ai-engineering-loop 1.14.0 → 1.15.0

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.
Files changed (92) hide show
  1. package/.agents/{workflows/ai-engineering-loop.md → skills/ai-engineering-loop/SKILL.md} +8 -6
  2. package/.agents/skills/ai-engineering-loop/references/loop-hosts.md +44 -0
  3. package/.claude/skills/ai-engineering-loop/SKILL.md +9 -10
  4. package/.claude/skills/ai-engineering-loop/references/loop-hosts.md +44 -0
  5. package/CHANGELOG.md +47 -0
  6. package/README.md +52 -6
  7. package/adapters/dot/README.md +1 -1
  8. package/bin/ai-engineering-loop.js +296 -11
  9. package/core/grill-policy.md +1 -1
  10. package/core/runtime-safety.md +2 -1
  11. package/lib/auto-update.js +3 -1
  12. package/lib/cli-args.js +11 -0
  13. package/lib/doctor.js +4 -15
  14. package/lib/host-skill-build.js +15 -15
  15. package/lib/hosts/agent-formats.js +135 -0
  16. package/lib/hosts/commands.js +126 -0
  17. package/lib/hosts/detect.js +56 -0
  18. package/lib/hosts/doctor.js +76 -0
  19. package/lib/hosts/redetect.js +60 -0
  20. package/lib/hosts/registry.js +271 -0
  21. package/lib/hosts/table.js +35 -0
  22. package/lib/run-abandon.js +116 -0
  23. package/lib/sync-hosts.js +155 -112
  24. package/package.json +2 -3
  25. package/.agents/devil-advocate.md +0 -79
  26. package/.agents/judge.md +0 -58
  27. package/.claude/commands/ai-engineering-loop.md +0 -11
  28. package/.gemini/skills/ai-engineering-loop/SKILL.md +0 -61
  29. package/.gemini/skills/animate/RECIPES.md +0 -324
  30. package/.gemini/skills/animate/SKILL.md +0 -207
  31. package/.gemini/skills/animate-expo/RECIPES.md +0 -385
  32. package/.gemini/skills/animate-expo/SKILL.md +0 -263
  33. package/.gemini/skills/animation-vocabulary/SKILL.md +0 -181
  34. package/.gemini/skills/apple-design/SKILL.md +0 -290
  35. package/.gemini/skills/ask-sonner/API.md +0 -64
  36. package/.gemini/skills/ask-sonner/SKILL.md +0 -88
  37. package/.gemini/skills/backend-development/SKILL.md +0 -272
  38. package/.gemini/skills/backend-development/references/api-design-guidelines.md +0 -95
  39. package/.gemini/skills/backend-development/references/query-and-database-best-practices.md +0 -53
  40. package/.gemini/skills/backend-development/references/security-checklist.md +0 -60
  41. package/.gemini/skills/emil-design-eng/SKILL.md +0 -674
  42. package/.gemini/skills/find-animation-opportunities/SKILL.md +0 -140
  43. package/.gemini/skills/improve-animations/AUDIT.md +0 -115
  44. package/.gemini/skills/improve-animations/PLAN-TEMPLATE.md +0 -73
  45. package/.gemini/skills/improve-animations/SKILL.md +0 -109
  46. package/.gemini/skills/mobile-native/SKILL.md +0 -311
  47. package/.gemini/skills/pick-ui-library/SKILL.md +0 -85
  48. package/.gemini/skills/prototype/PICKER.md +0 -197
  49. package/.gemini/skills/prototype/SKILL.md +0 -98
  50. package/.gemini/skills/review-animations/SKILL.md +0 -120
  51. package/.gemini/skills/review-animations/STANDARDS.md +0 -187
  52. package/.gemini/skills/write-swift/SKILL.md +0 -396
  53. package/.grok/commands/ai-engineering-loop.md +0 -11
  54. package/.grok/skills/ai-engineering-loop/SKILL.md +0 -62
  55. package/.grok/skills/ai-engineering-loop/references/loop-commands.md +0 -20
  56. package/.grok/skills/ai-engineering-loop/references/loop-deliver.md +0 -8
  57. package/.grok/skills/ai-engineering-loop/references/loop-goal.md +0 -10
  58. package/.grok/skills/ai-engineering-loop/references/loop-maker.md +0 -8
  59. package/.grok/skills/ai-engineering-loop/references/loop-review.md +0 -18
  60. package/.grok/skills/ai-engineering-loop/references/loop-risky.md +0 -9
  61. package/.grok/skills/ai-engineering-loop/references/loop-verify.md +0 -20
  62. package/.grok/skills/animate/RECIPES.md +0 -324
  63. package/.grok/skills/animate/SKILL.md +0 -207
  64. package/.grok/skills/animate-expo/RECIPES.md +0 -385
  65. package/.grok/skills/animate-expo/SKILL.md +0 -263
  66. package/.grok/skills/animation-vocabulary/SKILL.md +0 -181
  67. package/.grok/skills/apple-design/SKILL.md +0 -290
  68. package/.grok/skills/ask-sonner/API.md +0 -64
  69. package/.grok/skills/ask-sonner/SKILL.md +0 -88
  70. package/.grok/skills/backend-development/SKILL.md +0 -272
  71. package/.grok/skills/backend-development/references/api-design-guidelines.md +0 -95
  72. package/.grok/skills/backend-development/references/query-and-database-best-practices.md +0 -53
  73. package/.grok/skills/backend-development/references/security-checklist.md +0 -60
  74. package/.grok/skills/emil-design-eng/SKILL.md +0 -674
  75. package/.grok/skills/find-animation-opportunities/SKILL.md +0 -140
  76. package/.grok/skills/improve-animations/AUDIT.md +0 -115
  77. package/.grok/skills/improve-animations/PLAN-TEMPLATE.md +0 -73
  78. package/.grok/skills/improve-animations/SKILL.md +0 -109
  79. package/.grok/skills/mobile-native/SKILL.md +0 -311
  80. package/.grok/skills/pick-ui-library/SKILL.md +0 -85
  81. package/.grok/skills/prototype/PICKER.md +0 -197
  82. package/.grok/skills/prototype/SKILL.md +0 -98
  83. package/.grok/skills/review-animations/SKILL.md +0 -120
  84. package/.grok/skills/review-animations/STANDARDS.md +0 -187
  85. package/.grok/skills/write-swift/SKILL.md +0 -396
  86. /package/{.gemini → .agents}/skills/ai-engineering-loop/references/loop-commands.md +0 -0
  87. /package/{.gemini → .agents}/skills/ai-engineering-loop/references/loop-deliver.md +0 -0
  88. /package/{.gemini → .agents}/skills/ai-engineering-loop/references/loop-goal.md +0 -0
  89. /package/{.gemini → .agents}/skills/ai-engineering-loop/references/loop-maker.md +0 -0
  90. /package/{.gemini → .agents}/skills/ai-engineering-loop/references/loop-review.md +0 -0
  91. /package/{.gemini → .agents}/skills/ai-engineering-loop/references/loop-risky.md +0 -0
  92. /package/{.gemini → .agents}/skills/ai-engineering-loop/references/loop-verify.md +0 -0
@@ -1,18 +1,20 @@
1
1
  ---
2
2
  name: ai-engineering-loop
3
- description: Run the AI Engineering Loop on Antigravity (init, status, refresh, or full Maker then Devil's Advocate then Judge).
3
+ description: Use when the user runs /ai-engineering-loop, says "run the engineering loop" or "devil's advocate review", asks to init or refresh living project context, or wants the Maker / Devil's Advocate / Judge engineering loop.
4
4
  ---
5
5
  <!-- Generated from skill-src/ by npm run build:skills; do not edit. -->
6
6
 
7
- # AI Engineering Loop (Antigravity workflow)
7
+ # AI Engineering Loop
8
8
 
9
- Stage details: the `loop-*` references via `npx ai-engineering-loop docs <name>`, read only on entering that stage. Specs and references: `npx ai-engineering-loop docs <name> [--section <h>]`; never read whole spec directories.
9
+ Stage details: `references/loop-*.md` beside this file (also via `docs`), read only on entering that stage. Specs and references: `npx ai-engineering-loop docs <name> [--section <h>]`; never read whole spec directories.
10
10
 
11
11
  ## Host rules
12
12
 
13
- 1. If `invoke_subagent` (or Task) exists, spawn `devil-advocate` then `judge` as siblings and wait for each; `general-purpose` only if rejected. Do not use `browser_subagent`.
13
+ Same skill on every host. Before the first DA or Judge spawn, read your host's section in `loop-hosts` (exact tool, allowed keys, fallbacks).
14
+ 1. Spawn `devil-advocate` then `judge` as fresh siblings with the host's own subagent tool, passing only keys its schema has; wait for each, never in the background or nested; `general-purpose` only if the named type is rejected. Never use a browser subagent as reviewer.
14
15
  2. No subagent tool: same budgets in this session as `CONTEXT_ISOLATION_ONLY`; never claim independent execution.
15
- 3. Models: the host catalog; never type a model name.
16
+ 3. A tool says "cannot determine the safety" or returns HTTP 400: stop that tool, do not retry, continue read-only, and tell the user (`loop-hosts`).
17
+ 4. Models: the host catalog (`/models`, `grok models`); never type a model name.
16
18
 
17
19
  ## Commands
18
20
 
@@ -41,7 +43,7 @@ Invariants (every tier):
41
43
 
42
44
  ## Report header
43
45
 
44
- When a child actually returned a result:
46
+ When a subagent actually returned its own result (Grok: its own `subagent_id`):
45
47
 
46
48
  ```
47
49
  Execution Mode: TRUE_INDEPENDENT_AGENT
@@ -0,0 +1,44 @@
1
+ # Host rules: subagent tools per host
2
+
3
+ Read only your host's section, before the first Devil's Advocate (DA) or Judge spawn. Every host shares the loop, budgets, and gates; only the spawn mechanics differ. Modes: `TRUE_INDEPENDENT_AGENT`, `ISOLATED_AGENT_INSTANCE`, `FRESH_PROCESS_AGENT`, `CONTEXT_ISOLATION_ONLY`, `UNAVAILABLE`.
4
+
5
+ ## Claude Code (and Kiro-backed strict proxies)
6
+
7
+ Strict proxies (including Kiro) return HTTP 400 `REQUEST_BODY_INVALID` on unknown keys:
8
+ 1. Use only tools that exist in this session. Spawn subagents with **Task** (or **Agent** if that is the only one), passing only `subagent_type`, `description`, `prompt`, and `run_in_background: false` only if the schema has it. Never invent other keys.
9
+ 2. `subagent_type: devil-advocate` / `judge`; `general-purpose` only if rejected. No Task/Agent tool: review in this session as `CONTEXT_ISOLATION_ONLY`.
10
+ 3. Bash or Write says "cannot determine the safety" or 400: stop that tool, do not retry, use Read/Grep/Glob, and tell the user to leave auto permission mode or add a permissions.allow rule, then start a new session.
11
+ 4. Models: `/models` when it exists; never type a model name.
12
+
13
+ ## Grok CLI
14
+
15
+ 1. `spawn_subagent` present and `GROK_SUBAGENTS` not `0`: review is **INVOCATION_AVAILABLE**; **PROVEN** only after a child returns its own `subagent_id`. Otherwise use `CONTEXT_ISOLATION_ONLY`, disclosed; never call it a subagent review.
16
+ 2. Siblings only (depth limit 1): `capability_mode: "execute"`, `background: false`, `isolation: none`, no `resume_from`. Forbidden `subagent_type` for DA/Judge: `caveman:cavecrew-reviewer`, `caveman:cavecrew-builder`, `caveman:cavecrew-investigator`, `explore`, `plan`. Unregistered: `general-purpose`, agent spec prepended, `description` prefixed `[devil-advocate]`/`[judge]`.
17
+ 3. Models: `grok models` (drop grok-imagine-* and video); never type a model name. Headless `grok -p` is `FRESH_PROCESS_AGENT` only once it prints a model response.
18
+ 4. Alias: `NATIVE_SUBAGENT` → `TRUE_INDEPENDENT_AGENT`.
19
+
20
+ ## Antigravity (IDE, 2.0, `agy` CLI)
21
+
22
+ 1. If `invoke_subagent` (or Task) exists, spawn `devil-advocate` then `judge` (custom agents with `subagent: true`) as siblings, wait for each, never in the background; `general-purpose` only if the named type is rejected. Do not use `browser_subagent` (or the `browser` subagent).
23
+ 2. No subagent tool: run the same budgets in this session as `CONTEXT_ISOLATION_ONLY`; do not claim independent agent execution.
24
+ 3. Models: the host catalog (`/models` when it exists); never type a model name.
25
+
26
+ ## Gemini CLI
27
+
28
+ 1. Subagents `devil-advocate` and `judge` live in `~/.gemini/agents/` after `sync-hosts`; delegate to them by name when the session exposes them, one at a time, and wait.
29
+ 2. Otherwise `CONTEXT_ISOLATION_ONLY`. Models: `/model`; never type a model name.
30
+
31
+ ## Codex CLI
32
+
33
+ 1. Custom agents `devil-advocate` and `judge` live in `~/.codex/agents/*.toml` after `sync-hosts`; spawn them as sibling agents when the session has a spawn tool, and wait for each result.
34
+ 2. Otherwise `CONTEXT_ISOLATION_ONLY`. Models: the host catalog; never type a model name.
35
+
36
+ ## Cursor, GitHub Copilot, OpenCode, Factory Droid, Augment, Qwen Code, Kiro, Junie
37
+
38
+ 1. `sync-hosts` installs `devil-advocate` and `judge` in the host's own agent format. Delegate with the host's subagent tool by that name (Cursor subagents, Copilot custom agents, OpenCode `@devil-advocate`, Droid Task `subagent_type`, Auggie subagents, Qwen `/agents`, Kiro custom agents, Junie subagents), one at a time, and wait.
39
+ 2. No subagent tool, or the agent is missing: `CONTEXT_ISOLATION_ONLY`.
40
+
41
+ ## Other hosts (Windsurf/Devin, Amp, Zed, Goose, Cline, Roo, unknown)
42
+
43
+ 1. Use a native subagent only if it can run the DA or Judge prompt with a fresh context and return its own result; read-only research subagents qualify only for DA.
44
+ 2. Otherwise run DA and Judge in this session as `CONTEXT_ISOLATION_ONLY`, disclosed, with the same budgets.
@@ -1,21 +1,20 @@
1
1
  ---
2
2
  name: ai-engineering-loop
3
- description: Use when the user runs /ai-engineering-loop, asks to init or refresh living project context, or wants the Maker / Devil's Advocate / Judge engineering loop on Claude Code.
4
- allowed-tools: "Read, Grep, Glob, Edit, Write, Task, Bash(npm run *), Bash(npm test *), Bash(npx *), Bash(git *)"
3
+ description: Use when the user runs /ai-engineering-loop, says "run the engineering loop" or "devil's advocate review", asks to init or refresh living project context, or wants the Maker / Devil's Advocate / Judge engineering loop.
5
4
  ---
6
5
  <!-- Generated from skill-src/ by npm run build:skills; do not edit. -->
7
6
 
8
- # AI Engineering Loop (Claude Code)
7
+ # AI Engineering Loop
9
8
 
10
- Stage details: `references/loop-*.md` beside this file, read only on entering that stage. Specs and references: `npx ai-engineering-loop docs <name> [--section <h>]`; never read whole spec directories.
9
+ Stage details: `references/loop-*.md` beside this file (also via `docs`), read only on entering that stage. Specs and references: `npx ai-engineering-loop docs <name> [--section <h>]`; never read whole spec directories.
11
10
 
12
11
  ## Host rules
13
12
 
14
- Strict proxies (including Kiro) return HTTP 400 `REQUEST_BODY_INVALID` on unknown keys:
15
- 1. Use only tools that exist in this session. Spawn subagents with **Task** (or **Agent** if that is the only one), passing only `subagent_type`, `description`, `prompt`, and `run_in_background: false` only if the schema has it. Never invent other keys.
16
- 2. `subagent_type: devil-advocate` / `judge`; `general-purpose` only if rejected. No Task/Agent tool: review in this session as `CONTEXT_ISOLATION_ONLY`.
17
- 3. Bash or Write says "cannot determine the safety" or 400: stop that tool, do not retry, use Read/Grep/Glob, and tell the user to leave auto permission mode or add a permissions.allow rule, then start a new session.
18
- 4. Models: `/models` when it exists; never type a model name.
13
+ Same skill on every host. Before the first DA or Judge spawn, read your host's section in `loop-hosts` (exact tool, allowed keys, fallbacks).
14
+ 1. Spawn `devil-advocate` then `judge` as fresh siblings with the host's own subagent tool, passing only keys its schema has; wait for each, never in the background or nested; `general-purpose` only if the named type is rejected. Never use a browser subagent as reviewer.
15
+ 2. No subagent tool: same budgets in this session as `CONTEXT_ISOLATION_ONLY`; never claim independent execution.
16
+ 3. A tool says "cannot determine the safety" or returns HTTP 400: stop that tool, do not retry, continue read-only, and tell the user (`loop-hosts`).
17
+ 4. Models: the host catalog (`/models`, `grok models`); never type a model name.
19
18
 
20
19
  ## Commands
21
20
 
@@ -44,7 +43,7 @@ Invariants (every tier):
44
43
 
45
44
  ## Report header
46
45
 
47
- When Task/Agent returned a child result:
46
+ When a subagent actually returned its own result (Grok: its own `subagent_id`):
48
47
 
49
48
  ```
50
49
  Execution Mode: TRUE_INDEPENDENT_AGENT
@@ -0,0 +1,44 @@
1
+ # Host rules: subagent tools per host
2
+
3
+ Read only your host's section, before the first Devil's Advocate (DA) or Judge spawn. Every host shares the loop, budgets, and gates; only the spawn mechanics differ. Modes: `TRUE_INDEPENDENT_AGENT`, `ISOLATED_AGENT_INSTANCE`, `FRESH_PROCESS_AGENT`, `CONTEXT_ISOLATION_ONLY`, `UNAVAILABLE`.
4
+
5
+ ## Claude Code (and Kiro-backed strict proxies)
6
+
7
+ Strict proxies (including Kiro) return HTTP 400 `REQUEST_BODY_INVALID` on unknown keys:
8
+ 1. Use only tools that exist in this session. Spawn subagents with **Task** (or **Agent** if that is the only one), passing only `subagent_type`, `description`, `prompt`, and `run_in_background: false` only if the schema has it. Never invent other keys.
9
+ 2. `subagent_type: devil-advocate` / `judge`; `general-purpose` only if rejected. No Task/Agent tool: review in this session as `CONTEXT_ISOLATION_ONLY`.
10
+ 3. Bash or Write says "cannot determine the safety" or 400: stop that tool, do not retry, use Read/Grep/Glob, and tell the user to leave auto permission mode or add a permissions.allow rule, then start a new session.
11
+ 4. Models: `/models` when it exists; never type a model name.
12
+
13
+ ## Grok CLI
14
+
15
+ 1. `spawn_subagent` present and `GROK_SUBAGENTS` not `0`: review is **INVOCATION_AVAILABLE**; **PROVEN** only after a child returns its own `subagent_id`. Otherwise use `CONTEXT_ISOLATION_ONLY`, disclosed; never call it a subagent review.
16
+ 2. Siblings only (depth limit 1): `capability_mode: "execute"`, `background: false`, `isolation: none`, no `resume_from`. Forbidden `subagent_type` for DA/Judge: `caveman:cavecrew-reviewer`, `caveman:cavecrew-builder`, `caveman:cavecrew-investigator`, `explore`, `plan`. Unregistered: `general-purpose`, agent spec prepended, `description` prefixed `[devil-advocate]`/`[judge]`.
17
+ 3. Models: `grok models` (drop grok-imagine-* and video); never type a model name. Headless `grok -p` is `FRESH_PROCESS_AGENT` only once it prints a model response.
18
+ 4. Alias: `NATIVE_SUBAGENT` → `TRUE_INDEPENDENT_AGENT`.
19
+
20
+ ## Antigravity (IDE, 2.0, `agy` CLI)
21
+
22
+ 1. If `invoke_subagent` (or Task) exists, spawn `devil-advocate` then `judge` (custom agents with `subagent: true`) as siblings, wait for each, never in the background; `general-purpose` only if the named type is rejected. Do not use `browser_subagent` (or the `browser` subagent).
23
+ 2. No subagent tool: run the same budgets in this session as `CONTEXT_ISOLATION_ONLY`; do not claim independent agent execution.
24
+ 3. Models: the host catalog (`/models` when it exists); never type a model name.
25
+
26
+ ## Gemini CLI
27
+
28
+ 1. Subagents `devil-advocate` and `judge` live in `~/.gemini/agents/` after `sync-hosts`; delegate to them by name when the session exposes them, one at a time, and wait.
29
+ 2. Otherwise `CONTEXT_ISOLATION_ONLY`. Models: `/model`; never type a model name.
30
+
31
+ ## Codex CLI
32
+
33
+ 1. Custom agents `devil-advocate` and `judge` live in `~/.codex/agents/*.toml` after `sync-hosts`; spawn them as sibling agents when the session has a spawn tool, and wait for each result.
34
+ 2. Otherwise `CONTEXT_ISOLATION_ONLY`. Models: the host catalog; never type a model name.
35
+
36
+ ## Cursor, GitHub Copilot, OpenCode, Factory Droid, Augment, Qwen Code, Kiro, Junie
37
+
38
+ 1. `sync-hosts` installs `devil-advocate` and `judge` in the host's own agent format. Delegate with the host's subagent tool by that name (Cursor subagents, Copilot custom agents, OpenCode `@devil-advocate`, Droid Task `subagent_type`, Auggie subagents, Qwen `/agents`, Kiro custom agents, Junie subagents), one at a time, and wait.
39
+ 2. No subagent tool, or the agent is missing: `CONTEXT_ISOLATION_ONLY`.
40
+
41
+ ## Other hosts (Windsurf/Devin, Amp, Zed, Goose, Cline, Roo, unknown)
42
+
43
+ 1. Use a native subagent only if it can run the DA or Judge prompt with a fresh context and return its own result; read-only research subagents qualify only for DA.
44
+ 2. Otherwise run DA and Judge in this session as `CONTEXT_ISOLATION_ONLY`, disclosed, with the same budgets.
package/CHANGELOG.md CHANGED
@@ -6,6 +6,53 @@ All notable changes to this project are documented here. Versions follow [Semant
6
6
 
7
7
  _No changes yet._
8
8
 
9
+ ## 1.15.0 - 2026-10-11
10
+
11
+ ### Multi-agent hosts: `setup` suggests `auto` detection mode (#54 decision 4)
12
+
13
+ - **Changed:** interactive `setup` now asks "Sync agents you install later automatically? [Y/n] (recommended: Y = auto)"; pressing Enter picks `auto`. `setup --yes`, a missing TTY, CI, and scripts keep `manual` unless `--mode` is passed. Gemini CLI detection, Kiro/Junie read-only reviewers, and the deferred Cline reviewer are unchanged.
14
+
15
+ ### Multi-agent hosts, phase 4: new agents, `hosts doctor`, generated host table (#52)
16
+
17
+ - **Added:** agents installed after `setup` are detected again (stat only). With `hosts.mode: auto`, the background `update auto` of a global install enables and syncs them; a host you disabled stays disabled. With `manual` (default), `status` prints one short notice per new agent, at most once a day. Nothing is written or shown in CI, in `--json` output, or with `AEL_NO_AUTO_UPDATE=1`. `update auto --json` reports `hosts.added`.
18
+ - **Added:** `hosts doctor [--json]`: per enabled host, how many copies of the core skill it sees across the folders it scans, whether they are identical, and which AEL files still need a sync. Read-only; exits 1 when something needs attention.
19
+ - **Changed:** the README host table is generated from `lib/hosts/registry.js` (`npm run build:hosts-table`); `npm test` fails when it drifts.
20
+
21
+ ### Multi-agent hosts, phase 3: own-folder hosts (#51)
22
+
23
+ - **Added:** Cline (`~/.cline/skills`), Kiro (`~/.kiro/skills`), and Qwen Code (`~/.qwen/skills`) get their own byte-identical copy of the skill, because they do not read `~/.agents/skills/`.
24
+ - **Added:** Roo Code and JetBrains Junie, which the current docs show also read `~/.agents/skills/`, so they use the shared copy (the research report had marked this as inferred "no").
25
+ - **Added:** reviewer subagents for Kiro (`~/.kiro/agents/*.md`, `tools: [read]`), Qwen (`~/.qwen/agents/*.md`, `approvalMode: plan`), and Junie (`~/.junie/agents/*.md`, `tools: [Read, Grep]`). Cline and Roo get none (no documented file format), so the loop runs `CONTEXT_ISOLATION_ONLY` there.
26
+
27
+ ### Multi-agent hosts, phase 2: shared-folder hosts (#50)
28
+
29
+ - **Added:** OpenCode, Windsurf/Devin Desktop, Amp, Factory Droid, Augment (Auggie), Zed, and Goose to the host registry. All of them read the shared `~/.agents/skills/` folder, so they use the same single copy of the skill and never get a second one in their own folders.
30
+ - **Added:** reviewer subagents where the host supports file-based ones: OpenCode `~/.config/opencode/agents/*.md` (`mode: subagent`, edits denied), Factory `~/.factory/droids/*.md` (`tools: read-only`), and Augment `~/.augment/agents/*.md`. Amp (TypeScript plugins), Zed, Goose, and Windsurf have no file-based reviewer agent, so the loop runs DA and Judge as `CONTEXT_ISOLATION_ONLY` there.
31
+
32
+ ### Multi-agent hosts, phase 1: host registry, setup, and `hosts` (#49)
33
+
34
+ - **Added:** a data-driven host registry (`lib/hosts/registry.js`). Each entry holds detection signals, the skill folder (the shared `~/.agents/skills` or the host's own), the folders the host scans, the reviewer subagent format, official doc links, and a verification date. Tier 1 hosts: Claude Code, Codex CLI, Gemini CLI, Antigravity (IDE/2.0 and the `agy` CLI), Grok CLI, Cursor, and GitHub Copilot.
35
+ - **Added:** detection by config folder or by an executable on `PATH`. The binary is checked with `stat` only and never executed.
36
+ - **Added:** reviewer subagents in each host's own format, all from the same `agents/shared/*.body.md`: Codex `~/.codex/agents/*.toml` (read-only sandbox), Gemini CLI `~/.gemini/agents/*.md`, Cursor `~/.cursor/agents/*.md` (`readonly`), and Copilot `~/.copilot/agents/*.agent.md`.
37
+ - **Added:** `setup [--yes] [--hosts a,b] [--mode auto|manual] [--json]`, which runs once and asks before writing. Without a TTY it prints the plan and writes nothing unless `--yes` is passed. Also added: `hosts list [--json]`, `hosts enable <id...>`, and `hosts disable <id...>`. Disabling removes only manifest-tracked files that AEL wrote and you did not edit. The shared folder stays while any enabled host still reads it.
38
+ - **Added:** a first-run hint that replaces a `postinstall` hook. It appears on interactive stderr at most once a day until hosts are chosen, never in CI or `--json`, and can be silenced with `AEL_NO_SETUP_HINT=1`. The package still defines no install script.
39
+ - Until `setup` runs, `sync-hosts` and `update auto` write only to hosts whose config folder already exists, or that an earlier sync already installed. Hosts found only on `PATH` wait for `setup`.
40
+
41
+ ### Multi-agent hosts, phase 0: close the host gaps (#48)
42
+
43
+ - **Fixed:** the `ai-engineering-loop` skill now lands in the shared `~/.agents/skills/` folder, so Codex, Gemini CLI, and the other hosts that read it see the loop. Grok, Gemini CLI, and Codex installs trigger it.
44
+ - **Fixed:** Gemini CLI no longer gets Antigravity's `~/.gemini/config/skills/` path. Antigravity keeps `~/.gemini/config/skills/`, and its Devil's Advocate and Judge now install as `~/.gemini/config/agents/<name>.md` subagents (`subagent: true`) instead of `~/.agents/*.md`.
45
+ - **Changed:** one host-neutral `SKILL.md` (standard `name`/`description` frontmatter only) is generated for every host, byte-identical everywhere. Per-host spawn rules moved to `references/loop-hosts.md`. Grok no longer gets its own skill copies (it reads `~/.claude/skills` and `~/.agents/skills`), and the `user-invocable` overlay is gone (Grok's default is already `true`).
46
+ - **Removed:** `~/.agents/workflows/ai-engineering-loop.md`, `~/.agents/{devil-advocate,judge}.md`, and the `~/.claude/commands` and `~/.grok/commands` copies. The skill already provides `/ai-engineering-loop`. `sync-hosts` deletes these files where AEL wrote them, and keeps them if you edited them.
47
+ - **Note:** the Claude skill no longer pre-approves tools through `allowed-tools`, because other hosts (for example Copilot) treat that field as a permission grant. Claude Code may ask for permission a little more often.
48
+
49
+ ### `run --abandon` for stale runs (#46)
50
+
51
+ - **Added:** `run --abandon [--run <id>] --reason <text> --by <name> [--yes] [--json]`. It moves a run that will never finish to `CANCELLED`, records reason, actor, and time in the run's history ledger (recipe-bound runs also get a `RUN_CANCELLED` event), and releases `current.json` so `refresh --non-destructive` and `update auto` process the project again. Run data is kept. With `--run <id>` for a non-current run, the current pointer is left alone.
52
+ - ASSISTED runs ask for confirmation (or `--yes`). UNATTENDED runs are refused (exit 2) unless a human passes `--yes`. Finished runs and "no current run" exit 2. `--help` writes nothing, and unknown flags are rejected before any write.
53
+ - `status` (text and `--json` `activeRun`), `state`, and `projects list` point at `run --abandon` when the active run has not moved for 7 days or more. The "skipping refresh" message and the pending-projects update summary suggest it too.
54
+ - A pointer renamed by hand to `runs/current.stale-*.json` is simply ignored.
55
+
9
56
  ## 1.14.0 - 2026-10-10
10
57
 
11
58
  ### Auto-update and project registry (#37)
package/README.md CHANGED
@@ -89,6 +89,15 @@ npx ai-engineering-loop update rollback --yes
89
89
 
90
90
  Global installs apply patch and minor releases automatically. They then re-sync host skills and refresh every registered project, keeping your edits (new templates arrive as `*.ael-new`). Project installs only show a short notice (current -> latest, a few changelog highlights, the exact `npm`/`pnpm`/`yarn`/`bun` command, how to silence it), at most once a day per project, because AEL never edits your `package.json`. Projects from versions before hash tracking are overwritten on their first update, with the old files kept in `.ai-engineering-loop/.ael-backup/` and restored by `update rollback`. Major updates run `migrate --from <old>` after install. Opt out with `AEL_NO_AUTO_UPDATE=1`; CI is always off. There is no daemon, so other machines pick up an update the next time the CLI runs there.
91
91
 
92
+ Projects with an unfinished run are skipped until that run ends. If a run was simply left behind, close it (the run is kept, marked `CANCELLED`, and `current.json` is released):
93
+
94
+ ```bash
95
+ npx ai-engineering-loop run --abandon --reason "left behind after delivery" --by ega # asks to confirm; add --yes to skip
96
+ npx ai-engineering-loop run --abandon --run <run-id> --reason "superseded" --by ega --yes # a non-current run
97
+ ```
98
+
99
+ `status`, `state`, and `projects list` show this hint when an active run has not moved for 7 days. UNATTENDED runs need `--yes` from a human.
100
+
92
101
  When context packs exceed their budget, the CLI now reports the limit and a per-file size/token estimate so an agent can choose smaller files without trial and error. For a delivery gate blocked by a recipe approval node, inspect `node status --run <run-id>` and explicitly approve the READY prerequisite; the gate error points to the actionable command.
93
102
 
94
103
  ## Meet Workflow Studio
@@ -157,14 +166,51 @@ Under the hood, these moments use eight evidence-backed stages. The rigor is the
157
166
 
158
167
  AI Engineering Loop is designed to work with the tools developers already use:
159
168
 
160
- - **Claude Code**
161
- - **Grok CLI**
162
- - **Gemini / Antigravity**
163
- - Other agent hosts that can read project instructions and run local commands
169
+ <!-- hosts-table:start (generated from lib/hosts/registry.js; run npm run build:hosts-table) -->
170
+ | Host | id | Skill folder | Reviewer agents | Detected by |
171
+ |---|---|---|---|---|
172
+ | Claude Code | `claude` | `~/.claude/skills` | `~/.claude/agents` | `~/.claude`, `claude` |
173
+ | Codex CLI | `codex` | `~/.agents/skills` (shared) | `~/.codex/agents` | `~/.codex`, `codex` |
174
+ | Gemini CLI | `gemini` | `~/.agents/skills` (shared) | `~/.gemini/agents` | `~/.gemini`, `gemini` |
175
+ | Antigravity (IDE / 2.0) | `antigravity` | `~/.gemini/config/skills` | `~/.gemini/config/agents` | `~/.gemini/antigravity`, `antigravity` |
176
+ | Antigravity CLI (agy) | `antigravity-cli` | `~/.gemini/antigravity-cli/skills` | `~/.gemini/config/agents` | `~/.gemini/antigravity-cli`, `agy` |
177
+ | Grok CLI | `grok` | `~/.agents/skills` (shared) | `~/.grok/agents` | `~/.grok`, `grok` |
178
+ | Cursor (editor + CLI) | `cursor` | `~/.agents/skills` (shared) | `~/.cursor/agents` | `~/.cursor`, `cursor-agent`, `cursor` |
179
+ | GitHub Copilot (CLI / VS Code) | `copilot` | `~/.agents/skills` (shared) | `~/.copilot/agents` | `~/.copilot`, `copilot` |
180
+ | OpenCode | `opencode` | `~/.agents/skills` (shared) | `~/.config/opencode/agents` | `~/.config/opencode`, `opencode` |
181
+ | Windsurf / Devin Desktop | `windsurf` | `~/.agents/skills` (shared) | none (in-session review) | `~/.codeium/windsurf`, `~/.config/devin` |
182
+ | Amp | `amp` | `~/.agents/skills` (shared) | none (in-session review) | `~/.config/amp`, `amp` |
183
+ | Factory Droid | `factory` | `~/.agents/skills` (shared) | `~/.factory/droids` | `~/.factory`, `droid` |
184
+ | Augment (Auggie) | `augment` | `~/.agents/skills` (shared) | `~/.augment/agents` | `~/.augment`, `auggie` |
185
+ | Zed | `zed` | `~/.agents/skills` (shared) | none (in-session review) | `~/.config/zed`, `~/Library/Application Support/Zed`, `zed` |
186
+ | Goose | `goose` | `~/.agents/skills` (shared) | none (in-session review) | `~/.config/goose`, `goose` |
187
+ | Cline | `cline` | `~/.cline/skills` | none (in-session review) | `~/.cline`, `cline` |
188
+ | Roo Code | `roo` | `~/.agents/skills` (shared) | none (in-session review) | `~/.roo` |
189
+ | Kiro (IDE + CLI) | `kiro` | `~/.kiro/skills` | `~/.kiro/agents` | `~/.kiro`, `kiro-cli`, `kiro` |
190
+ | Qwen Code | `qwen` | `~/.qwen/skills` | `~/.qwen/agents` | `~/.qwen`, `qwen` |
191
+ | JetBrains Junie | `junie` | `~/.agents/skills` (shared) | `~/.junie/agents` | `~/.junie`, `junie` |
192
+
193
+ Not supported (no native skills): Aider, Continue.
194
+ <!-- hosts-table:end -->
195
+
196
+ Every host gets the **same** `ai-engineering-loop` skill (byte-identical, so an agent that scans several skill folders never sees two different versions). The few host-specific spawn rules live in its `references/loop-hosts.md`. Each host follows the same Goal, verification, review, and approval rules.
197
+
198
+ Install once, then let AEL find your agents:
199
+
200
+ ```bash
201
+ npm i -g ai-engineering-loop
202
+ ai-engineering-loop setup # detects agents (config folder or binary on PATH, never executed), asks, installs
203
+ ai-engineering-loop hosts list # what is detected / enabled, and where each host reads skills
204
+ ai-engineering-loop hosts doctor # per host: copies of the skill it sees, identical or not, files to sync
205
+ ai-engineering-loop hosts enable cursor copilot
206
+ ai-engineering-loop hosts disable codex # removes the files AEL wrote there (edited files are kept)
207
+ ```
208
+
209
+ There is no `postinstall` hook: npm 7+ hides its output, pnpm 10 and Bun block it, and `--ignore-scripts` skips it. Instead the first interactive command suggests `setup` (at most once a day; silence with `AEL_NO_SETUP_HINT=1`). `setup` without a terminal only prints the plan unless you pass `--yes`. Until you run `setup`, `sync-hosts` keeps the old behaviour: it writes only to hosts whose config folder already exists.
164
210
 
165
- The project includes ready-to-use skills and reviewer roles for supported hosts. Each host follows the same Goal, verification, review, and approval rules.
211
+ Agents you install later are noticed by `status` and the background `update auto` (stat only, cheap). With `auto` (the answer `setup` suggests when it asks; just press Enter), a global install enables and syncs them on its own; with `manual` (the default for `setup --yes` and any non-interactive run) you get one short notice per new agent, at most once a day. Nothing is written or shown in CI, in `--json` output, or with `AEL_NO_AUTO_UPDATE=1`.
166
212
 
167
- `sync-hosts` installs the **core** pack by default: the `ai-engineering-loop` skill, Devil's Advocate and Judge agents, commands, and the small helper skills the loop itself uses. Optional packs stay out of every session's skill index until you ask for them:
213
+ `sync-hosts` installs the **core** pack by default: the `ai-engineering-loop` skill, Devil's Advocate and Judge agents, and the small helper skills the loop itself uses. Optional packs stay out of every session's skill index until you ask for them:
168
214
 
169
215
  ```bash
170
216
  npx ai-engineering-loop sync-hosts --pack backend # framework-agnostic backend best practices
@@ -60,7 +60,7 @@ On a DOT repo (`adapter_type: dot`), **run `ai-engineering-loop`**, not the old
60
60
  | **`ai-engineering-loop`** | Engineering OS (Stages 0-7). Use this for DOT bugfix/feature/refactor. |
61
61
  | **`dot-dev-workflow`** | Stage 8 delivery only after Judge PASS. Not a parallel engineering loop. |
62
62
  | **`dot-dev-skill-router`** | Routes commit-bound DOT work to `ai-engineering-loop`, then Stage 8. |
63
- | **`task-impact-inquiry`** | Business blast radius (lifecycle sketch, four pillars, ASCII picture). Canonical: `adapters/dot/skills/task-impact-inquiry/`. Host copies: `~/.claude/skills/`, `~/.grok/skills/`, `~/.gemini/config/skills/`. Fills Stage 1 grill; impact-only stops after the matrix. Not a parallel OS. |
63
+ | **`task-impact-inquiry`** | Business blast radius (lifecycle sketch, four pillars, ASCII picture). Canonical: `adapters/dot/skills/task-impact-inquiry/`. Host copies: `~/.claude/skills/`, `~/.agents/skills/` (Codex, Gemini CLI, Grok, and other shared-folder hosts), `~/.gemini/config/skills/` (Antigravity). Fills Stage 1 grill; impact-only stops after the matrix. Not a parallel OS. |
64
64
  | **`backend-development`** | Framework-agnostic backend guidelines (clean naming, database queries, security, error handling). |
65
65
  | **`backend-safety-guardrails`** | 6 architectural backend safety invariants (queue bypass, BigInt, status recalculation loops). |
66
66
  | **`devils-advocate`** | Legacy DOT pre-commit skill. On AEL, Stages 6-7 are package Devil's Advocate + Judge. Do not re-run this skill after Judge PASS. |