered overlay: the selector, the level, and every rendered key. A
39
39
  * selector carries a slash and may carry other characters a host rejects in
40
40
  * a file name, so unsafe characters in the readable prefix become hyphens.
41
41
  */
@@ -47,14 +47,16 @@ export function overlayFileName(model: OmpSessionModel): string {
47
47
 
48
48
  /**
49
49
  * Role keys in the order used by SoT/.omp/config.yml for readable diffs. The
50
- * SoT does not set `memory` and `judge`, so they come last. An unset role
51
- * falls back to the omp built-in priority chain, which can name a paid model.
52
- * The `web` role is left out on purpose, so the deployed web-search provider
53
- * order applies.
50
+ * SoT does not set `advisor`, `memory`, and `judge`, so they come last. An
51
+ * unset role falls back to the omp built-in priority chain, which can name a
52
+ * paid model. omp takes the `/advisor on` model from the `advisor` role and
53
+ * uses `slow` only when that role is unset, so the overlay pins `advisor`
54
+ * too: a deployed or project advisor role would otherwise send the advisor
55
+ * to a paid model. The `web` role is left out on purpose, so the
56
+ * deployed web-search provider order applies.
54
57
  */
55
58
  const ROLE_ORDER: ReadonlyArray<string> = [
56
59
  "smol",
57
- "advisor",
58
60
  "designer",
59
61
  "plan",
60
62
  "commit",
@@ -67,6 +69,7 @@ const ROLE_ORDER: ReadonlyArray<string> = [
67
69
  "switch_fable",
68
70
  "astra",
69
71
  "reviewer",
72
+ "advisor",
70
73
  "memory",
71
74
  "judge",
72
75
  ];
@@ -78,7 +81,6 @@ const ROLE_ORDER: ReadonlyArray<string> = [
78
81
  */
79
82
  const FALLBACK_ORDER: ReadonlyArray<string> = [
80
83
  "default",
81
- "advisor",
82
84
  "task",
83
85
  "vision",
84
86
  "smol",
@@ -147,29 +149,12 @@ export function ladderCeiling(levels: ReadonlyArray<string>): string | undefined
147
149
  return undefined;
148
150
  }
149
151
 
150
- /**
151
- * Resolve the advisor level from the model own ladder. The advisor runs
152
- * quick review passes, so it takes the highest level at or below medium,
153
- * and the lowest level when the ladder starts above medium. The result
154
- * never exceeds the ladder ceiling by construction.
155
- */
156
- export function advisorLevelFor(levels: ReadonlyArray<string>): string | undefined {
157
- const known = THINKING_LADDER.filter((level) => levels.includes(level));
158
- if (known.length === 0) return undefined;
159
- const mediumIndex = THINKING_LADDER.indexOf("medium");
160
- let advisor: string | undefined;
161
- for (const level of known) {
162
- if ((THINKING_LADDER.indexOf(level) as number) <= (mediumIndex as number)) advisor = level;
163
- }
164
- return advisor ?? (known[0] as string);
165
- }
166
-
167
152
  /**
168
153
  * What the picker may ask about thinking levels for one model. omp accepts a
169
154
  * `:level` suffix on a role only for a level the model publishes, so the
170
155
  * question set comes from the model own ladder: no ladder means no question,
171
- * a single level means no choice to make, and two or more levels mean the
172
- * user can split the advisor from the other roles.
156
+ * a single level means no choice to make, and two or more levels mean one
157
+ * level choice for every role.
173
158
  */
174
159
  export type EffortPlan =
175
160
  | { readonly kind: "none" }
@@ -184,39 +169,19 @@ export function planEffortChoice(levels: ReadonlyArray<string>): EffortPlan {
184
169
  return { kind: "choose", levels: known, highest: known[known.length - 1] as string };
185
170
  }
186
171
 
187
- /**
188
- * Recommend an advisor level for a chosen main level. The advisor runs quick
189
- * review passes, so it sits two steps down the model own ladder, and it
190
- * clamps to the lowest level the model publishes. Steps count positions in
191
- * that model ladder, not the global ladder, so a sparse ladder such as
192
- * `high, max` still recommends a real level.
193
- */
194
- export function advisorRecommendation(
195
- levels: ReadonlyArray<string>,
196
- main: string,
197
- ): string | undefined {
198
- const known = THINKING_LADDER.filter((level) => levels.includes(level));
199
- const index = known.indexOf(main);
200
- if (index < 0) return known[0];
201
- return known[Math.max(0, index - 2)];
202
- }
203
-
204
172
  /** A thinking level the overlay can render, or undefined for a blank one. */
205
173
  function renderableLevel(level: string | undefined): string | undefined {
206
174
  return typeof level === "string" && level.trim() !== "" ? level : undefined;
207
175
  }
208
176
 
209
177
  /**
210
- * The value the overlay gives one role. The overlay, the session `--model`,
178
+ * The value the overlay gives every role. The overlay, the session `--model`,
211
179
  * and the child environment all use it, so the three cannot drift apart. A
212
180
  * model without a level gets the bare selector so the deployed level applies.
213
181
  */
214
- function roleValue(model: OmpSessionModel, role: string): string {
182
+ function roleValue(model: OmpSessionModel): string {
215
183
  const thinking = renderableLevel(model.thinking);
216
- if (thinking === undefined) return model.selector;
217
- const level =
218
- role === "advisor" ? (renderableLevel(model.advisorThinking) ?? thinking) : thinking;
219
- return `${model.selector}:${level}`;
184
+ return thinking === undefined ? model.selector : `${model.selector}:${thinking}`;
220
185
  }
221
186
 
222
187
  /**
@@ -230,7 +195,7 @@ export function renderFreeOverlay(model: OmpSessionModel): string {
230
195
  if (thinking !== undefined) lines.push(`defaultThinkingLevel: ${thinking}`);
231
196
  lines.push("modelRoles:");
232
197
  for (const role of ROLE_ORDER) {
233
- lines.push(` ${role}: ${roleValue(model, role)}`);
198
+ lines.push(` ${role}: ${roleValue(model)}`);
234
199
  }
235
200
  if (thinking !== undefined) lines.push("task:", ` maxEffort: ${thinking}`);
236
201
  lines.push("retry:", " fallbackChains:");
@@ -258,22 +223,11 @@ export function buildOmpArgs(
258
223
  session: OmpSessionModel,
259
224
  passthrough: ReadonlyArray<string>,
260
225
  ): ReadonlyArray<string> {
261
- return [
262
- "launch",
263
- "--config",
264
- overlayPath,
265
- "--model",
266
- roleValue(session, "default"),
267
- ...passthrough,
268
- ];
226
+ return ["launch", "--config", overlayPath, "--model", roleValue(session), ...passthrough];
269
227
  }
270
228
 
271
229
  // Variables that omp reads at launch to set a role above every config layer.
272
- const MODEL_ENV_ROLES: ReadonlyArray<readonly [string, string]> = [
273
- ["PI_SMOL_MODEL", "smol"],
274
- ["PI_SLOW_MODEL", "slow"],
275
- ["PI_PLAN_MODEL", "plan"],
276
- ];
230
+ const MODEL_ENV_NAMES: ReadonlyArray<string> = ["PI_SMOL_MODEL", "PI_SLOW_MODEL", "PI_PLAN_MODEL"];
277
231
 
278
232
  export interface OmpChildEnvironment {
279
233
  readonly env: Record<string, string | undefined>;
@@ -300,8 +254,8 @@ export function ompChildEnvironment(
300
254
  PI_CONFIG_FILES: [...inherited, overlayPath].join(delimiter),
301
255
  };
302
256
  const replaced: Array<string> = [];
303
- for (const [name, role] of MODEL_ENV_ROLES) {
304
- const value = roleValue(session, role);
257
+ const value = roleValue(session);
258
+ for (const name of MODEL_ENV_NAMES) {
305
259
  const previous = parent[name];
306
260
  if (previous !== undefined && previous !== "" && previous !== value) replaced.push(name);
307
261
  env[name] = value;
@@ -17,18 +17,31 @@ import type { Ctx } from "./index";
17
17
  import { backupPrivateFile } from "./ompFileDeploy";
18
18
  import { bashPatternKey, bashRuleKey } from "./ompYaml";
19
19
 
20
- type RetiredScalar = string | number | boolean;
20
+ /** A retired leaf value: a scalar, or a sequence the kit shipped as one value. */
21
+ type RetiredValue = string | number | boolean | ReadonlyArray<string>;
21
22
 
22
23
  /**
23
24
  * Keys the kit used to deploy, each paired with the exact value it deployed. A
24
25
  * key is pruned only while the deployed value still equals that value, so a
25
- * user who changed the setting keeps it. Every recorded value except
26
- * `retry.usageAwareFallback` also equals omp's current default, so pruning those
27
- * changes no behavior today and lets a later upstream default change take
28
- * effect. Pruning `retry.usageAwareFallback: true` restores omp's default
29
- * `false`, which removes the coding-plan reserve prompt.
26
+ * user who changed the setting keeps it. A key listed twice shipped both
27
+ * values at different times.
28
+ *
29
+ * Most recorded values equal omp's current default, so pruning them changes no
30
+ * behavior today and lets a later upstream default change take effect. These
31
+ * entries differ from the default, and pruning them is intended:
32
+ * - `retry.usageAwareFallback: true` restores omp's default `false`, which
33
+ * removes the coding-plan reserve prompt.
34
+ * - `advisor.enabled: true` and `advisor.syncBacklog: "1"` (defaults `false`
35
+ * and `"off"`), `modelRoles.advisor`, and the empty
36
+ * `retry.fallbackChains.advisor` chain: the owner removed the advisor. omp
37
+ * keeps it off, and an `/advisor on` session runs on the `slow` role.
38
+ * - `codexResets.autoRedeem: "no"`: omp migrates this legacy key in memory to
39
+ * `autoRedeem5h` and `autoRedeemWeekly`, which the SoT now declares with the
40
+ * same value.
41
+ * - `compaction.thresholdTokens: 231200`: an old fixed compaction trigger.
42
+ * Pruning it restores omp's reserve-based default `-1`.
30
43
  */
31
- const OMP_RETIRED_VALUES: ReadonlyArray<readonly [string, RetiredScalar]> = [
44
+ export const OMP_RETIRED_VALUES: ReadonlyArray<readonly [string, RetiredValue]> = [
32
45
  ["symbolPreset", "unicode"],
33
46
  ["theme.dark", "titanium"],
34
47
  ["statusLine.preset", "default"],
@@ -48,6 +61,30 @@ const OMP_RETIRED_VALUES: ReadonlyArray<readonly [string, RetiredScalar]> = [
48
61
  ["autoResume", false],
49
62
  ["startup.changelogMode", "summary"],
50
63
  ["retry.usageAwareFallback", true],
64
+ ["defaultThinkingLevel", "high"],
65
+ ["tier.anthropic", "none"],
66
+ ["advisor.enabled", true],
67
+ ["advisor.enabled", false],
68
+ ["advisor.syncBacklog", "1"],
69
+ ["task.softRequestBudget", 200],
70
+ ["task.softRequestBudgetNotice", true],
71
+ ["task.batch", true],
72
+ ["task.enableEffort", false],
73
+ ["task.maxRecursionDepth", 2],
74
+ ["modelRoles.advisor", "anthropic/claude-opus-5-5:medium"],
75
+ ["providers.anthropic.serverSideFallback", false],
76
+ ["providers.fetch", "auto"],
77
+ ["retry.fallbackChains.advisor", []],
78
+ ["includeWorkspaceTree", false],
79
+ ["commands.enableOpencodeUser", false],
80
+ ["skills.enableClaudeUser", false],
81
+ ["skills.enableCodexUser", false],
82
+ ["skills.enableAgentsUser", true],
83
+ ["compaction.thresholdTokens", -1],
84
+ ["compaction.thresholdTokens", 231200],
85
+ ["textVerbosity", "low"],
86
+ ["codexResets.autoRedeem", "no"],
87
+ ["tools.approvalMode", "yolo"],
51
88
  ];
52
89
 
53
90
  /**
@@ -352,7 +389,9 @@ export function syncOmpRemovals(ctx: Ctx, configFile: string, alreadyBackedUp: b
352
389
  retiredKeys([
353
390
  ...OMP_RETIRED_VALUES.map(([path, value]): RetiredEntry => [
354
391
  path,
355
- (node) => isScalar(node) && node.value === value,
392
+ Array.isArray(value)
393
+ ? (node) => isSeq(node) && isDeepStrictEqual(node.toJSON(), value)
394
+ : (node) => isScalar(node) && node.value === value,
356
395
  ]),
357
396
  ...OMP_RETIRED_KEYS.map((path): RetiredEntry => [path, () => true]),
358
397
  ]),
@@ -47,8 +47,6 @@ export interface OmpSessionModel {
47
47
  // Session ceiling; absent when the model publishes no ladder, so no
48
48
  // invented level ever reaches a selector that omp must resolve.
49
49
  readonly thinking?: string;
50
- // Advisor level; absent when the model publishes no ladder.
51
- readonly advisorThinking?: string;
52
50
  }
53
51
 
54
52
  /**
@@ -1,7 +1,7 @@
1
1
  // Generated by cli/scripts/generate-sot-payload.ts. DO NOT EDIT.
2
2
  // Edit SoT/, notification.mp3, or package.json, then run: bun cli/scripts/generate-sot-payload.ts
3
3
 
4
- export const GENERATED_PACKAGE_VERSION = "0.22.20"
4
+ export const GENERATED_PACKAGE_VERSION = "0.22.22"
5
5
 
6
6
  export const GENERATED_PAYLOAD_TEXT = {
7
7
  "SoT/.agents/skills.txt": "# Universal AI-agent skill manifest intentionally empty.\n# Global skill discovery is opt-in: add one slug per installed skill: <owner>/<repo>@<skill-name> (or a path to one skill directory).\n# EngineNative ignores comments and blank lines.\n",
@@ -18,7 +18,7 @@ export const GENERATED_PAYLOAD_TEXT = {
18
18
  "SoT/.codex/plugins/marketplace.json": "{\n \"name\": \"docks\",\n \"interface\": {\n \"displayName\": \"DocksDocks\"\n },\n \"plugins\": [\n {\n \"name\": \"docks\",\n \"source\": {\n \"source\": \"git-subdir\",\n \"url\": \"https://github.com/DocksDocks/docks.git\",\n \"path\": \"./plugins/docks\",\n \"ref\": \"main\"\n },\n \"policy\": {\n \"installation\": \"AVAILABLE\",\n \"authentication\": \"ON_INSTALL\"\n },\n \"category\": \"Productivity\"\n },\n {\n \"name\": \"plan-lifecycle\",\n \"source\": {\n \"source\": \"git-subdir\",\n \"url\": \"https://github.com/DocksDocks/docks.git\",\n \"path\": \"./plugins/plan-lifecycle\",\n \"ref\": \"main\"\n },\n \"policy\": {\n \"installation\": \"AVAILABLE\",\n \"authentication\": \"ON_INSTALL\"\n },\n \"category\": \"Productivity\"\n }\n ]\n}\n",
19
19
  "SoT/.codex/rules/docks.rules": "prefix_rule(pattern=[\"pwd\"], decision=\"allow\")\nprefix_rule(pattern=[\"ls\"], decision=\"allow\")\nprefix_rule(pattern=[\"cat\"], decision=\"allow\")\nprefix_rule(pattern=[\"head\"], decision=\"allow\")\nprefix_rule(pattern=[\"tail\"], decision=\"allow\")\nprefix_rule(pattern=[\"wc\"], decision=\"allow\")\nprefix_rule(pattern=[\"nl\"], decision=\"allow\")\nprefix_rule(pattern=[\"grep\"], decision=\"allow\")\nprefix_rule(pattern=[\"diff\"], decision=\"allow\")\nprefix_rule(pattern=[\"which\"], decision=\"allow\")\nprefix_rule(pattern=[\"date\"], decision=\"allow\")\nprefix_rule(pattern=[\"basename\"], decision=\"allow\")\nprefix_rule(pattern=[\"dirname\"], decision=\"allow\")\nprefix_rule(pattern=[\"realpath\"], decision=\"allow\")\nprefix_rule(pattern=[\"readlink\"], decision=\"allow\")\nprefix_rule(pattern=[\"jq\"], decision=\"allow\")\nprefix_rule(pattern=[\"cut\"], decision=\"allow\")\nprefix_rule(pattern=[\"tr\"], decision=\"allow\")\nprefix_rule(pattern=[\"echo\"], decision=\"allow\")\nprefix_rule(pattern=[\"printf\"], decision=\"allow\")\nprefix_rule(pattern=[\"printenv\"], decision=\"allow\")\nprefix_rule(pattern=[\"uname\"], decision=\"allow\")\nprefix_rule(pattern=[\"file\"], decision=\"allow\")\nprefix_rule(pattern=[\"stat\"], decision=\"allow\")\nprefix_rule(pattern=[\"du\"], decision=\"allow\")\nprefix_rule(pattern=[\"id\"], decision=\"allow\")\nprefix_rule(pattern=[\"whoami\"], decision=\"allow\")\n\nprefix_rule(pattern=[\"git\", \"status\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"blame\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"rev-parse\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"ls-files\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"ls-tree\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"branch\", \"--show-current\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"branch\", \"-vv\"], decision=\"allow\")\n\nprefix_rule(pattern=[\"gh\", \"pr\", \"view\"], decision=\"allow\")\nprefix_rule(pattern=[\"gh\", \"pr\", \"list\"], decision=\"allow\")\nprefix_rule(pattern=[\"gh\", \"pr\", \"diff\"], decision=\"allow\")\nprefix_rule(pattern=[\"gh\", \"pr\", \"status\"], decision=\"allow\")\nprefix_rule(pattern=[\"gh\", \"pr\", \"checks\"], decision=\"allow\")\n\nprefix_rule(pattern=[\"docker\", \"ps\"], decision=\"allow\")\n\nprefix_rule(pattern=[\"git\", \"push\"], decision=\"prompt\")\nprefix_rule(pattern=[\"git\", \"reset\"], decision=\"prompt\")\nprefix_rule(pattern=[\"git\", \"clean\"], decision=\"prompt\")\nprefix_rule(pattern=[\"git\", \"merge\"], decision=\"prompt\")\nprefix_rule(pattern=[\"git\", \"rebase\"], decision=\"prompt\")\nprefix_rule(pattern=[\"git\", \"checkout\"], decision=\"prompt\")\nprefix_rule(pattern=[\"git\", \"mv\"], decision=\"prompt\")\n\nprefix_rule(pattern=[\"rm\"], decision=\"prompt\")\nprefix_rule(pattern=[\"mv\"], decision=\"prompt\")\nprefix_rule(pattern=[\"chmod\"], decision=\"prompt\")\nprefix_rule(pattern=[\"chown\"], decision=\"prompt\")\nprefix_rule(pattern=[\"kill\"], decision=\"prompt\")\nprefix_rule(pattern=[\"pkill\"], decision=\"prompt\")\n\nprefix_rule(pattern=[\"npm\", \"install\"], decision=\"prompt\")\nprefix_rule(pattern=[\"npm\", \"uninstall\"], decision=\"prompt\")\nprefix_rule(pattern=[\"pnpm\", \"add\"], decision=\"prompt\")\nprefix_rule(pattern=[\"pnpm\", \"remove\"], decision=\"prompt\")\nprefix_rule(pattern=[\"yarn\", \"add\"], decision=\"prompt\")\nprefix_rule(pattern=[\"yarn\", \"remove\"], decision=\"prompt\")\nprefix_rule(pattern=[\"pip\", \"install\"], decision=\"prompt\")\nprefix_rule(pattern=[\"pip\", \"uninstall\"], decision=\"prompt\")\nprefix_rule(pattern=[\"pip3\", \"install\"], decision=\"prompt\")\nprefix_rule(pattern=[\"pip3\", \"uninstall\"], decision=\"prompt\")\n\nprefix_rule(pattern=[\"docker\", \"run\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"rm\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"stop\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"volume\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"system\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"compose\", \"up\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"compose\", \"down\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"compose\", \"rm\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"compose\", \"stop\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker-compose\", \"up\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker-compose\", \"down\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker-compose\", \"rm\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker-compose\", \"stop\"], decision=\"prompt\")\n\n# `tail -f`/`--follow` never returns and hangs the agent (bare `tail` stays allowed above).\nprefix_rule(pattern=[\"tail\", \"-f\"], decision=\"prompt\")\nprefix_rule(pattern=[\"tail\", \"--follow\"], decision=\"prompt\")\n# These commands are prompt or absent, NOT allow, because argv-prefix matching\n# cannot gate a later write or exec flag, and allow runs outside the sandbox:\n# rg --pre=CMD; sed -n 'e CMD' or -ni; sort -o FILE or --compress-program=CMD;\n# the uniq OUTPUT operand; tree -o FILE; git diff/log/show --output=FILE;\n# git grep --open-files-in-pager=CMD or -O; git mv into .git/hooks.\n# Without a rule, sort, uniq, tree, git diff/log/show, and git grep run in the\n# sandbox with no prompt.\nprefix_rule(pattern=[\"rg\"], decision=\"prompt\")\nprefix_rule(pattern=[\"sed\", \"-n\"], decision=\"prompt\")\nprefix_rule(pattern=[\"find\"], decision=\"prompt\")\nprefix_rule(pattern=[\"sed\", \"-i\"], decision=\"prompt\")\nprefix_rule(pattern=[\"sed\", \"--in-place\"], decision=\"prompt\")\nprefix_rule(pattern=[\"awk\"], decision=\"prompt\")\nprefix_rule(pattern=[\"xargs\"], decision=\"prompt\")\nprefix_rule(pattern=[\"tee\"], decision=\"prompt\")\nprefix_rule(pattern=[\"curl\"], decision=\"prompt\")\nprefix_rule(pattern=[\"env\"], decision=\"prompt\")\n\nprefix_rule(pattern=[\"sudo\"], decision=\"forbidden\")\nprefix_rule(pattern=[\"eval\"], decision=\"forbidden\")\nprefix_rule(pattern=[\"mkfs\"], decision=\"forbidden\")\nprefix_rule(pattern=[\"dd\"], decision=\"forbidden\")\nprefix_rule(pattern=[\"git\", \"push\", \"--force\", \"origin\", \"main\"], decision=\"forbidden\")\nprefix_rule(pattern=[\"git\", \"push\", \"--force\", \"origin\", \"master\"], decision=\"forbidden\")\nprefix_rule(pattern=[\"git\", \"push\", \"-f\", \"origin\", \"main\"], decision=\"forbidden\")\nprefix_rule(pattern=[\"git\", \"push\", \"-f\", \"origin\", \"master\"], decision=\"forbidden\")\n\n# Destructive-command guards. Codex applies the strictest matching rule\n# (forbidden > prompt > allow), so an allow rule in another .rules file cannot\n# loosen them, and a narrow allow cannot carve an exception out of a prompt.\n# The rm, find, git push, git reset, and git clean prompt rules above already\n# make every recursive or bulk deletion and every history-destroying git\n# command prompt. Codex prefix rules cannot see an option after an operand,\n# so every rm prompts, a single-file rm too. A prompt goes to the approvals\n# reviewer in config.toml (auto_review), not always to a person.\n#\n# rm of the filesystem root as Codex runs it: argv tokens, or a plain script\n# that Codex splits into argv tokens.\nprefix_rule(pattern=[\"rm\", \"/\"], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[\"rm\", [\"-r\", \"-R\", \"-f\", \"-rf\", \"-fr\", \"-Rf\", \"-fR\", \"-rfv\", \"-vrf\", \"-v\", \"--recursive\", \"--force\", \"--no-preserve-root\", \"--\"], \"/\"], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[\"rm\", [\"-r\", \"-R\", \"-f\", \"-rf\", \"-fr\", \"-Rf\", \"-fR\", \"-rfv\", \"-vrf\", \"-v\", \"--recursive\", \"--force\", \"--no-preserve-root\", \"--\"], [\"-r\", \"-R\", \"-f\", \"-rf\", \"-fr\", \"-Rf\", \"-fR\", \"-rfv\", \"-vrf\", \"-v\", \"--recursive\", \"--force\", \"--no-preserve-root\", \"--\"], \"/\"], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[\"rm\", [\"-r\", \"-R\", \"-f\", \"-rf\", \"-fr\", \"-Rf\", \"-fR\", \"-rfv\", \"-vrf\", \"-v\", \"--recursive\", \"--force\", \"--no-preserve-root\", \"--\"], [\"-r\", \"-R\", \"-f\", \"-rf\", \"-fr\", \"-Rf\", \"-fR\", \"-rfv\", \"-vrf\", \"-v\", \"--recursive\", \"--force\", \"--no-preserve-root\", \"--\"], [\"-r\", \"-R\", \"-f\", \"-rf\", \"-fr\", \"-Rf\", \"-fR\", \"-rfv\", \"-vrf\", \"-v\", \"--recursive\", \"--force\", \"--no-preserve-root\", \"--\"], \"/\"], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\n# Codex does not split a script that holds ~, $HOME, a glob, or a substitution.\n# It matches the whole [shell, -c, script] invocation, so these rules forbid\n# only the exact scripts listed.\nprefix_rule(pattern=[[\"bash\", \"sh\", \"zsh\"], [\"-c\", \"-lc\"], [\"rm ~\", \"rm -r ~\", \"rm -R ~\", \"rm -f ~\", \"rm -rf ~\", \"rm -fr ~\", \"rm -Rf ~\", \"rm -fR ~\", \"rm -r -f ~\", \"rm -f -r ~\", \"rm --recursive ~\", \"rm --recursive --force ~\"]], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[[\"bash\", \"sh\", \"zsh\"], [\"-c\", \"-lc\"], [\"rm ~/\", \"rm -r ~/\", \"rm -R ~/\", \"rm -f ~/\", \"rm -rf ~/\", \"rm -fr ~/\", \"rm -Rf ~/\", \"rm -fR ~/\", \"rm -r -f ~/\", \"rm -f -r ~/\", \"rm --recursive ~/\", \"rm --recursive --force ~/\"]], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[[\"bash\", \"sh\", \"zsh\"], [\"-c\", \"-lc\"], [\"rm $HOME\", \"rm -r $HOME\", \"rm -R $HOME\", \"rm -f $HOME\", \"rm -rf $HOME\", \"rm -fr $HOME\", \"rm -Rf $HOME\", \"rm -fR $HOME\", \"rm -r -f $HOME\", \"rm -f -r $HOME\", \"rm --recursive $HOME\", \"rm --recursive --force $HOME\"]], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[[\"bash\", \"sh\", \"zsh\"], [\"-c\", \"-lc\"], [\"rm $HOME/\", \"rm -r $HOME/\", \"rm -R $HOME/\", \"rm -f $HOME/\", \"rm -rf $HOME/\", \"rm -fr $HOME/\", \"rm -Rf $HOME/\", \"rm -fR $HOME/\", \"rm -r -f $HOME/\", \"rm -f -r $HOME/\", \"rm --recursive $HOME/\", \"rm --recursive --force $HOME/\"]], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[[\"bash\", \"sh\", \"zsh\"], [\"-c\", \"-lc\"], [\"rm \\\"$HOME\\\"\", \"rm -r \\\"$HOME\\\"\", \"rm -R \\\"$HOME\\\"\", \"rm -f \\\"$HOME\\\"\", \"rm -rf \\\"$HOME\\\"\", \"rm -fr \\\"$HOME\\\"\", \"rm -Rf \\\"$HOME\\\"\", \"rm -fR \\\"$HOME\\\"\", \"rm -r -f \\\"$HOME\\\"\", \"rm -f -r \\\"$HOME\\\"\", \"rm --recursive \\\"$HOME\\\"\", \"rm --recursive --force \\\"$HOME\\\"\"]], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[[\"bash\", \"sh\", \"zsh\"], [\"-c\", \"-lc\"], [\"rm \\\"$HOME/\\\"\", \"rm -r \\\"$HOME/\\\"\", \"rm -R \\\"$HOME/\\\"\", \"rm -f \\\"$HOME/\\\"\", \"rm -rf \\\"$HOME/\\\"\", \"rm -fr \\\"$HOME/\\\"\", \"rm -Rf \\\"$HOME/\\\"\", \"rm -fR \\\"$HOME/\\\"\", \"rm -r -f \\\"$HOME/\\\"\", \"rm -f -r \\\"$HOME/\\\"\", \"rm --recursive \\\"$HOME/\\\"\", \"rm --recursive --force \\\"$HOME/\\\"\"]], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[[\"bash\", \"sh\", \"zsh\"], [\"-c\", \"-lc\"], [\"rm \\\"$HOME\\\"/\", \"rm -r \\\"$HOME\\\"/\", \"rm -R \\\"$HOME\\\"/\", \"rm -f \\\"$HOME\\\"/\", \"rm -rf \\\"$HOME\\\"/\", \"rm -fr \\\"$HOME\\\"/\", \"rm -Rf \\\"$HOME\\\"/\", \"rm -fR \\\"$HOME\\\"/\", \"rm -r -f \\\"$HOME\\\"/\", \"rm -f -r \\\"$HOME\\\"/\", \"rm --recursive \\\"$HOME\\\"/\", \"rm --recursive --force \\\"$HOME\\\"/\"]], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[[\"bash\", \"sh\", \"zsh\"], [\"-c\", \"-lc\"], [\"rm ${HOME}\", \"rm -r ${HOME}\", \"rm -R ${HOME}\", \"rm -f ${HOME}\", \"rm -rf ${HOME}\", \"rm -fr ${HOME}\", \"rm -Rf ${HOME}\", \"rm -fR ${HOME}\", \"rm -r -f ${HOME}\", \"rm -f -r ${HOME}\", \"rm --recursive ${HOME}\", \"rm --recursive --force ${HOME}\"]], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[[\"bash\", \"sh\", \"zsh\"], [\"-c\", \"-lc\"], [\"rm ${HOME}/\", \"rm -r ${HOME}/\", \"rm -R ${HOME}/\", \"rm -f ${HOME}/\", \"rm -rf ${HOME}/\", \"rm -fr ${HOME}/\", \"rm -Rf ${HOME}/\", \"rm -fR ${HOME}/\", \"rm -r -f ${HOME}/\", \"rm -f -r ${HOME}/\", \"rm --recursive ${HOME}/\", \"rm --recursive --force ${HOME}/\"]], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[[\"bash\", \"sh\", \"zsh\"], [\"-c\", \"-lc\"], [\"rm \\\"${HOME}\\\"\", \"rm -r \\\"${HOME}\\\"\", \"rm -R \\\"${HOME}\\\"\", \"rm -f \\\"${HOME}\\\"\", \"rm -rf \\\"${HOME}\\\"\", \"rm -fr \\\"${HOME}\\\"\", \"rm -Rf \\\"${HOME}\\\"\", \"rm -fR \\\"${HOME}\\\"\", \"rm -r -f \\\"${HOME}\\\"\", \"rm -f -r \\\"${HOME}\\\"\", \"rm --recursive \\\"${HOME}\\\"\", \"rm --recursive --force \\\"${HOME}\\\"\"]], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[[\"bash\", \"sh\", \"zsh\"], [\"-c\", \"-lc\"], [\"rm \\\"${HOME}/\\\"\", \"rm -r \\\"${HOME}/\\\"\", \"rm -R \\\"${HOME}/\\\"\", \"rm -f \\\"${HOME}/\\\"\", \"rm -rf \\\"${HOME}/\\\"\", \"rm -fr \\\"${HOME}/\\\"\", \"rm -Rf \\\"${HOME}/\\\"\", \"rm -fR \\\"${HOME}/\\\"\", \"rm -r -f \\\"${HOME}/\\\"\", \"rm -f -r \\\"${HOME}/\\\"\", \"rm --recursive \\\"${HOME}/\\\"\", \"rm --recursive --force \\\"${HOME}/\\\"\"]], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[[\"bash\", \"sh\", \"zsh\"], [\"-c\", \"-lc\"], [\"rm \\\"${HOME}\\\"/\", \"rm -r \\\"${HOME}\\\"/\", \"rm -R \\\"${HOME}\\\"/\", \"rm -f \\\"${HOME}\\\"/\", \"rm -rf \\\"${HOME}\\\"/\", \"rm -fr \\\"${HOME}\\\"/\", \"rm -Rf \\\"${HOME}\\\"/\", \"rm -fR \\\"${HOME}\\\"/\", \"rm -r -f \\\"${HOME}\\\"/\", \"rm -f -r \\\"${HOME}\\\"/\", \"rm --recursive \\\"${HOME}\\\"/\", \"rm --recursive --force \\\"${HOME}\\\"/\"]], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[[\"bash\", \"sh\", \"zsh\"], [\"-c\", \"-lc\"], [\"rm /*\", \"rm -r /*\", \"rm -R /*\", \"rm -f /*\", \"rm -rf /*\", \"rm -fr /*\", \"rm -Rf /*\", \"rm -fR /*\", \"rm -r -f /*\", \"rm -f -r /*\", \"rm --recursive /*\", \"rm --recursive --force /*\"]], decision=\"forbidden\", justification=\"Never remove the home directory or the filesystem root. Move a path to the trash with gio trash -- <path> (Linux) or trash <path> (macOS 15+).\")\nprefix_rule(pattern=[[\"bash\", \"sh\", \"zsh\"], [\"-c\", \"-lc\"], [\"export HOME=$(mktemp -d)\", \"export HOME=\\\"$(mktemp -d)\\\"\", \"HOME=$(mktemp -d)\", \"HOME=\\\"$(mktemp -d)\\\"\"]], decision=\"forbidden\", justification=\"Never reassign HOME. Each command runs in a new shell, so use literal absolute paths.\")\n\n# Forced git removal discards uncommitted changes, and the prefix cannot see a\n# later --force, so both commands ask in every form.\nprefix_rule(pattern=[\"git\", \"rm\"], decision=\"prompt\", justification=\"git rm --force and git worktree remove --force discard uncommitted changes. A prefix rule cannot see a later --force, so every git rm and git worktree remove asks.\")\nprefix_rule(pattern=[\"git\", \"worktree\", \"remove\"], decision=\"prompt\", justification=\"git rm --force and git worktree remove --force discard uncommitted changes. A prefix rule cannot see a later --force, so every git rm and git worktree remove asks.\")\n\n# gio trash can empty the trash or overwrite a restored path, and the prefix\n# cannot tell those forms from gio trash -- <path>, so every gio trash asks.\n# The macOS trash command has no such option.\nprefix_rule(pattern=[\"gio\", \"trash\"], decision=\"prompt\", justification=\"gio trash -f --empty, -ff --empty, and --restore --force delete or overwrite data, and a prefix rule cannot tell them from gio trash -- <path>, so every gio trash asks.\")\nprefix_rule(pattern=[\"trash\"], decision=\"allow\")\n",
20
20
  "SoT/.omp/AGENTS.md": "# Global OMP guidance\n\n- Verify unfamiliar or version-sensitive APIs and configuration against current official documentation before implementation.\n- When the user asks for an assessment rather than a change, report findings without editing.\n- For Docks plan reviews, cross-company review is standing-authorized; host security policy still applies.\n- Please remove all mannered prose.\n\n## Asking me things\n\nIf you need an answer from me, it MUST go through `ask`; do not ask in prose.\n\nMUST use `ask` before:\n- Anything irreversible or destructive: deleting/overwriting files or data you did not create,\n force-push, history rewrite, dropping tables, running migrations, mass rename, touching\n secrets/credentials, or publishing outward (release, upstream PR, issue, comment).\n- Two or more viable approaches whose tradeoffs are mine to own: schema/API/protocol shape,\n adding a dependency, or establishing a convention this repo does not already have.\n- A fact only I hold: intended semantics of an ambiguous requirement, which of several\n conflicting existing patterns is canonical, or which environment/account/target to use.\n- A request that contradicts the repo: surface the conflict and let me resolve it; never\n silently pick one side.\n\nWhen I invoke the `yolo` skill, that invocation answers every ask this section requires,\nuntil the run asks its merge question. It does not cover destructive work, secrets, or\nproduction systems.\n\nIf `ask` is not registered — subagent, headless, or `-p` print runs, where `hasUI` is false —\nthe MUST above cannot be satisfied: do not fabricate the call and do not stall on it. Take the\nconservative reversible option and put the question, plus the assumption you made, in your\nfinal report so whoever spawned you can decide.\n\nNEVER use `ask` for:\n- Permission to begin, or to confirm scope already stated in the request.\n- Anything a tool, grep, or doc can answer — go read it.\n- A cheap reversible choice — take the conservative option and say which you took.\n- Something already answered earlier in the conversation.\n\nBatch every open question into one `ask` call with multiple questions; do not serialize\nround trips. Being overruled ends the discussion — execute my call without relitigating.\n\n## Removing files\n\nTo remove, use the trash or a command that checks the path.\n\n- To remove a temporary file or directory, use the `scratch_remove` tool or run `docks-kit scratch remove <path>`. Both remove only a path inside the scratch root, the system temporary directory, or `/var/tmp`. `gio trash` does not work on a `tmpfs` `/tmp`.\n- To remove any other file or directory, run `gio trash -- <path>` on Linux or `trash <path>` on macOS.\n- To remove a path from the git index, run `git rm -- <path>`.\n- To remove a worktree, run `git worktree remove -- <path>`.\n- If git refuses because the worktree has changes, make sure that each of its commits is on the remote. Then make sure that `git status --porcelain` lists only generated files. Then run `git worktree remove --force -- <path>`.\n- Never pass `--force` two times to `git worktree remove`.\n- Write the `--` exactly as shown.\n- Do not use `rm`. omp denies a recursive `rm`, `find -delete`, `find -exec rm`, and `xargs rm`.\n- Do not delete files through `eval`, Python, or Node code.\n- A subagent cannot get my approval, so omp rejects every ask in a subagent.\n- Do not delete in bulk yourself (`git clean`, `git reset --hard`). In the main session, ask me first.\n- If a deletion needs `rm -r` or a bulk command, put the paths in your report. I run that deletion myself.\n- Do not use `--force`, `-f`, or an abbreviation of it with `git rm` or `git push`.\n- Write each ref of a `git push` command as literal text. Run `git push` as its own command. omp denies a command that holds a `$` or a backtick after `git push`.\n- To push the current branch, run `git push -u origin HEAD`. To delete several remote branches, list them in one command: `git push origin --delete <branch-a> <branch-b>`.\n- Write literal absolute paths. Do not use `~` or `$HOME` in a command.\n- Do not set or export `HOME`.\n\n## Repository hooks\n\n- Do not skip or turn off a repository hook. Do not use `--no-verify`, `git commit -n`, `git am -n`, or a `core.hooksPath` change.\n- When a hook fails on a problem that your change did not cause, report the failure. In the main session, ask me before you continue.\n\n## Cleaning up what you create\n\n- Follow the `workspace-hygiene` skill for each resource that you create: worktrees, temporary files and directories, processes, containers, clusters, tunnels, scheduled jobs, global installs, and remote test resources.\n- Create a temporary directory with the `scratch_new` tool or `docks-kit scratch new <label>`. Put each temporary file in that directory. Do not put a temporary file, a temporary directory, a package store, a cache, or a clone in `/tmp`.\n- Create a worktree only at `<data>/agent-worktrees/<repository>/<name>`. `<data>` is `$XDG_DATA_HOME`, or `.local/share` in the home directory when that variable is not set. Write the literal absolute path.\n- Run a test suite in single-run mode. Start a server, a watcher, a tunnel, or a database only as a named bash service or an async job. Do not detach a process with `nohup`, `setsid`, `disown`, `tmux`, or `screen`.\n- Do not install a package globally, add a scheduled job, or enable a service unless I ask for it.\n- Do not remove a Docker volume, image, or build cache that you did not create, and do not run `docker system prune`.\n- Before your final answer, remove each resource that you created and that the task no longer needs. Keep a resource only when I ask for it or a later step needs it, and name it in your final answer.\n- A scratch directory is deleted after 7 idle days. Put evidence that you cite in the issue, the pull request, or the repository.\n- Resources on this workstation are always development. A remote resource is one that you reach through SSH or a provider CLI, such as `wrangler`, `vercel`, `netlify`, `fly`, `supabase`, `kubectl`, or a remote Docker host.\n- Clean up a remote resource only when its target is named local, development, dev, test, homolog, homologation, staging, or preview. Every other target is production. For example, `wrangler delete` without `--env` acts on the top-level Worker, which is usually production.\n- Never stop, remove, undeploy, or delete a production resource without an `ask` immediately before it. A production cleanup must be rare. A `yolo` invocation does not answer this ask. In a subagent, do not do it; name the resource in your report.\n\n## Output Standard\n\nApply Simplified Technical English to all agent text. This includes responses, messages,\ndocumentation, comments, and interface text.\n\nReply in the language I use, and apply every rule below to that language.\n\nA rule that names English grammar applies only to English. The contraction ban is one\nsuch rule. In another language, follow the normal grammar of that language. Portuguese,\nSpanish, French, Italian, and German merge a preposition with an article, and that merge\nis required, not optional.\n\nTreat the word limits as approximate outside English.\n\n- Use the simplest precise technical term.\n- Use each term consistently.\n- Expand an abbreviation at its first occurrence.\n- Explain a technical term when I ask for an explanation.\n- Write complete and grammatically correct sentences.\n- Use active voice and identify the actor.\n- Use the imperative form for instructions.\n- Put only one action in each instruction sentence.\n- Put a necessary condition before its instruction.\n- Use simple verb tenses.\n- Do not use contractions, idioms, or slang. Avoid humor and rhetorical questions.\n- Keep procedural sentences to 20 words or fewer.\n- Keep descriptive sentences to 25 words or fewer.\n- Keep each paragraph to one topic and six sentences or fewer.\n- Do not use more than three nouns together.\n- Use vertical lists for complex information.\n- Put a warning or caution before a related hazardous instruction.\n\n### Naming\n\n- Say what the thing does before you name it. Put the technical term after the plain\n description, once, in parentheses.\n- Do not use a technical term as the only name for something you just introduced.\n- Prefer the short common word. Use \"use\", not \"utilize\". Use \"set up\", not \"provision\".\n- Do not explain by metaphor alone. A metaphor may follow a literal statement.\n",
21
- "SoT/.omp/config.yml": "statusLine:\n compactThinkingLevel: false\n\ndefaultThinkingLevel: high\n\ncycleOrder:\n - smol\n - default\n - slow\n - fable\n - astra\n\ntier:\n anthropic: none\n\nadvisor:\n enabled: true\n syncBacklog: \"1\"\n\ngithub:\n enabled: true\n\nfind:\n enabled: true\n\nbrowser:\n idleCloseSec: 600\n\ntask:\n eager: always\n showResolvedModelBadge: true\n softRequestBudget: 200\n softRequestBudgetNotice: true\n batch: true\n enableLsp: true\n enableEffort: false\n maxEffort: xhigh\n maxConcurrency: 16\n maxRecursionDepth: 2\n maxRuntimeMs: 3600000\n agentIdleTtlMs: 120000\n agentModelOverrides:\n reviewer: \"@reviewer\"\n security-reviewer: \"@reviewer\"\n code-reviewer: \"@reviewer\"\n plan-reviewer: \"@reviewer\"\n agentServiceTierOverrides:\n reviewer: inherit\n security-reviewer: inherit\n code-reviewer: inherit\n plan-reviewer: inherit\n\nmodelRoles:\n smol: openai-codex/gpt-6-luna:medium\n advisor: anthropic/claude-opus-5-5:medium\n designer: anthropic/claude-opus-5-5:high\n plan: anthropic/claude-opus-5-5:xhigh\n commit: openai-codex/gpt-6-luna:medium\n task: anthropic/claude-opus-5-5:high\n vision: anthropic/claude-opus-5-5:medium\n tiny: openai-codex/gpt-6-luna:low\n default: anthropic/claude-opus-5-5:high\n slow: anthropic/claude-opus-5-5:xhigh\n fable: anthropic/claude-fable-5-1:medium\n switch_fable: anthropic/claude-fable-5-1:medium\n astra: openai-codex/gpt-6-astra:xhigh\n reviewer: openai-codex/gpt-6.1-terra:high\n web: web/firecrawl\n\nmodelTags:\n fable:\n name: Fable 5.1\n switch_fable:\n name: Fable switch default\n hidden: true\n astra:\n name: GPT-6 Astra\n reviewer:\n name: Reviewer\n hidden: true\n\ndisplay:\n showTokenUsage: true\n\nproviders:\n anthropic:\n serverSideFallback: false\n fetch: auto\n webSearchTimeoutSeconds: 30\n\nretry:\n fallbackChains:\n default:\n - openai-codex/gpt-6.1-sol:high\n advisor: []\n task:\n - openai-codex/gpt-6.1-sol:high\n vision:\n - openai-codex/gpt-6.1-sol:medium\n smol:\n - anthropic/claude-opus-5-5:low\n tiny:\n - anthropic/claude-opus-5-5:low\n commit:\n - anthropic/claude-opus-5-5:medium\n switch_fable: []\n fable:\n - openai-codex/gpt-6-astra:xhigh\n astra:\n - anthropic/claude-fable-5-1:medium\n reviewer:\n - anthropic/claude-opus-5-5:high\n web:\n - web/exa\n - web/perplexity\n - openai-codex/gpt-6-luna\n - web/parallel\n - web/zai\n - web/tinyfish\n - web/jina\n - web/kagi\n - web/tavily\n - web/brave\n - web/kimi\n - web/synthetic\n - web/ollama\n - web/searxng\n - web/startpage\n - web/duckduckgo\n - web/ecosia\n - web/google\n - web/mojeek\n - web/public\n\nincludeWorkspaceTree: false\n\nbranchSummary:\n enabled: true\n\ncommands:\n enableOpencodeProject: false\n enableOpencodeUser: false\n\nskills:\n enableClaudeUser: false\n enableCodexUser: false\n enableAgentsUser: true\n\nsteeringMode: all\n\ndev:\n autoqa: false\n autoqaConsent: denied\n\ncompaction:\n thresholdTokens: -1\n idleEnabled: true\n handoffSaveToDisk: true\n\ndoubleEscapeAction: tree\ntextVerbosity: low\n\nfeatures:\n unexpectedStopDetection: smart\n\ncodexResets:\n autoRedeem: \"no\"\n\nstartup:\n quiet: true\n\ntools:\n approvalMode: yolo\n\nbash:\n # First match wins. omp checks deny rules against the whole line and each\n # quote-stripped segment, so `rm -rf \"$HOME\"` matches `rm * $HOME`. `*`\n # matches any text, spaces and slashes included; no escape spells a literal\n # `*`.\n # The kit ships no prompt rule, because a subagent rejects every prompt.\n # A command that no deny rule matches runs under yolo, unless a prompt rule\n # that the user added matches it: a plain rm, git rm, git worktree remove,\n # gio trash, docks-kit scratch remove, git clean, git reset --hard, and\n # every git push that the denies below do not stop.\n # omp's critical-command check turns a prompt into an allow under yolo, so\n # every rm shape it can flag is a deny.\n patterns:\n # Deny: rm of the home directory or the filesystem root, sudo before rm,\n # rm with an r or f option before an absolute path, recursive rm (bare, by\n # path, or after any word such as env, xargs, find -exec, or git), bulk\n # removal through find -delete, find -exec rm, and xargs rm, HOME\n # reassignment, a force push to main or master, and a $ or a backtick\n # after git push.\n - { match: \"rm /\", approval: deny }\n - { match: \"rm / *\", approval: deny }\n - { match: \"rm * /\", approval: deny }\n - { match: \"rm * / *\", approval: deny }\n - { match: \"rm ~\", approval: deny }\n - { match: \"rm ~ *\", approval: deny }\n - { match: \"rm * ~\", approval: deny }\n - { match: \"rm * ~ *\", approval: deny }\n - { match: \"rm ~/\", approval: deny }\n - { match: \"rm ~/ *\", approval: deny }\n - { match: \"rm * ~/\", approval: deny }\n - { match: \"rm * ~/ *\", approval: deny }\n - { match: \"rm $HOME\", approval: deny }\n - { match: \"rm $HOME *\", approval: deny }\n - { match: \"rm * $HOME\", approval: deny }\n - { match: \"rm * $HOME *\", approval: deny }\n - { match: \"rm $HOME/\", approval: deny }\n - { match: \"rm $HOME/ *\", approval: deny }\n - { match: \"rm * $HOME/\", approval: deny }\n - { match: \"rm * $HOME/ *\", approval: deny }\n - { match: \"rm ${HOME}\", approval: deny }\n - { match: \"rm ${HOME} *\", approval: deny }\n - { match: \"rm * ${HOME}\", approval: deny }\n - { match: \"rm * ${HOME} *\", approval: deny }\n - { match: \"rm ${HOME}/\", approval: deny }\n - { match: \"rm ${HOME}/ *\", approval: deny }\n - { match: \"rm * ${HOME}/\", approval: deny }\n - { match: \"rm * ${HOME}/ *\", approval: deny }\n - { match: \"* rm /\", approval: deny }\n - { match: \"* rm / *\", approval: deny }\n - { match: \"* rm * /\", approval: deny }\n - { match: \"* rm * / *\", approval: deny }\n - { match: \"* rm ~\", approval: deny }\n - { match: \"* rm ~ *\", approval: deny }\n - { match: \"* rm * ~\", approval: deny }\n - { match: \"* rm * ~ *\", approval: deny }\n - { match: \"* rm ~/\", approval: deny }\n - { match: \"* rm ~/ *\", approval: deny }\n - { match: \"* rm * ~/\", approval: deny }\n - { match: \"* rm * ~/ *\", approval: deny }\n - { match: \"* rm $HOME\", approval: deny }\n - { match: \"* rm $HOME *\", approval: deny }\n - { match: \"* rm * $HOME\", approval: deny }\n - { match: \"* rm * $HOME *\", approval: deny }\n - { match: \"* rm $HOME/\", approval: deny }\n - { match: \"* rm $HOME/ *\", approval: deny }\n - { match: \"* rm * $HOME/\", approval: deny }\n - { match: \"* rm * $HOME/ *\", approval: deny }\n - { match: \"* rm ${HOME}\", approval: deny }\n - { match: \"* rm ${HOME} *\", approval: deny }\n - { match: \"* rm * ${HOME}\", approval: deny }\n - { match: \"* rm * ${HOME} *\", approval: deny }\n - { match: \"* rm ${HOME}/\", approval: deny }\n - { match: \"* rm ${HOME}/ *\", approval: deny }\n - { match: \"* rm * ${HOME}/\", approval: deny }\n - { match: \"* rm * ${HOME}/ *\", approval: deny }\n - { match: \"*/rm /\", approval: deny }\n - { match: \"*/rm / *\", approval: deny }\n - { match: \"*/rm * /\", approval: deny }\n - { match: \"*/rm * / *\", approval: deny }\n - { match: \"*/rm ~\", approval: deny }\n - { match: \"*/rm ~ *\", approval: deny }\n - { match: \"*/rm * ~\", approval: deny }\n - { match: \"*/rm * ~ *\", approval: deny }\n - { match: \"*/rm ~/\", approval: deny }\n - { match: \"*/rm ~/ *\", approval: deny }\n - { match: \"*/rm * ~/\", approval: deny }\n - { match: \"*/rm * ~/ *\", approval: deny }\n - { match: \"*/rm $HOME\", approval: deny }\n - { match: \"*/rm $HOME *\", approval: deny }\n - { match: \"*/rm * $HOME\", approval: deny }\n - { match: \"*/rm * $HOME *\", approval: deny }\n - { match: \"*/rm $HOME/\", approval: deny }\n - { match: \"*/rm $HOME/ *\", approval: deny }\n - { match: \"*/rm * $HOME/\", approval: deny }\n - { match: \"*/rm * $HOME/ *\", approval: deny }\n - { match: \"*/rm ${HOME}\", approval: deny }\n - { match: \"*/rm ${HOME} *\", approval: deny }\n - { match: \"*/rm * ${HOME}\", approval: deny }\n - { match: \"*/rm * ${HOME} *\", approval: deny }\n - { match: \"*/rm ${HOME}/\", approval: deny }\n - { match: \"*/rm ${HOME}/ *\", approval: deny }\n - { match: \"*/rm * ${HOME}/\", approval: deny }\n - { match: \"*/rm * ${HOME}/ *\", approval: deny }\n - { match: \"sudo rm\", approval: deny }\n - { match: \"sudo rm *\", approval: deny }\n - { match: \"sudo * rm\", approval: deny }\n - { match: \"sudo * rm *\", approval: deny }\n - { match: \"sudo */rm\", approval: deny }\n - { match: \"sudo */rm *\", approval: deny }\n - { match: \"* sudo rm\", approval: deny }\n - { match: \"* sudo rm *\", approval: deny }\n - { match: \"* sudo * rm\", approval: deny }\n - { match: \"* sudo * rm *\", approval: deny }\n - { match: \"* sudo */rm\", approval: deny }\n - { match: \"* sudo */rm *\", approval: deny }\n - { match: \"*/sudo rm\", approval: deny }\n - { match: \"*/sudo rm *\", approval: deny }\n - { match: \"*/sudo * rm\", approval: deny }\n - { match: \"*/sudo * rm *\", approval: deny }\n - { match: \"*/sudo */rm\", approval: deny }\n - { match: \"*/sudo */rm *\", approval: deny }\n - { match: \"rm *-*r* /*\", approval: deny }\n - { match: \"rm *-*R* /*\", approval: deny }\n - { match: \"rm *-*f* /*\", approval: deny }\n - { match: \"rm *-*F* /*\", approval: deny }\n - { match: \"rm *--no-preserve-root*\", approval: deny }\n - { match: \"* rm *-*r* /*\", approval: deny }\n - { match: \"* rm *-*R* /*\", approval: deny }\n - { match: \"* rm *-*f* /*\", approval: deny }\n - { match: \"* rm *-*F* /*\", approval: deny }\n - { match: \"* rm *--no-preserve-root*\", approval: deny }\n - { match: \"*/rm *-*r* /*\", approval: deny }\n - { match: \"*/rm *-*R* /*\", approval: deny }\n - { match: \"*/rm *-*f* /*\", approval: deny }\n - { match: \"*/rm *-*F* /*\", approval: deny }\n - { match: \"*/rm *--no-preserve-root*\", approval: deny }\n - { match: \"rm *-r *\", approval: deny }\n - { match: \"rm *-r\", approval: deny }\n - { match: \"rm *-rf *\", approval: deny }\n - { match: \"rm *-rf\", approval: deny }\n - { match: \"rm *-fr *\", approval: deny }\n - { match: \"rm *-fr\", approval: deny }\n - { match: \"rm *-rv *\", approval: deny }\n - { match: \"rm *-rv\", approval: deny }\n - { match: \"rm *-vr *\", approval: deny }\n - { match: \"rm *-vr\", approval: deny }\n - { match: \"rm *-rfv *\", approval: deny }\n - { match: \"rm *-rfv\", approval: deny }\n - { match: \"rm *-rvf *\", approval: deny }\n - { match: \"rm *-rvf\", approval: deny }\n - { match: \"rm *-frv *\", approval: deny }\n - { match: \"rm *-frv\", approval: deny }\n - { match: \"rm *-fvr *\", approval: deny }\n - { match: \"rm *-fvr\", approval: deny }\n - { match: \"rm *-vrf *\", approval: deny }\n - { match: \"rm *-vrf\", approval: deny }\n - { match: \"rm *-vfr *\", approval: deny }\n - { match: \"rm *-vfr\", approval: deny }\n - { match: \"rm *-ri *\", approval: deny }\n - { match: \"rm *-ri\", approval: deny }\n - { match: \"rm *-ir *\", approval: deny }\n - { match: \"rm *-ir\", approval: deny }\n - { match: \"rm *-Ri *\", approval: deny }\n - { match: \"rm *-Ri\", approval: deny }\n - { match: \"rm *-iR *\", approval: deny }\n - { match: \"rm *-iR\", approval: deny }\n - { match: \"rm *-R *\", approval: deny }\n - { match: \"rm *-R\", approval: deny }\n - { match: \"rm *-Rf *\", approval: deny }\n - { match: \"rm *-Rf\", approval: deny }\n - { match: \"rm *-fR *\", approval: deny }\n - { match: \"rm *-fR\", approval: deny }\n - { match: \"rm *-Rv *\", approval: deny }\n - { match: \"rm *-Rv\", approval: deny }\n - { match: \"rm *-vR *\", approval: deny }\n - { match: \"rm *-vR\", approval: deny }\n - { match: \"rm *-Rfv *\", approval: deny }\n - { match: \"rm *-Rfv\", approval: deny }\n - { match: \"rm *-Rvf *\", approval: deny }\n - { match: \"rm *-Rvf\", approval: deny }\n - { match: \"rm *-fRv *\", approval: deny }\n - { match: \"rm *-fRv\", approval: deny }\n - { match: \"rm *-fvR *\", approval: deny }\n - { match: \"rm *-fvR\", approval: deny }\n - { match: \"rm *-vRf *\", approval: deny }\n - { match: \"rm *-vRf\", approval: deny }\n - { match: \"rm *-vfR *\", approval: deny }\n - { match: \"rm *-vfR\", approval: deny }\n - { match: \"rm *--recursive *\", approval: deny }\n - { match: \"rm *--recursive\", approval: deny }\n - { match: \"*/rm *-r *\", approval: deny }\n - { match: \"*/rm *-r\", approval: deny }\n - { match: \"*/rm *-rf *\", approval: deny }\n - { match: \"*/rm *-rf\", approval: deny }\n - { match: \"*/rm *-fr *\", approval: deny }\n - { match: \"*/rm *-fr\", approval: deny }\n - { match: \"*/rm *-rv *\", approval: deny }\n - { match: \"*/rm *-rv\", approval: deny }\n - { match: \"*/rm *-vr *\", approval: deny }\n - { match: \"*/rm *-vr\", approval: deny }\n - { match: \"*/rm *-rfv *\", approval: deny }\n - { match: \"*/rm *-rfv\", approval: deny }\n - { match: \"*/rm *-rvf *\", approval: deny }\n - { match: \"*/rm *-rvf\", approval: deny }\n - { match: \"*/rm *-frv *\", approval: deny }\n - { match: \"*/rm *-frv\", approval: deny }\n - { match: \"*/rm *-fvr *\", approval: deny }\n - { match: \"*/rm *-fvr\", approval: deny }\n - { match: \"*/rm *-vrf *\", approval: deny }\n - { match: \"*/rm *-vrf\", approval: deny }\n - { match: \"*/rm *-vfr *\", approval: deny }\n - { match: \"*/rm *-vfr\", approval: deny }\n - { match: \"*/rm *-ri *\", approval: deny }\n - { match: \"*/rm *-ri\", approval: deny }\n - { match: \"*/rm *-ir *\", approval: deny }\n - { match: \"*/rm *-ir\", approval: deny }\n - { match: \"*/rm *-Ri *\", approval: deny }\n - { match: \"*/rm *-Ri\", approval: deny }\n - { match: \"*/rm *-iR *\", approval: deny }\n - { match: \"*/rm *-iR\", approval: deny }\n - { match: \"*/rm *-R *\", approval: deny }\n - { match: \"*/rm *-R\", approval: deny }\n - { match: \"*/rm *-Rf *\", approval: deny }\n - { match: \"*/rm *-Rf\", approval: deny }\n - { match: \"*/rm *-fR *\", approval: deny }\n - { match: \"*/rm *-fR\", approval: deny }\n - { match: \"*/rm *-Rv *\", approval: deny }\n - { match: \"*/rm *-Rv\", approval: deny }\n - { match: \"*/rm *-vR *\", approval: deny }\n - { match: \"*/rm *-vR\", approval: deny }\n - { match: \"*/rm *-Rfv *\", approval: deny }\n - { match: \"*/rm *-Rfv\", approval: deny }\n - { match: \"*/rm *-Rvf *\", approval: deny }\n - { match: \"*/rm *-Rvf\", approval: deny }\n - { match: \"*/rm *-fRv *\", approval: deny }\n - { match: \"*/rm *-fRv\", approval: deny }\n - { match: \"*/rm *-fvR *\", approval: deny }\n - { match: \"*/rm *-fvR\", approval: deny }\n - { match: \"*/rm *-vRf *\", approval: deny }\n - { match: \"*/rm *-vRf\", approval: deny }\n - { match: \"*/rm *-vfR *\", approval: deny }\n - { match: \"*/rm *-vfR\", approval: deny }\n - { match: \"*/rm *--recursive *\", approval: deny }\n - { match: \"*/rm *--recursive\", approval: deny }\n - { match: \"* rm *-r *\", approval: deny }\n - { match: \"* rm *-r\", approval: deny }\n - { match: \"* rm *-rf *\", approval: deny }\n - { match: \"* rm *-rf\", approval: deny }\n - { match: \"* rm *-fr *\", approval: deny }\n - { match: \"* rm *-fr\", approval: deny }\n - { match: \"* rm *-rv *\", approval: deny }\n - { match: \"* rm *-rv\", approval: deny }\n - { match: \"* rm *-vr *\", approval: deny }\n - { match: \"* rm *-vr\", approval: deny }\n - { match: \"* rm *-rfv *\", approval: deny }\n - { match: \"* rm *-rfv\", approval: deny }\n - { match: \"* rm *-rvf *\", approval: deny }\n - { match: \"* rm *-rvf\", approval: deny }\n - { match: \"* rm *-frv *\", approval: deny }\n - { match: \"* rm *-frv\", approval: deny }\n - { match: \"* rm *-fvr *\", approval: deny }\n - { match: \"* rm *-fvr\", approval: deny }\n - { match: \"* rm *-vrf *\", approval: deny }\n - { match: \"* rm *-vrf\", approval: deny }\n - { match: \"* rm *-vfr *\", approval: deny }\n - { match: \"* rm *-vfr\", approval: deny }\n - { match: \"* rm *-R *\", approval: deny }\n - { match: \"* rm *-R\", approval: deny }\n - { match: \"* rm *-ri *\", approval: deny }\n - { match: \"* rm *-ri\", approval: deny }\n - { match: \"* rm *-ir *\", approval: deny }\n - { match: \"* rm *-ir\", approval: deny }\n - { match: \"* rm *-Ri *\", approval: deny }\n - { match: \"* rm *-Ri\", approval: deny }\n - { match: \"* rm *-iR *\", approval: deny }\n - { match: \"* rm *-iR\", approval: deny }\n - { match: \"* rm *-Rf *\", approval: deny }\n - { match: \"* rm *-Rf\", approval: deny }\n - { match: \"* rm *-fR *\", approval: deny }\n - { match: \"* rm *-fR\", approval: deny }\n - { match: \"* rm *-Rv *\", approval: deny }\n - { match: \"* rm *-Rv\", approval: deny }\n - { match: \"* rm *-vR *\", approval: deny }\n - { match: \"* rm *-vR\", approval: deny }\n - { match: \"* rm *-Rfv *\", approval: deny }\n - { match: \"* rm *-Rfv\", approval: deny }\n - { match: \"* rm *-Rvf *\", approval: deny }\n - { match: \"* rm *-Rvf\", approval: deny }\n - { match: \"* rm *-fRv *\", approval: deny }\n - { match: \"* rm *-fRv\", approval: deny }\n - { match: \"* rm *-fvR *\", approval: deny }\n - { match: \"* rm *-fvR\", approval: deny }\n - { match: \"* rm *-vRf *\", approval: deny }\n - { match: \"* rm *-vRf\", approval: deny }\n - { match: \"* rm *-vfR *\", approval: deny }\n - { match: \"* rm *-vfR\", approval: deny }\n - { match: \"* rm *--recursive *\", approval: deny }\n - { match: \"* rm *--recursive\", approval: deny }\n # Bulk removal: find -delete, find -exec rm, and xargs rm, in every position.\n - { match: \"find *-delete*\", approval: deny }\n - { match: \"*/find *-delete*\", approval: deny }\n - { match: \"* find *-delete*\", approval: deny }\n - { match: \"*-exec rm *\", approval: deny }\n - { match: \"*-exec */rm *\", approval: deny }\n - { match: \"*-execdir rm *\", approval: deny }\n - { match: \"*-execdir */rm *\", approval: deny }\n - { match: \"*-ok rm *\", approval: deny }\n - { match: \"*-ok */rm *\", approval: deny }\n - { match: \"*-okdir rm *\", approval: deny }\n - { match: \"*-okdir */rm *\", approval: deny }\n - { match: \"*xargs rm\", approval: deny }\n - { match: \"*xargs rm *\", approval: deny }\n - { match: \"*xargs * rm\", approval: deny }\n - { match: \"*xargs * rm *\", approval: deny }\n - { match: \"*xargs */rm\", approval: deny }\n - { match: \"*xargs */rm *\", approval: deny }\n - { match: \"HOME=*\", approval: deny }\n - { match: \"export HOME=*\", approval: deny }\n - { match: \"env HOME=*\", approval: deny }\n - { match: \"env * HOME=*\", approval: deny }\n - { match: \"git push --force origin main\", approval: deny }\n - { match: \"git push --force origin main *\", approval: deny }\n - { match: \"git push --force origin master\", approval: deny }\n - { match: \"git push --force origin master *\", approval: deny }\n - { match: \"git push -f origin main\", approval: deny }\n - { match: \"git push -f origin main *\", approval: deny }\n - { match: \"git push -f origin master\", approval: deny }\n - { match: \"git push -f origin master *\", approval: deny }\n # A $ or a backtick anywhere after git push: the matcher reads the text\n # before the shell expands it, so it cannot tell a branch name from +main\n # or --force. An unquoted value inside a word also splits into more words.\n # A deny, not a prompt: the agent reads the refusal and writes the ref\n # literally (git push -u origin HEAD). No person is asked.\n # The leading * also reaches a git push after a shell keyword such as do,\n # after a wrapper such as env, and after a path such as /usr/bin/git.\n - { match: \"*git push *$*\", approval: deny }\n - { match: \"*git push *`*\", approval: deny }\n # Allow: the macOS trash command.\n - { match: \"trash *\", approval: allow }\n",
21
+ "SoT/.omp/config.yml": "statusLine:\n compactThinkingLevel: false\n\ncycleOrder:\n - smol\n - default\n - slow\n - fable\n - astra\n\ngithub:\n enabled: true\n\nfind:\n enabled: true\n\nbrowser:\n idleCloseSec: 600\n\ntask:\n eager: always\n showResolvedModelBadge: true\n enableLsp: true\n maxEffort: xhigh\n maxConcurrency: 16\n maxRuntimeMs: 3600000\n agentIdleTtlMs: 120000\n agentModelOverrides:\n reviewer: \"@reviewer\"\n security-reviewer: \"@reviewer\"\n code-reviewer: \"@reviewer\"\n plan-reviewer: \"@reviewer\"\n agentServiceTierOverrides:\n reviewer: inherit\n security-reviewer: inherit\n code-reviewer: inherit\n plan-reviewer: inherit\n\nmodelRoles:\n smol: openai-codex/gpt-6-luna:medium\n designer: anthropic/claude-opus-5-5:high\n plan: anthropic/claude-opus-5-5:xhigh\n commit: openai-codex/gpt-6-luna:medium\n task: anthropic/claude-opus-5-5:high\n vision: anthropic/claude-opus-5-5:medium\n tiny: openai-codex/gpt-6-luna:low\n default: anthropic/claude-opus-5-5:high\n slow: anthropic/claude-opus-5-5:xhigh\n fable: anthropic/claude-fable-5-2:medium\n switch_fable: anthropic/claude-fable-5-2:medium\n astra: openai-codex/gpt-6-astra:xhigh\n reviewer: openai-codex/gpt-6.1-terra:high\n web: web/firecrawl\n\nmodelTags:\n fable:\n name: Fable 5.2\n switch_fable:\n name: Fable switch default\n hidden: true\n astra:\n name: GPT-6 Astra\n reviewer:\n name: Reviewer\n hidden: true\n\ndisplay:\n showTokenUsage: true\n\nproviders:\n webSearchTimeoutSeconds: 30\n\nretry:\n fallbackChains:\n default:\n - openai-codex/gpt-6.1-sol:high\n task:\n - openai-codex/gpt-6.1-sol:high\n vision:\n - openai-codex/gpt-6.1-sol:medium\n smol:\n - anthropic/claude-opus-5-5:low\n tiny:\n - anthropic/claude-opus-5-5:low\n commit:\n - anthropic/claude-opus-5-5:medium\n switch_fable: []\n fable:\n - openai-codex/gpt-6-astra:xhigh\n astra:\n - anthropic/claude-fable-5-2:medium\n reviewer:\n - anthropic/claude-opus-5-5:high\n web:\n - web/exa\n - web/perplexity\n - openai-codex/gpt-6-luna\n - web/parallel\n - web/zai\n - web/tinyfish\n - web/jina\n - web/kagi\n - web/tavily\n - web/brave\n - web/kimi\n - web/synthetic\n - web/ollama\n - web/searxng\n - web/startpage\n - web/duckduckgo\n - web/ecosia\n - web/google\n - web/mojeek\n - web/public\n\nbranchSummary:\n enabled: true\n\ncommands:\n enableOpencodeProject: false\n\nsteeringMode: all\n\ndev:\n autoqa: false\n autoqaConsent: denied\n\ncompaction:\n idleEnabled: true\n handoffSaveToDisk: true\n\ndoubleEscapeAction: tree\n\nfeatures:\n unexpectedStopDetection: smart\n\ncodexResets:\n autoRedeem5h: \"no\"\n autoRedeemWeekly: \"no\"\n\nstartup:\n quiet: true\n\nbash:\n # First match wins. omp checks deny rules against the whole line and each\n # quote-stripped segment, so `rm -rf \"$HOME\"` matches `rm * $HOME`. `*`\n # matches any text, spaces and slashes included; no escape spells a literal\n # `*`.\n # The kit ships no prompt rule, because a subagent rejects every prompt.\n # A command that no deny rule matches runs under yolo, unless a prompt rule\n # that the user added matches it: a plain rm, git rm, git worktree remove,\n # gio trash, docks-kit scratch remove, git clean, git reset --hard, and\n # every git push that the denies below do not stop.\n # omp's critical-command check turns a prompt into an allow under yolo, so\n # every rm shape it can flag is a deny.\n patterns:\n # Deny: rm of the home directory or the filesystem root, sudo before rm,\n # rm with an r or f option before an absolute path, recursive rm (bare, by\n # path, or after any word such as env, xargs, find -exec, or git), bulk\n # removal through find -delete, find -exec rm, and xargs rm, HOME\n # reassignment, a force push to main or master, and a $ or a backtick\n # after git push.\n - { match: \"rm /\", approval: deny }\n - { match: \"rm / *\", approval: deny }\n - { match: \"rm * /\", approval: deny }\n - { match: \"rm * / *\", approval: deny }\n - { match: \"rm ~\", approval: deny }\n - { match: \"rm ~ *\", approval: deny }\n - { match: \"rm * ~\", approval: deny }\n - { match: \"rm * ~ *\", approval: deny }\n - { match: \"rm ~/\", approval: deny }\n - { match: \"rm ~/ *\", approval: deny }\n - { match: \"rm * ~/\", approval: deny }\n - { match: \"rm * ~/ *\", approval: deny }\n - { match: \"rm $HOME\", approval: deny }\n - { match: \"rm $HOME *\", approval: deny }\n - { match: \"rm * $HOME\", approval: deny }\n - { match: \"rm * $HOME *\", approval: deny }\n - { match: \"rm $HOME/\", approval: deny }\n - { match: \"rm $HOME/ *\", approval: deny }\n - { match: \"rm * $HOME/\", approval: deny }\n - { match: \"rm * $HOME/ *\", approval: deny }\n - { match: \"rm ${HOME}\", approval: deny }\n - { match: \"rm ${HOME} *\", approval: deny }\n - { match: \"rm * ${HOME}\", approval: deny }\n - { match: \"rm * ${HOME} *\", approval: deny }\n - { match: \"rm ${HOME}/\", approval: deny }\n - { match: \"rm ${HOME}/ *\", approval: deny }\n - { match: \"rm * ${HOME}/\", approval: deny }\n - { match: \"rm * ${HOME}/ *\", approval: deny }\n - { match: \"* rm /\", approval: deny }\n - { match: \"* rm / *\", approval: deny }\n - { match: \"* rm * /\", approval: deny }\n - { match: \"* rm * / *\", approval: deny }\n - { match: \"* rm ~\", approval: deny }\n - { match: \"* rm ~ *\", approval: deny }\n - { match: \"* rm * ~\", approval: deny }\n - { match: \"* rm * ~ *\", approval: deny }\n - { match: \"* rm ~/\", approval: deny }\n - { match: \"* rm ~/ *\", approval: deny }\n - { match: \"* rm * ~/\", approval: deny }\n - { match: \"* rm * ~/ *\", approval: deny }\n - { match: \"* rm $HOME\", approval: deny }\n - { match: \"* rm $HOME *\", approval: deny }\n - { match: \"* rm * $HOME\", approval: deny }\n - { match: \"* rm * $HOME *\", approval: deny }\n - { match: \"* rm $HOME/\", approval: deny }\n - { match: \"* rm $HOME/ *\", approval: deny }\n - { match: \"* rm * $HOME/\", approval: deny }\n - { match: \"* rm * $HOME/ *\", approval: deny }\n - { match: \"* rm ${HOME}\", approval: deny }\n - { match: \"* rm ${HOME} *\", approval: deny }\n - { match: \"* rm * ${HOME}\", approval: deny }\n - { match: \"* rm * ${HOME} *\", approval: deny }\n - { match: \"* rm ${HOME}/\", approval: deny }\n - { match: \"* rm ${HOME}/ *\", approval: deny }\n - { match: \"* rm * ${HOME}/\", approval: deny }\n - { match: \"* rm * ${HOME}/ *\", approval: deny }\n - { match: \"*/rm /\", approval: deny }\n - { match: \"*/rm / *\", approval: deny }\n - { match: \"*/rm * /\", approval: deny }\n - { match: \"*/rm * / *\", approval: deny }\n - { match: \"*/rm ~\", approval: deny }\n - { match: \"*/rm ~ *\", approval: deny }\n - { match: \"*/rm * ~\", approval: deny }\n - { match: \"*/rm * ~ *\", approval: deny }\n - { match: \"*/rm ~/\", approval: deny }\n - { match: \"*/rm ~/ *\", approval: deny }\n - { match: \"*/rm * ~/\", approval: deny }\n - { match: \"*/rm * ~/ *\", approval: deny }\n - { match: \"*/rm $HOME\", approval: deny }\n - { match: \"*/rm $HOME *\", approval: deny }\n - { match: \"*/rm * $HOME\", approval: deny }\n - { match: \"*/rm * $HOME *\", approval: deny }\n - { match: \"*/rm $HOME/\", approval: deny }\n - { match: \"*/rm $HOME/ *\", approval: deny }\n - { match: \"*/rm * $HOME/\", approval: deny }\n - { match: \"*/rm * $HOME/ *\", approval: deny }\n - { match: \"*/rm ${HOME}\", approval: deny }\n - { match: \"*/rm ${HOME} *\", approval: deny }\n - { match: \"*/rm * ${HOME}\", approval: deny }\n - { match: \"*/rm * ${HOME} *\", approval: deny }\n - { match: \"*/rm ${HOME}/\", approval: deny }\n - { match: \"*/rm ${HOME}/ *\", approval: deny }\n - { match: \"*/rm * ${HOME}/\", approval: deny }\n - { match: \"*/rm * ${HOME}/ *\", approval: deny }\n - { match: \"sudo rm\", approval: deny }\n - { match: \"sudo rm *\", approval: deny }\n - { match: \"sudo * rm\", approval: deny }\n - { match: \"sudo * rm *\", approval: deny }\n - { match: \"sudo */rm\", approval: deny }\n - { match: \"sudo */rm *\", approval: deny }\n - { match: \"* sudo rm\", approval: deny }\n - { match: \"* sudo rm *\", approval: deny }\n - { match: \"* sudo * rm\", approval: deny }\n - { match: \"* sudo * rm *\", approval: deny }\n - { match: \"* sudo */rm\", approval: deny }\n - { match: \"* sudo */rm *\", approval: deny }\n - { match: \"*/sudo rm\", approval: deny }\n - { match: \"*/sudo rm *\", approval: deny }\n - { match: \"*/sudo * rm\", approval: deny }\n - { match: \"*/sudo * rm *\", approval: deny }\n - { match: \"*/sudo */rm\", approval: deny }\n - { match: \"*/sudo */rm *\", approval: deny }\n - { match: \"rm *-*r* /*\", approval: deny }\n - { match: \"rm *-*R* /*\", approval: deny }\n - { match: \"rm *-*f* /*\", approval: deny }\n - { match: \"rm *-*F* /*\", approval: deny }\n - { match: \"rm *--no-preserve-root*\", approval: deny }\n - { match: \"* rm *-*r* /*\", approval: deny }\n - { match: \"* rm *-*R* /*\", approval: deny }\n - { match: \"* rm *-*f* /*\", approval: deny }\n - { match: \"* rm *-*F* /*\", approval: deny }\n - { match: \"* rm *--no-preserve-root*\", approval: deny }\n - { match: \"*/rm *-*r* /*\", approval: deny }\n - { match: \"*/rm *-*R* /*\", approval: deny }\n - { match: \"*/rm *-*f* /*\", approval: deny }\n - { match: \"*/rm *-*F* /*\", approval: deny }\n - { match: \"*/rm *--no-preserve-root*\", approval: deny }\n - { match: \"rm *-r *\", approval: deny }\n - { match: \"rm *-r\", approval: deny }\n - { match: \"rm *-rf *\", approval: deny }\n - { match: \"rm *-rf\", approval: deny }\n - { match: \"rm *-fr *\", approval: deny }\n - { match: \"rm *-fr\", approval: deny }\n - { match: \"rm *-rv *\", approval: deny }\n - { match: \"rm *-rv\", approval: deny }\n - { match: \"rm *-vr *\", approval: deny }\n - { match: \"rm *-vr\", approval: deny }\n - { match: \"rm *-rfv *\", approval: deny }\n - { match: \"rm *-rfv\", approval: deny }\n - { match: \"rm *-rvf *\", approval: deny }\n - { match: \"rm *-rvf\", approval: deny }\n - { match: \"rm *-frv *\", approval: deny }\n - { match: \"rm *-frv\", approval: deny }\n - { match: \"rm *-fvr *\", approval: deny }\n - { match: \"rm *-fvr\", approval: deny }\n - { match: \"rm *-vrf *\", approval: deny }\n - { match: \"rm *-vrf\", approval: deny }\n - { match: \"rm *-vfr *\", approval: deny }\n - { match: \"rm *-vfr\", approval: deny }\n - { match: \"rm *-ri *\", approval: deny }\n - { match: \"rm *-ri\", approval: deny }\n - { match: \"rm *-ir *\", approval: deny }\n - { match: \"rm *-ir\", approval: deny }\n - { match: \"rm *-Ri *\", approval: deny }\n - { match: \"rm *-Ri\", approval: deny }\n - { match: \"rm *-iR *\", approval: deny }\n - { match: \"rm *-iR\", approval: deny }\n - { match: \"rm *-R *\", approval: deny }\n - { match: \"rm *-R\", approval: deny }\n - { match: \"rm *-Rf *\", approval: deny }\n - { match: \"rm *-Rf\", approval: deny }\n - { match: \"rm *-fR *\", approval: deny }\n - { match: \"rm *-fR\", approval: deny }\n - { match: \"rm *-Rv *\", approval: deny }\n - { match: \"rm *-Rv\", approval: deny }\n - { match: \"rm *-vR *\", approval: deny }\n - { match: \"rm *-vR\", approval: deny }\n - { match: \"rm *-Rfv *\", approval: deny }\n - { match: \"rm *-Rfv\", approval: deny }\n - { match: \"rm *-Rvf *\", approval: deny }\n - { match: \"rm *-Rvf\", approval: deny }\n - { match: \"rm *-fRv *\", approval: deny }\n - { match: \"rm *-fRv\", approval: deny }\n - { match: \"rm *-fvR *\", approval: deny }\n - { match: \"rm *-fvR\", approval: deny }\n - { match: \"rm *-vRf *\", approval: deny }\n - { match: \"rm *-vRf\", approval: deny }\n - { match: \"rm *-vfR *\", approval: deny }\n - { match: \"rm *-vfR\", approval: deny }\n - { match: \"rm *--recursive *\", approval: deny }\n - { match: \"rm *--recursive\", approval: deny }\n - { match: \"*/rm *-r *\", approval: deny }\n - { match: \"*/rm *-r\", approval: deny }\n - { match: \"*/rm *-rf *\", approval: deny }\n - { match: \"*/rm *-rf\", approval: deny }\n - { match: \"*/rm *-fr *\", approval: deny }\n - { match: \"*/rm *-fr\", approval: deny }\n - { match: \"*/rm *-rv *\", approval: deny }\n - { match: \"*/rm *-rv\", approval: deny }\n - { match: \"*/rm *-vr *\", approval: deny }\n - { match: \"*/rm *-vr\", approval: deny }\n - { match: \"*/rm *-rfv *\", approval: deny }\n - { match: \"*/rm *-rfv\", approval: deny }\n - { match: \"*/rm *-rvf *\", approval: deny }\n - { match: \"*/rm *-rvf\", approval: deny }\n - { match: \"*/rm *-frv *\", approval: deny }\n - { match: \"*/rm *-frv\", approval: deny }\n - { match: \"*/rm *-fvr *\", approval: deny }\n - { match: \"*/rm *-fvr\", approval: deny }\n - { match: \"*/rm *-vrf *\", approval: deny }\n - { match: \"*/rm *-vrf\", approval: deny }\n - { match: \"*/rm *-vfr *\", approval: deny }\n - { match: \"*/rm *-vfr\", approval: deny }\n - { match: \"*/rm *-ri *\", approval: deny }\n - { match: \"*/rm *-ri\", approval: deny }\n - { match: \"*/rm *-ir *\", approval: deny }\n - { match: \"*/rm *-ir\", approval: deny }\n - { match: \"*/rm *-Ri *\", approval: deny }\n - { match: \"*/rm *-Ri\", approval: deny }\n - { match: \"*/rm *-iR *\", approval: deny }\n - { match: \"*/rm *-iR\", approval: deny }\n - { match: \"*/rm *-R *\", approval: deny }\n - { match: \"*/rm *-R\", approval: deny }\n - { match: \"*/rm *-Rf *\", approval: deny }\n - { match: \"*/rm *-Rf\", approval: deny }\n - { match: \"*/rm *-fR *\", approval: deny }\n - { match: \"*/rm *-fR\", approval: deny }\n - { match: \"*/rm *-Rv *\", approval: deny }\n - { match: \"*/rm *-Rv\", approval: deny }\n - { match: \"*/rm *-vR *\", approval: deny }\n - { match: \"*/rm *-vR\", approval: deny }\n - { match: \"*/rm *-Rfv *\", approval: deny }\n - { match: \"*/rm *-Rfv\", approval: deny }\n - { match: \"*/rm *-Rvf *\", approval: deny }\n - { match: \"*/rm *-Rvf\", approval: deny }\n - { match: \"*/rm *-fRv *\", approval: deny }\n - { match: \"*/rm *-fRv\", approval: deny }\n - { match: \"*/rm *-fvR *\", approval: deny }\n - { match: \"*/rm *-fvR\", approval: deny }\n - { match: \"*/rm *-vRf *\", approval: deny }\n - { match: \"*/rm *-vRf\", approval: deny }\n - { match: \"*/rm *-vfR *\", approval: deny }\n - { match: \"*/rm *-vfR\", approval: deny }\n - { match: \"*/rm *--recursive *\", approval: deny }\n - { match: \"*/rm *--recursive\", approval: deny }\n - { match: \"* rm *-r *\", approval: deny }\n - { match: \"* rm *-r\", approval: deny }\n - { match: \"* rm *-rf *\", approval: deny }\n - { match: \"* rm *-rf\", approval: deny }\n - { match: \"* rm *-fr *\", approval: deny }\n - { match: \"* rm *-fr\", approval: deny }\n - { match: \"* rm *-rv *\", approval: deny }\n - { match: \"* rm *-rv\", approval: deny }\n - { match: \"* rm *-vr *\", approval: deny }\n - { match: \"* rm *-vr\", approval: deny }\n - { match: \"* rm *-rfv *\", approval: deny }\n - { match: \"* rm *-rfv\", approval: deny }\n - { match: \"* rm *-rvf *\", approval: deny }\n - { match: \"* rm *-rvf\", approval: deny }\n - { match: \"* rm *-frv *\", approval: deny }\n - { match: \"* rm *-frv\", approval: deny }\n - { match: \"* rm *-fvr *\", approval: deny }\n - { match: \"* rm *-fvr\", approval: deny }\n - { match: \"* rm *-vrf *\", approval: deny }\n - { match: \"* rm *-vrf\", approval: deny }\n - { match: \"* rm *-vfr *\", approval: deny }\n - { match: \"* rm *-vfr\", approval: deny }\n - { match: \"* rm *-R *\", approval: deny }\n - { match: \"* rm *-R\", approval: deny }\n - { match: \"* rm *-ri *\", approval: deny }\n - { match: \"* rm *-ri\", approval: deny }\n - { match: \"* rm *-ir *\", approval: deny }\n - { match: \"* rm *-ir\", approval: deny }\n - { match: \"* rm *-Ri *\", approval: deny }\n - { match: \"* rm *-Ri\", approval: deny }\n - { match: \"* rm *-iR *\", approval: deny }\n - { match: \"* rm *-iR\", approval: deny }\n - { match: \"* rm *-Rf *\", approval: deny }\n - { match: \"* rm *-Rf\", approval: deny }\n - { match: \"* rm *-fR *\", approval: deny }\n - { match: \"* rm *-fR\", approval: deny }\n - { match: \"* rm *-Rv *\", approval: deny }\n - { match: \"* rm *-Rv\", approval: deny }\n - { match: \"* rm *-vR *\", approval: deny }\n - { match: \"* rm *-vR\", approval: deny }\n - { match: \"* rm *-Rfv *\", approval: deny }\n - { match: \"* rm *-Rfv\", approval: deny }\n - { match: \"* rm *-Rvf *\", approval: deny }\n - { match: \"* rm *-Rvf\", approval: deny }\n - { match: \"* rm *-fRv *\", approval: deny }\n - { match: \"* rm *-fRv\", approval: deny }\n - { match: \"* rm *-fvR *\", approval: deny }\n - { match: \"* rm *-fvR\", approval: deny }\n - { match: \"* rm *-vRf *\", approval: deny }\n - { match: \"* rm *-vRf\", approval: deny }\n - { match: \"* rm *-vfR *\", approval: deny }\n - { match: \"* rm *-vfR\", approval: deny }\n - { match: \"* rm *--recursive *\", approval: deny }\n - { match: \"* rm *--recursive\", approval: deny }\n # Bulk removal: find -delete, find -exec rm, and xargs rm, in every position.\n - { match: \"find *-delete*\", approval: deny }\n - { match: \"*/find *-delete*\", approval: deny }\n - { match: \"* find *-delete*\", approval: deny }\n - { match: \"*-exec rm *\", approval: deny }\n - { match: \"*-exec */rm *\", approval: deny }\n - { match: \"*-execdir rm *\", approval: deny }\n - { match: \"*-execdir */rm *\", approval: deny }\n - { match: \"*-ok rm *\", approval: deny }\n - { match: \"*-ok */rm *\", approval: deny }\n - { match: \"*-okdir rm *\", approval: deny }\n - { match: \"*-okdir */rm *\", approval: deny }\n - { match: \"*xargs rm\", approval: deny }\n - { match: \"*xargs rm *\", approval: deny }\n - { match: \"*xargs * rm\", approval: deny }\n - { match: \"*xargs * rm *\", approval: deny }\n - { match: \"*xargs */rm\", approval: deny }\n - { match: \"*xargs */rm *\", approval: deny }\n - { match: \"HOME=*\", approval: deny }\n - { match: \"export HOME=*\", approval: deny }\n - { match: \"env HOME=*\", approval: deny }\n - { match: \"env * HOME=*\", approval: deny }\n - { match: \"git push --force origin main\", approval: deny }\n - { match: \"git push --force origin main *\", approval: deny }\n - { match: \"git push --force origin master\", approval: deny }\n - { match: \"git push --force origin master *\", approval: deny }\n - { match: \"git push -f origin main\", approval: deny }\n - { match: \"git push -f origin main *\", approval: deny }\n - { match: \"git push -f origin master\", approval: deny }\n - { match: \"git push -f origin master *\", approval: deny }\n # A $ or a backtick anywhere after git push: the matcher reads the text\n # before the shell expands it, so it cannot tell a branch name from +main\n # or --force. An unquoted value inside a word also splits into more words.\n # A deny, not a prompt: the agent reads the refusal and writes the ref\n # literally (git push -u origin HEAD). No person is asked.\n # The leading * also reaches a git push after a shell keyword such as do,\n # after a wrapper such as env, and after a path such as /usr/bin/git.\n - { match: \"*git push *$*\", approval: deny }\n - { match: \"*git push *`*\", approval: deny }\n # Allow: the macOS trash command.\n - { match: \"trash *\", approval: allow }\n",
22
22
  "SoT/.omp/intercom.json": "{\n \"brokerCommand\": \"bun\",\n \"brokerArgs\": []\n}\n",
23
23
  "SoT/.omp/mcp.json": "{\n \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n \"disabledServers\": [\n \"chrome-devtools\",\n \"context7:context7\",\n \"openaiDeveloperDocs\"\n ]\n}\n",
24
24
  "SoT/.omp/models.yml": "providers:\n openai-codex:\n modelOverrides:\n gpt-6-astra:\n thinking:\n mode: effort\n efforts:\n - low\n - medium\n - high\n - xhigh\n - max\n defaultLevel: xhigh\n",
@@ -60,4 +60,4 @@ export const GENERATED_PAYLOAD_PATHS = [
60
60
  "notification.mp3"
61
61
  ] as const
62
62
 
63
- export const GENERATED_PAYLOAD_HASH = "e2f4ffdce679436cce6c177e60eee06c4855b56b229655e9da72a3e46c641d2c"
63
+ export const GENERATED_PAYLOAD_HASH = "69e352ef2541ba57fdc257e5d5fdbced56d4b9d8412bda21615199be53aad8b2"
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "docks-kit",
3
- "version": "0.22.20",
3
+ "version": "0.22.22",
4
4
  "description": "Portable AI coding agent config kit — SoT sync engine + typed CLI for Claude Code, Codex, and universal agent skills",
5
5
  "type": "module",
6
6
  "license": "MIT",