claude-dev-env 2.28.0 → 2.29.0

package/rules/AGENTS.md

@@ -1,59 +1 @@
----
-paths:
-  - "**/rules/**"
----
 
-# rules
-
-Rule files installed into `~/.claude/rules/` by `bin/install.mjs`. A rule without `paths:` frontmatter loads at the start of every session; a rule with `paths:` frontmatter loads only when the session works with a file its globs match. The `InstructionsLoaded` log records that match as a `path_glob_match` event. The `asd-ste100-language.md` file owns general user-facing language. Each other `.md` file covers one named behavior contract; hook-enforced rules are also backed by a Python hook in `hooks/`.
-
-## Files
-
-| File | Rule |
-|---|---|
-| `asd-ste100-language.md` | Sole general user-facing language authority; concise conversational adaptation of ASD-STE100 Issue 9 |
-| `agent-spawn-protocol.md` | Check context sufficiency before a spawn and ask subagents for file-and-line answers; `/prompt-generator` is recommended for a complex or user-facing spawn |
-| `anti-corollary-tests.md` | Tests must carry information: no corollary matrices over canonical reductions, no suite that only matches a dead-implementation default, stated mutation in the audit lane |
-| `ask-user-question-required.md` | Every user-directed question goes through the `AskUserQuestion` tool — no plain-text questions |
-| `bdd.md` | BDD discovery-driven development workflow and Example Mapping reference |
-| `claims-as-quotes.md` | On agent reports, hand-offs, review verdicts, and PR or commit prose, a design-gating claim travels with its quoted lines and `path:line` reference; chat keeps research-mode compact citations; a claim without its quote is a lead to check |
-| `cleanup-temp-files.md` | Remove temporary files created during a task when the task is complete |
-| `code-standards.md` | Pointer to `CODE_RULES.md` as the single source of truth, including §8 (TDD) and §7 (right-sizing); BDD is the outer process and TDD the inner loop |
-| `confirm-implementation-forks.md` | Stop and ask when two or more workable implementation paths change the deliverable |
-| `conservative-action.md` | Research and recommend when intent is ambiguous; act only on explicit request |
-| `context7.md` | Use Context7 MCP to fetch current library docs; always prefer live docs over built-in knowledge |
-| `destructive-commands.md` | Allowed removal forms and the ephemeral namespace the `destructive_command_blocker` auto-allows; keep destructive literals out of a Bash command string even as data |
-| `doc-inventory-integrity.md` | Three inventory shapes stay in step with the code: a per-directory `CLAUDE.md` file list, a package `README`/`SKILL.md` inventory, and an env-var summary table |
-| `docstring-prose-matches-implementation.md` | Prose enumerations in docstrings cover every behavior the body applies |
-| `durable-post-artifacts.md` | GitHub post bodies never reference volatile scratch paths; text embeds inline and binary artifacts upload to the `artifacts` release with the permanent URL linked |
-| `explore-thoroughly.md` | Read relevant files and map existing patterns before proposing a change |
-| `falsify-before-green.md` | A check's green counts as evidence only after that same check ran red on a named break, with a passing control beside it |
-| `file-global-constants.md` | File-global constants need at least two same-file references; otherwise move value to `config/` |
-| `few-words.md` | The style reminder. Syncs to Cursor as an always-on `.mdc` rule. |
-| `filesystem-search.md` | Every filesystem search names a scope; `es.exe`, `Glob`, `Grep`, and `Read` are equally sanctioned, and the `unscoped_search_blocker` denies a walk from a root |
-| `gh-cli-conventions.md` | `--body-file` for every `gh` body; `--paginate --slurp` piped to external `jq` for every paginated list read |
-| `git-workflow.md` | PR workflow: always create as draft, one commit per review stage, never commit working docs or images; carries the review-response protocol and a See-also block for its seven siblings |
-| `hedging-claims.md` | State the evidence or name the claim unverified; the `hedging_language_blocker` Stop hook sends a hedged response back for a re-check |
-| `long-horizon-autonomy.md` | Autonomous-run behaviors: act on what you have, do not end on a promise, delegate and keep working |
-| `measurement-denominators.md` | Every reported count names what it scanned and carries its denominator; a rate needs two runs; the consumer cross-checks the count against the scope its denominator names |
-| `nas-ssh-invocation.md` | Reach the NAS through the paramiko-backed `nas_ssh_key.py` runner, which signs in-process; every ssh-family client reads the key through file permissions, refuses it, and stalls an unattended run on a password prompt |
-| `no-cross-skill-duplicate-helpers.md` | Within one skill a duplicated helper is blocked; across two skill folders a small self-contained copy is a sanctioned isolation tradeoff that draws a non-blocking advisory naming the source skill |
-| `orphan-css-class.md` | Every `class="..."` attribute in Python-generated markup has a matching selector in the `<style>` block |
-| `paired-test-coverage.md` | A public function omitted by a module's established paired test suite must get a behavioral test |
-| `parallel-tools.md` | Make all independent tool calls in a single response |
-| `plain-illustrative-docstrings.md` | Public docstring narrative reads plainly and shows behavior with a diagram block (a `::` example or a doctest), painting a concrete scene a general developer follows on first read; a run-on backstop hook, a prose-wall backstop hook, and Category O9 audit enforce it |
-| `prompt-workflow-context-controls.md` | Keep prompt-workflow instruction layers small and stable; load heavy skills on demand |
-| `re-stage-before-commit.md` | Stage the files edited this session before `git commit`; the session edit stage gate denies a commit that leaves a tracked session edit unstaged, with `-a`, a pathspec, a preceding `git add`, and `# partial-commit` as escapes |
-| `research-mode.md` | Three anti-hallucination constraints: say "I don't know", verify with citations, quote for factual grounding |
-| `shell-invocation.md` | Windows shell commands run through `pwsh`; no `$(...)`, backtick, or process substitution in a Bash tool command |
-| `testing.md` | Test quality and infrastructure standards |
-| `vault-context.md` | Search Obsidian vault for prior sessions and decisions before substantive project work |
-| `verify-before-asking.md` | Answer questions by inspecting files or running tools before asking; recalled facts expire until re-checked this session |
-| `verify-runtime-state.md` | A "component is fine / not at fault" verdict rests on a live probe this session, never code reading or prior-session memory |
-| `windows-filesystem-safe.md` | Use safe `rmtree` patterns on Windows; `mkdirSync` with `recursive: true` on possibly-existing paths |
-| `workers-done-before-complete.md` | A task reaches `completed` only when every spawned worker has finished and its results are merged into run state |
-| `workflow-substitution-slots.md` | Per-iteration values in `.workflow.js` templates use angle-bracket slots |
-
-## Hook enforcement
-
-Rules marked with ⚡ in `~/.claude/docs/CODE_RULES.md` are backed by a blocking hook in `hooks/blocking/`. Rules without a hook are judgment-based and enforced via audit rubrics (`audit-rubrics/`).

package/rules/claims-as-quotes.md

@@ -53,13 +53,3 @@ def build_refund(order, requested_amount):
 ## Enforcement
 
 This rule binds as prose discipline: a reviewer applies it to the claims a report, a verdict, or a PR body makes about existing code. No hook backs it, because telling a design-deciding claim from background prose needs meaning a regex cannot read.
-
-## Sibling rules
-
-| Rule | Role |
-|---|---|
-| `research-mode.md` | Names what counts as a citation and grounds a factual claim in word-for-word quotes |
-| `hedging-claims.md` | Catches a hedge word standing in for evidence on a claim; this rule catches a claim missing its quote |
-| `verify-runtime-state.md` | A verdict about what runs rests on a live probe from this session |
-| `falsify-before-green.md` | A check's green counts once the check has been shown red |
-| `measurement-denominators.md` | Every count names what it scanned |

package/rules/code-standards.md

@@ -1,21 +1,21 @@
 # Code Standards
 
-> **Checked-in review contract:** [`.cursor/BUGBOT.md`](../../../.cursor/BUGBOT.md) — the human and AI review contract for code quality.
-> **Compact projection:** [`CODE_RULES.md`](../docs/CODE_RULES.md) — validated summary for generation load.
+> **Canonical review contract:** [`CODE_RULES.md`](../docs/CODE_RULES.md) — the human and AI review contract for code quality, loaded on demand.
+> **Checked-in pointer:** [`.cursor/BUGBOT.md`](../../../.cursor/BUGBOT.md) — the file Cursor BugBot reads; it points at `CODE_RULES.md`.
 > **Production enforcement:** `hooks/blocking/code_rules_enforcer.py` — hand-maintained Write/Edit gates; each mechanical rule carries a synchronization test.
 
 ## Policy surface map
 
 | Layer | Path | Role |
 |---|---|---|
-| Contract | `.cursor/BUGBOT.md` | Full review criteria for PR agents |
-| Projection | `docs/CODE_RULES.md` | Compact always-load reference; must not diverge from AGENTS |
+| Contract | `docs/CODE_RULES.md` | Full review criteria for PR agents, loaded on demand |
+| Pointer | `.cursor/BUGBOT.md` | Checked-in file Cursor BugBot reads; points at `CODE_RULES.md` |
 | Enforcer | `hooks/blocking/code_rules_enforcer.py` | Hand-maintained blockers; not generated from the docs |
 | Session rules | `rules/*.md` | Runtime session policy (questions, tasks, shell) |
 
-Load `.cursor/BUGBOT.md` when reviewing a PR or resolving a policy conflict. Load `CODE_RULES.md` when generating code under the compact checklist. Prefer linking these refs over restating rules.
+Load `CODE_RULES.md` when reviewing a PR, resolving a policy conflict, or generating code. Prefer linking this ref over restating rules.
 
-Two standards live in the canonical policy in full (and in the projection by name):
+Two standards live in `CODE_RULES.md` in full:
 
 - **TDD** — CODE_RULES §8 / AGENTS Tests: red, green, refactor; no production code before a failing test.
 - **Right-sized engineering** — CODE_RULES §7 / AGENTS Design: functions over classes; concrete over abstract; add an abstraction at the commit that introduces its second concrete implementation.

package/rules/explore-thoroughly.md

@@ -23,5 +23,4 @@ The depth budget shrinks once the evidence is in hand. When you can already name
 
 ## Relationship to other rules
 
-- **conservative-action.md** gates *whether* to act. This rule governs *how deeply* to investigate.
 - **research-mode.md** ensures factual claims are grounded. This rule ensures implementation plans are grounded in the actual codebase.

package/rules/failure-blast-radius.md

@@ -116,11 +116,3 @@ Report as: N of M complete, K parked, and what you are working now.
 Close with: what broke, how each one ended, and which of them deserve a
 durable fix.
 ```
-
-## Sibling rules
-
-| Rule | Role |
-|---|---|
-| [`code-standards.md`](code-standards.md) | `CODE_RULES.md` §9.7 names the boundary that turns a recorded per-member failure into an explicit outcome |
-| [`confirm-implementation-forks.md`](confirm-implementation-forks.md) | A defect correction creates an implementation fork when it routes around parking; surface and decide that fork |
-| [`long-horizon-autonomy.md`](long-horizon-autonomy.md) | A parked member receives an explicit report entry and follow-up |

package/rules/falsify-before-green.md

@@ -55,14 +55,6 @@ The harness writes the row, file, or event the assertion counts, so the assertio
 
 All three land together. A record carrying the red alone shows a check that fails on everything; a record carrying the control alone shows a check that passes on everything.
 
-## Sibling rules
-
-| Rule | Role |
-|---|---|
-| `anti-corollary-tests.md` | Each test carries information; the stated mutation names one code change and how many tests it kills |
-| `verify-runtime-state.md` | A runtime verdict rests on a live probe from this session |
-| `measurement-denominators.md` | Every count names what it scanned; a rate needs two runs |
-
 ## Enforcement
 
 This rule binds as prose discipline: a reviewer reads the shown-red record beside each new check a PR adds. No hook backs it, because a green that measured the code and a green that measured nothing look the same to a regex — the difference sits in what the check reached at run time.

package/rules/file-global-constants.md

@@ -24,9 +24,9 @@ Constants placed in `config/` satisfy the constants-location rule; the use-count
 
 ## Dead constant in a dedicated constants module (cross-module)
 
-The use-count rule above governs a file-global constant in production code outside `config/` by counting same-file references. A dedicated constants module — a file whose name ends in `_constants.py`, or any module under a `config/` directory — exports its constants to importer modules elsewhere, so a same-file count proves nothing. A separate hook, `check_dead_module_constants` (dispatched from `code_rules_enforcer`), governs these modules: it flags an `UPPER_SNAKE` constant defined in the written module whose name appears in no `.py` module anywhere under the enclosing package tree — not imported, not read, not listed in another module's `__all__` literal, not named in a string annotation. That is the dead exported constant CODE_RULES §9.8 targets, caught at Write/Edit time.
+The use-count rule above governs a file-global constant in production code outside `config/` by counting same-file references. A dedicated constants module — a file whose name ends in `_constants.py`, or any module under a `config/` directory — exports its constants to importer modules elsewhere, so a same-file count proves nothing.
 
-The scan resolves the enclosing package tree from the written file: for a constants module inside a package subdirectory, the tree is the package's parent (so an importer one directory up is in scope); for a `config/` module, the tree is the parent of the `config` directory. A module that declares its own `__all__` narrows the check to the constants its `__all__` list names — the explicit export surface — and requires each to be imported or read by another module; the module's own `__all__` entry does not count as that consumer, so an exported constant no module consumes is flagged, while a constant `__all__` omits is the author's private value and is left alone. A reference from a test module under the tree keeps a constant live. Test modules and migration modules are themselves exempt from the check.
+This cross-module concern belongs to the audit lane, not a write-time hook: an `UPPER_SNAKE` constant defined in a constants module whose name appears in no `.py` module anywhere under the enclosing package tree — not imported, not read, not listed in another module's `__all__` literal, not named in a string annotation — is the dead exported constant CODE_RULES §9.8 targets. Category E (dead code) is where a PR audit checks a changed constants module's exports against the rest of the package tree; a reference from a test module under the tree keeps a constant live, and a constant `__all__` omits is the author's private value and is left alone.
 
 ## Examples
 

package/rules/filesystem-search.md

@@ -43,7 +43,7 @@ When `es.exe` fails or returns nothing, fall back to `Glob` or `Grep` without pa
 
 ## Shell batching
 
-Issue one shell search at a time when the walk is large. Parallel full-tree searches contend for the shell and can lock the host. Harness `Grep` and `Glob` calls carry no such cost and run in parallel freely — see [`parallel-tools.md`](parallel-tools.md).
+Issue one shell search at a time when the walk is large. Parallel full-tree searches contend for the shell and can lock the host. Harness `Grep` and `Glob` calls carry no such cost and run in parallel freely.
 
 ## Enforcement
 

package/rules/git-workflow.md

@@ -55,12 +55,4 @@ An image a PR needs as visual evidence is not an exception to that row. Upload i
 
 Repair only reported findings, then re-verify after every repair.
 
-## See also
-
-| Rule | Covers |
-|---|---|
-| [`gh-cli-conventions.md`](gh-cli-conventions.md) | `--body-file` for post bodies; `--paginate --slurp` for list reads |
-| [`re-stage-before-commit.md`](re-stage-before-commit.md) | Staging session edits so a commit does not drop them |
-| [`durable-post-artifacts.md`](durable-post-artifacts.md) | Keeping volatile scratch paths out of a post body |
-| [`destructive-commands.md`](destructive-commands.md) | Allowed removal forms; destructive literals in commit and post bodies |
-| [`code-standards.md`](code-standards.md) | The code standards a PR's diff is reviewed against |
+Every `gh` post in this workflow uses `--body-file` per `gh-cli-conventions.md` and keeps volatile scratch paths out per `durable-post-artifacts.md`; stage session edits per `re-stage-before-commit.md` before each commit.

package/rules/hedging-claims.md

@@ -1,11 +1,7 @@
 # Hedging Claims
 
-State a claim with the evidence that backs it, or name the claim unverified. A hedge word stands in for evidence you did not gather.
+State a claim with the evidence that backs it, or name the claim unverified. A hedge word (`likely`, `probably`, `might be`, `appears to`, and similar) stands in for evidence you did not gather.
 
-`hedging_language_blocker` (Stop hook, hosted by `stop_dispatcher`) runs when `CLAUDE_PROSE_STYLE_ENFORCEMENT` is on (see [`docs/references/prose-style-enforcement.md`](../docs/references/prose-style-enforcement.md)). It blocks a response that carries a bare hedge word — `likely`, `probably`, `presumably`, `perhaps`, `possibly`, `seemingly`, `apparently`, `arguably`, `supposedly`, `ostensibly`, `conceivably`, `plausibly`, `unlikely`, `probable`, and the phrases `might be`, `could be`, `seems to be`, `appears to be`, `in all likelihood`, `more likely than not`, `it's possible that` — **unless the same sentence** labels the claim with explicit uncertainty (`unverified`, `I don't know`, `I do not know`, `no source for this claim`, `without a source`).
-
-A label in another sentence does not clear a bare hedge. Deleting the hedge word and keeping the claim does not clear the block. Gather the source, run the probe, label the claim unverified in that sentence, or ask the user through `AskUserQuestion` — then re-output the whole revised response.
-
-When enforcement is off, bare hedges still emit privacy-safe advisory candidates for precision measurement (OP-07B).
+A label elsewhere in the response does not cover a bare hedge in a different sentence. Label the claim unverified in the same sentence as the hedge, or replace the hedge: gather the source, run the probe, or ask the user through `AskUserQuestion`.
 
 Sibling rules: [`research-mode.md`](research-mode.md) names what counts as a citation; [`verify-runtime-state.md`](verify-runtime-state.md) names the live probe a runtime verdict rests on.

package/rules/long-horizon-autonomy.md

@@ -8,7 +8,7 @@ Source: [Anthropic - Prompting Claude Fable 5](https://platform.claude.com/docs/
 
 When you have enough to act, act. Do not re-derive facts already settled in the conversation, re-open a decision the user already made, or narrate options you will not pursue in user-facing text. When you weigh a choice, give a recommendation, not a full survey. This shapes user-facing messages, not your private reasoning.
 
-This is the autonomous-run partner to `conservative-action`: that rule covers the ambiguous case (research and recommend first); this one covers the clear case (once the evidence is in hand, act).
+This is the autonomous-run partner to the ambiguous case: research and recommend first when intent is unclear; this rule covers the clear case, where the evidence is already in hand.
 
 ## Do not end a turn on a promise
 

package/rules/measurement-denominators.md

@@ -34,15 +34,6 @@ A number written into a docstring or a doc carries its denominator beside it. A
 
 A sweep reports "read 3 files". The change under review touches 10 files. The arithmetic reads: the sweep covered 3 of 10, so its clean verdict covers 3 of 10. The gap is the finding — send the sweep back for the other 7, and hold the verdict until the two numbers meet.
 
-## Sibling rules
-
-| Rule | Role |
-|---|---|
-| `falsify-before-green.md` | A check's green counts once the check was shown red |
-| `anti-corollary-tests.md` | Each test carries information; no corollary matrices; no suite that only matches the dead default |
-| `docstring-prose-matches-implementation.md` | A docstring enumeration covers every behavior the body applies |
-| `measurement-denominators.md` | Every count names what it scanned; a rate needs two runs |
-
 ## Enforcement
 
 This rule binds as prose discipline: a reviewer applies it to the counts a PR's prose and docstrings state, and to the counts a report claims. No hook backs it, because weighing a figure's denominator against the scope it covers needs meaning a regex cannot read.

package/rules/research-mode.md

@@ -25,9 +25,3 @@ The grounding requirement above never relaxes: state no claim you cannot source.
 
 ## Exceptions
 Creative thinking, brainstorming, and novel ideas don't require citation. You can synthesize across sources to reach new conclusions, but the inputs must be grounded.
-
-## Sibling rules
-
-- [`explore-thoroughly.md`](explore-thoroughly.md) — grounds an implementation plan in the codebase, as this rule grounds a factual claim in a source.
-- [`verify-runtime-state.md`](verify-runtime-state.md) — a runtime verdict needs a live probe from this session, not a citation.
-- [`hedging-claims.md`](hedging-claims.md) — the Stop hook that catches a bare hedge word; an explicit uncertainty label in the same sentence is the allowed alternative to a citation.

package/rules/verify-before-asking.md

@@ -47,8 +47,3 @@ Reserve user questions for:
 
 **Wrong:** "Is there a Prisma schema in this project?"
 **Right:** Glob for `schema.prisma` and check.
-
-## Parent rules
-
-- [`ask-user-question-required.md`](ask-user-question-required.md) — once a question genuinely belongs to the user, this rule routes it through `AskUserQuestion`.
-- [`verify-runtime-state.md`](verify-runtime-state.md) — the same duty applied to a verdict: gather the live probe before you conclude, not just before you ask.

package/rules/verify-runtime-state.md

@@ -33,8 +33,3 @@ Only after a live signal backs the claim do you state it.
 
 **Wrong:** "The config sets the timeout to 30 seconds, so the timeout is fine."
 **Right:** Print the loaded config at runtime and report the value the process actually holds.
-
-## Relationship to other rules
-
-- **`verify-before-asking`** answers questions with a tool before asking the user. This rule extends that to runtime verdicts: gather the live probe before you conclude, not just before you ask.
-- **`long-horizon-autonomy`** requires every progress claim to rest on a tool result from this session. A runtime verdict is a progress claim; this rule names the probes that back it.

package/scripts/AGENTS.md

@@ -1,56 +1 @@
-# scripts
 
-Utility scripts installed into `~/.claude/scripts/` by `bin/install.mjs`. Each script is a standalone tool a user or hook can invoke directly.
-
-## Scripts
-
-| File | Purpose |
-|---|---|
-| `claude_chain_runner.py` | Runs a `claude` invocation through a fallback chain (`~/.claude/claude-chain.json`) with `--routing-mode usage_ranked` (default: probe weekly remaining once via `claude_chain_usage` / the usage-pause OAuth probe, highest remaining first) or `ordered_account` (config list order; non-usage failures stop as `advisor_blocked`); falls over only on a usage-limit failure; returns `terminal_status` / optional `session_id` on the outcome; usable as an imported module (`run_claude`) or a CLI. Copy `claude-chain.example.json` to `~/.claude/claude-chain.json` and list your account binaries. Optional per-entry `credentials_path` names that account's OAuth credentials file for the usage probe |
-| `claude_chain_usage.py` | Reports remaining weekly usage for every account in `~/.claude/claude-chain.json` via the usage-pause OAuth probe; prints JSON (`accounts` with `weekly_remaining_percent` or null plus `error`); importable `report_chain_weekly_usage` and `rank_accounts_by_weekly_remaining` (highest remaining first, ties keep config order, unmeasurable last). The chain runner consumes this ranking for try order |
-| `gh_artifact_upload.py` | Uploads a file to a repo's durable `artifacts` prerelease under a timestamped asset name and prints the permanent download URL a GitHub post can link |
-| `grok_headless_runner.py` | Runs one worker as headless `grok`: builds argv with no turn cap (the timeout is the only bound), mints a unique leader socket, captures streams, refuses a timeout that is missing, below `MIN_WORKER_TIMEOUT_SECONDS`, or above the `MAXIMUM_WORKER_TIMEOUT_SECONDS` (5400) ceiling, kills the whole process tree on timeout with grace and retries the kill-and-drain round once, classifies ok/usage_limit/auth_failure/timeout/kill_failed/error; exports `require_timeout_within_bounds` so a dispatcher can apply the same bounds without launching; imported by `spawn_grok_batch.py` and `resolve_worker_spawn.py` |
-| `grok_worker_preflight.py` | Soft gate for the headless grok tier: binary on PATH, `grok models` auth, install manifest + role agents, opt-in cached live ping; non-zero exit is fallthrough, not failure |
-| `setup_project_paths.py` | One-time bootstrap: discovers git repos via `es.exe` (Everything) and writes `~/.claude/project-paths.json`; never hardcodes scan roots |
-| `spawn_grok_batch.py` | Launches a fleet of headless grok workers from a JSON batch spec: gates once through the preflight, refuses a spec whose `timeout_seconds` exceeds `MAXIMUM_WORKER_TIMEOUT_SECONDS` (5400) rather than clamping it, assembles each prompt from part files, optionally binds a unique worker advisor per role via the lead-supplied `advisor.launcher` (placeholder default in constants), injects `advisor_session_id`, requires the same session ENDORSE or bounded CORRECTION/PLAN then ENDORSE, classifies bind/verdict/timeout/missing-launcher failures as `advisor_blocked`, staggers starts, runs each through `grok_headless_runner.py`, and emits one batch summary JSON |
-| `sweep_empty_dirs.py` | Deletes empty directories older than a configurable age under a given root; runs once (`--once`) or in continuous-watch mode |
-| `sync_to_cursor.py` | Entry point for syncing Claude rules to Cursor `.mdc` files; delegates to the `sync_to_cursor/` package |
-| `resolve_worker_spawn.py` | Dispatches a worker role through grok then claude fallback tiers (preflight, headless grok, `claude_agent_required` handoff, optional claude headless); applies `require_timeout_within_bounds` before the preflight, so an out-of-bounds `--timeout-seconds` prints a `timeout_out_of_bounds` outcome and exits 3 on every tier; protocol: [`../_shared/pr-loop/worker-spawn.md`](../_shared/pr-loop/worker-spawn.md) |
-| `active_capability_references.py` | Inventories committed skill, agent, and command names and scans package markdown for active slash or backticked capability references; fails ban-listed names outside inert historical/example fences |
-| `verify_installable_package.py` | Verifies the published package: runs real `npm pack`, checks every surface in `installable-surfaces.manifest.json` appears in the tarball, requires each `hooks.json` `.py` command to be git-tracked, and smoke-compiles those scripts (`node --check` on `bin/install.mjs`) |
-
-## PowerShell scripts
-
-| File | Purpose |
-|---|---|
-| `Audit-ShellPolicy.ps1` | Audits Bash tool calls in session transcripts against the `pwsh`-only shell policy |
-| `Migrate-ShellPolicy.ps1` | Applies automated fixes for common shell-policy violations found by the audit script |
-| `Install-SweepEmptyDirs.ps1` | Registers `sweep_empty_dirs.py` as a scheduled task on Windows |
-| `Sync-RepoMain.ps1` | Fast-forwards a main-tracking mirror (`-RepoPath`, required) to its remote main using `merge --ff-only`; refuses a different checkout or a diverged branch, logs each run to `-LogPath`, and exits non-zero so a scheduled-task history row surfaces the problem. `-StashDirty` stashes tracked changes right before the fast-forward under a dated `pre-sync stash` message and leaves the stash in the list |
-| `check.ps1` | Runs the full code-quality check suite |
-| `Get-SessionAccount.ps1` | Reports which Claude account the current session is actually logged into by comparing `~/.claude.json`'s CLI login against a `CLAUDE_USER_DATA_DIR` desktop profile's `lastKnownAccountUuid`, recovering the desktop account's email from profile storage when the two accounts differ |
-| `Capture-PoolHealth.ps1` | Captures Windows memory pool counters, high-handle processes, and kernel pool tags (via `NtQuerySystemInformation` class 22), prints a threshold verdict with a remediation map, and exits non-zero when any alert threshold fires |
-| `Show-Asset.ps1` | Opens files on screen, sizing each image window to the image's pixel dimensions and falling back to the registered default application for non-image files |
-
-## Subdirectories
-
-| Entry | Description |
-|---|---|
-| `ci/` | CI-only adapters; `windows-installer-lifecycle.ps1` runs the Node installer 16-check driver under isolated HOME/USERPROFILE/GIT_CONFIG_GLOBAL and writes bounded evidence |
-| `dev_env_scripts_constants/` | Named constants (`timing.py`, `grok_worker_constants.py`, …) for scripts in this directory, including worker-advisor placeholder launcher/model/effort, four verdict signals, correction cap, and advisor timeout |
-| `sync_to_cursor/` | Package that builds Cursor `.mdc` files from Claude rules and docs |
-| `tests/` | pytest suite for the Python scripts and Pester (`*.Tests.ps1`) suite for the PowerShell scripts in this directory |
-
-## Running tests
-
-Python scripts (pytest):
-
-```bash
-python -m pytest packages/claude-dev-env/scripts/tests/
-```
-
-PowerShell scripts (Pester 5+, `*.Tests.ps1`):
-
-```powershell
-Invoke-Pester -Path packages/claude-dev-env/scripts/tests/
-```

package/scripts/codex_compat_materializer.py

@@ -64,18 +64,12 @@ codex_hook_dependency_manifest = (
     "hooks/blocking/code_rules_comments.py",
     "hooks/blocking/code_rules_constants_config.py",
     "hooks/blocking/codex_apply_patch.py",
-    "hooks/blocking/code_rules_dead_argparse_argument.py",
-    "hooks/blocking/code_rules_dead_config_field.py",
-    "hooks/blocking/code_rules_dead_dataclass_field.py",
-    "hooks/blocking/code_rules_dead_module_constant.py",
-    "hooks/blocking/code_rules_dead_split_branch.py",
     "hooks/blocking/code_rules_docstrings.py",
     "hooks/blocking/code_rules_duplicate_body.py",
     "hooks/blocking/code_rules_enforcer.py",
     "hooks/blocking/code_rules_imports_logging.py",
     "hooks/blocking/code_rules_js_conventions.py",
     "hooks/blocking/code_rules_magic_values.py",
-    "hooks/blocking/code_rules_mock_completeness.py",
     "hooks/blocking/code_rules_naming_collection.py",
     "hooks/blocking/code_rules_optional_params.py",
     "hooks/blocking/code_rules_orphan_css_class.py",
@@ -85,7 +79,6 @@ codex_hook_dependency_manifest = (
     "hooks/blocking/code_rules_probe_chains.py",
     "hooks/blocking/code_rules_probe_detection.py",
     "hooks/blocking/code_rules_probe_recording.py",
-    "hooks/blocking/code_rules_scope_binding.py",
     "hooks/blocking/code_rules_shared.py",
     "hooks/blocking/code_rules_string_magic.py",
     "hooks/blocking/code_rules_test_assertions.py",
@@ -94,7 +87,6 @@ codex_hook_dependency_manifest = (
     "hooks/blocking/code_rules_test_layout.py",
     "hooks/blocking/code_rules_type_escape.py",
     "hooks/blocking/code_rules_typeddict_stub.py",
-    "hooks/blocking/code_rules_unused_imports.py",
     "hooks/hooks_constants/__init__.py",
     "hooks/hooks_constants/any_type_config.py",
     "hooks/hooks_constants/banned_identifiers_constants.py",
@@ -103,10 +95,6 @@ codex_hook_dependency_manifest = (
     "hooks/hooks_constants/code_rules_enforcer_constants.py",
     "hooks/hooks_constants/code_rules_path_utils_constants.py",
     "hooks/hooks_constants/command_dispatch_constants.py",
-    "hooks/hooks_constants/dead_argparse_argument_constants.py",
-    "hooks/hooks_constants/dead_config_field_constants.py",
-    "hooks/hooks_constants/dead_dataclass_field_constants.py",
-    "hooks/hooks_constants/dead_module_constant_constants.py",
     "hooks/hooks_constants/duplicate_function_body_constants.py",
     "hooks/hooks_constants/hardcoded_user_path_constants.py",
     "hooks/hooks_constants/harness_scratchpad_constants.py",

package/scripts/dev_env_scripts_constants/AGENTS.md

@@ -1,21 +1 @@
-# dev_env_scripts_constants
 
-Named constants for scripts in `scripts/`. Follows the project convention that timeouts, delays, and retries live in `timing.py`.
-
-## Modules
-
-| File | Constants for |
-|---|---|
-| `timing.py` | `sweep_empty_dirs.py` - `DEFAULT_AGE_SECONDS` (smallest age before an empty directory is eligible for removal) and `DEFAULT_POLL_INTERVAL` (seconds between sweep passes in continuous-watch mode); `spawn_grok_batch.py` - `WORKER_STAGGER_SECONDS` (seconds between staggered headless grok worker starts); `invoke_code_review.py` - `DEFAULT_CODE_REVIEW_TIMEOUT_SECONDS` (timeout for one headless `/code-review` chain run) |
-| `gh_artifact_upload_constants.py` | `gh_artifact_upload.py` - the `artifacts` release tag, title, and notes body, the GitHub CLI binary name, the asset-name timestamp format and template, the asset download URL template, the notes-file suffix, and the text encoding |
-| `claude_chain_constants.py` | `claude_chain_runner.py` - the chain config filename and home subdirectory, the usage-limit signature text, the per-binary status labels, routing-mode tokens (`usage_ranked` / `ordered_account`), outcome `terminal_status` values (`served` / `advisor_blocked` / `chain_exhausted` / `timeout`), the default timeout, CLI flag and separator tokens, config JSON keys (including optional `credentials_path`), invalid-shape reason text, config-error and exhausted-chain message templates, and CLI exit codes (including advisor-blocked); `invoke_code_review.py` and `resolve_worker_spawn.py` - the text-codec keyword names and the `collect_forwarded_text_codec` helper that forwards them to the subprocess runner for text-mode capture |
-| `claude_chain_usage_constants.py` | `claude_chain_usage.py` - full weekly percent scale, usage-pause skill path segments, CLI config-path flag, JSON report keys, and probe error message templates |
-| `grok_worker_constants.py` | `grok_worker_preflight.py`, `grok_headless_runner.py`, `spawn_grok_batch.py`, and `resolve_worker_spawn.py` - the `grok` binary name and CLI flags, model and subcommand tokens, leader-socket and scratch-file name parts, auth and usage-limit signature lists, outcome classifications, fallthrough reasons, tool-profile names and prompt headers, worker timeouts (default, plus the floor and the `MAXIMUM_WORKER_TIMEOUT_SECONDS` ceiling that the batch spec parse, the headless runner, and the spawn dispatcher all enforce, each bound carrying one rejection template shared by those sites, plus launch-failure return code and post-kill grace), the process-tree kill attempt limit and kill-failed classification, the preflight ping's single-turn cap, ping-cache keys and TTL, batch-spec and summary JSON keys, worker-advisor placeholder launcher/model/effort tokens, four verdict signals, MAXIMUM_WORKER_ADVISOR_CORRECTIONS, advisor_blocked classification, and advisor_session_id report keys, the prompt-part and report-stream join separators, and the CLI launch-error stderr prefix |
-| `code_review_constants.py` | `invoke_code_review.py` - the `/code-review ultra --fix` prompt, opus model alias, permission-mode flag and value, result mode and JSON keys, session-model CLI flag, git dirty-check tokens, and in-session return markers; finding severity tokens (`blocker` / `high` / `medium` / `low` / `nit`), verification verdict tokens, loop terminal tokens (`clean` / `nits_fixed` / `advisor_blocked`), and pure helpers for retained-finding checks, head recording, terminal resolution, and terminal encoding |
-| `active_capability_constants.py` | `active_capability_references.py` - package skills/agents/commands directory names, skill manifest filename, ban-listed capability names, inert fence languages, slash and backtick extract patterns, fence open/close patterns, banned-reason prefix, UTF-8 encoding, and newline join separator |
-| `verify_installable_package_constants.py` | `verify_installable_package.py` - manifest filename and keys, npm pack / tarball / plugin-root tokens, git and node smoke argv pieces, surface classification labels, exit codes, and CLI status headers |
-| `__init__.py` | Empty package marker |
-
-## Convention
-
-Every constant is `UPPER_SNAKE_CASE` with an explicit type annotation and a docstring. Scripts import from here rather than embedding literal values in their bodies. `code_review_constants.py` also exports pure helpers that resolve review-loop terminals from those tokens.

package/scripts/sync_to_cursor/AGENTS.md

@@ -1,23 +1 @@
-# sync_to_cursor
 
-Python package that syncs Claude rules and docs to Cursor `.mdc` files. Entry point is `packages/claude-dev-env/scripts/sync_to_cursor.py`; this package holds the implementation modules.
-
-## Modules
-
-| File | Purpose |
-|---|---|
-| `engine.py` | Main sync logic: loads the manifest, builds rule mappings, hashes sources, writes `.mdc` files, and updates the manifest; `--claude-root` and `--cursor-root` select explicit layouts |
-| `rules.py` | Builds `RuleMapping` objects from Claude rule markdown files; applies transforms to fit Cursor's `.mdc` format; maps remaining `rules/*.md` files to `<stem>.mdc` |
-| `canonical_docs.py` | Checks and syncs canonical documentation files (`CODE_RULES.md`, `TEST_QUALITY.md`) to the Cursor rules directory |
-| `paths.py` | Resolves the Claude and Cursor layout paths; respects the `LLM_SETTINGS_ROOT` env var for non-home layouts |
-| `hashing.py` | SHA-256 helpers that detect whether source files changed since the last sync run |
-| `config/` | Package-level constants: `GENERATOR_VERSION`, `ALL_CANONICAL_DOC_FILES`, `MAX_RULE_BODY_LINES`, skipped inventory filenames, markdown suffix |
-| `__init__.py` | Empty package marker |
-
-## Layout resolution
-
-`paths.py` reads `LLM_SETTINGS_ROOT` from the environment. When set, it uses that path as the base for both `.claude/` and `.cursor/`. When unset, it falls back to `Path.home()`.
-
-## Tests
-
-Tests live in `packages/claude-dev-env/scripts/tests/test_sync_to_cursor.py`.

package/scripts/sync_to_cursor/rules.py

@@ -67,7 +67,6 @@ _merged_mapping_key_order = (
     "bdd",
     "test-quality",
     "research-mode",
-    "conservative-action",
     "explore-thoroughly",
 )
 
@@ -372,15 +371,6 @@ def _always_apply_mappings(rules_directory: Path, docs_directory: Path) -> tuple
             "Research mode: citations and I don't know",
             "near_verbatim",
         ),
-        RuleMapping(
-            "conservative-action",
-            (rules_directory / "conservative-action.md",),
-            "conservative-action.mdc",
-            True,
-            None,
-            "Prefer research over action when intent is unclear",
-            "near_verbatim",
-        ),
         RuleMapping(
             "explore-thoroughly",
             (rules_directory / "explore-thoroughly.md",),

package/scripts/tests/AGENTS.md

@@ -1,35 +1 @@
-# scripts/tests
 
-pytest suite for the Python scripts and Pester suite for the PowerShell scripts in `scripts/`.
-
-## Test files
-
-| File | Covers |
-|---|---|
-| `test_setup_project_paths.py` | `setup_project_paths.py` — discovery, filtering, and `project-paths.json` writing |
-| `test_setup_project_paths_config.py` | Configuration constants used by `setup_project_paths.py` |
-| `test_sweep_empty_dirs.py` | `sweep_empty_dirs.py` — age check, one-shot mode, and continuous-watch behavior |
-| `test_sync_to_cursor.py` | `sync_to_cursor/` package — mapping, hashing, manifest, and path resolution |
-| `test_rules.py` | Discovered Claude `rules/*.md` mappings to stem-named Cursor `.mdc` files |
-| `test_engine.py` | `sync_to_cursor` engine `--claude-root` / `--cursor-root` layout flags |
-| `test_grok_worker_constants.py` | `grok_worker_constants.py` — the accepted batch worker-key set stays in step with the worker key constants, and the unknown-key message names both its placeholders |
-
-## PowerShell test files
-
-| File | Covers |
-|---|---|
-| `Get-SessionAccount.Tests.ps1` | `Get-SessionAccount.ps1` — noise filtering, profile-storage email recovery, CLI-vs-desktop account resolution, and output formatting |
-
-## Running
-
-Python scripts (pytest):
-
-```bash
-python -m pytest packages/claude-dev-env/scripts/tests/
-```
-
-PowerShell scripts (Pester 5+, `*.Tests.ps1`):
-
-```powershell
-Invoke-Pester -Path packages/claude-dev-env/scripts/tests/
-```

package/scripts/tests/test_engine.py

@@ -46,7 +46,6 @@ def _write_minimal_curated_rules(rules_directory: Path) -> None:
         encoding="utf-8",
     )
     (rules_directory / "research-mode.md").write_text("# RM\n", encoding="utf-8")
-    (rules_directory / "conservative-action.md").write_text("# CA\n", encoding="utf-8")
     (rules_directory / "explore-thoroughly.md").write_text("# ET\n", encoding="utf-8")
 
 

package/scripts/tests/test_rules.py

@@ -30,7 +30,6 @@ def _write_minimal_curated_rules(rules_directory: Path) -> None:
         encoding="utf-8",
     )
     (rules_directory / "research-mode.md").write_text("# RM\n", encoding="utf-8")
-    (rules_directory / "conservative-action.md").write_text("# CA\n", encoding="utf-8")
     (rules_directory / "explore-thoroughly.md").write_text("# ET\n", encoding="utf-8")
 
 

package/scripts/tests/test_sync_to_cursor.py

@@ -44,7 +44,6 @@ def _minimal_rule_files(claude_rules: Path) -> None:
         encoding="utf-8",
     )
     (claude_rules / "research-mode.md").write_text("# RM\n", encoding="utf-8")
-    (claude_rules / "conservative-action.md").write_text("# CA\n", encoding="utf-8")
     (claude_rules / "explore-thoroughly.md").write_text("# ET\n", encoding="utf-8")
 
 

package/system-prompts/AGENTS.md

@@ -1,25 +1 @@
-# system-prompts
 
-System-prompt reference files installed into `~/.claude/system-prompts/` by `bin/install.mjs`. Rules and skills pull a file (or one of its sections) into context on demand by citing its installed path.
-
-Use `~/.claude/rules/asd-ste100-language.md` for user-facing word choice,
-sentence style, tone, punctuation, and prose form. Each prompt keeps its
-role-specific behavior contract.
-
-ELI5 owns the global beginner presentation envelope: large visuals, minimal
-text, one stable self-contained HTML artifact, update-in-place continuity, and
-sharing.
-
-## Files
-
-| File | Purpose |
-|---|---|
-| `software-engineer.xml` | Software-engineering reference: defines the engineering role, task-scope rules, output style, and the BDD `<behavior_protocol>` that `rules/bdd.md` cites on demand |
-
-## Format
-
-Files use XML with named sections (`<role>`, `<task_scope>`, `<output_style>`, `<behavior_protocol>`, etc.). A rule or skill cites a file, or one of its sections, to pull it into context when the task needs it.
-
-## Adding a prompt
-
-Create a new `.xml` file and run `bin/install.mjs` to copy it to `~/.claude/system-prompts/`. Reference the new file in the relevant rule or skill by its installed path.

package/system-prompts/software-engineer.xml

@@ -94,9 +94,9 @@
 </problem_solving>
 
 <code_quality>
-  The checked-in .cursor/BUGBOT.md is the full code-quality review contract.
-  ~/.claude/docs/CODE_RULES.md is the compact projection for generation load.
-  The checklist below is a short reminder, not a
+  ~/.claude/docs/CODE_RULES.md is the full code-quality review contract, loaded on demand.
+  The checked-in .cursor/BUGBOT.md is the pointer file Cursor BugBot reads; it points at
+  CODE_RULES.md. The checklist below is a short reminder, not a
   second canonical source.
 
   Naming — full words only: