ai-engineering-loop 2.4.0 → 2.6.0

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 (32) hide show
  1. package/.agents/skills/{ai-engineering-loop → ael}/SKILL.md +2 -2
  2. package/.agents/skills/ael/references/loop-verify.md +28 -0
  3. package/CHANGELOG.md +11 -0
  4. package/README.md +4 -4
  5. package/README.npm.md +6 -6
  6. package/adapters/dot/README.md +3 -3
  7. package/adapters/dot/skills/dot-dev-skill-router/SKILL.md +13 -13
  8. package/adapters/dot/skills/dot-dev-workflow/SKILL.md +3 -3
  9. package/adapters/generate-adapter/SKILL.md +1 -1
  10. package/adapters/generate-workflow/SKILL.md +1 -1
  11. package/adapters/quality/skills/task-impact-inquiry/SKILL.md +2 -2
  12. package/agents/instruction-only/AGENTS.md +1 -1
  13. package/bin/ai-engineering-loop.js +5 -5
  14. package/core/grill-policy.md +1 -1
  15. package/core/project-initialization.md +2 -2
  16. package/core/verification-loop.md +19 -7
  17. package/lib/bench.js +12 -12
  18. package/lib/claimed-vs-reality.js +9 -5
  19. package/lib/docs.js +1 -1
  20. package/lib/doctor.js +2 -2
  21. package/lib/host-skill-build.js +1 -1
  22. package/lib/hosts/doctor.js +6 -2
  23. package/lib/sync-hosts.js +3 -3
  24. package/package.json +3 -2
  25. package/.agents/skills/ai-engineering-loop/references/loop-verify.md +0 -20
  26. /package/.agents/skills/{ai-engineering-loop → ael}/references/loop-commands.md +0 -0
  27. /package/.agents/skills/{ai-engineering-loop → ael}/references/loop-deliver.md +0 -0
  28. /package/.agents/skills/{ai-engineering-loop → ael}/references/loop-goal.md +0 -0
  29. /package/.agents/skills/{ai-engineering-loop → ael}/references/loop-hosts.md +0 -0
  30. /package/.agents/skills/{ai-engineering-loop → ael}/references/loop-maker.md +0 -0
  31. /package/.agents/skills/{ai-engineering-loop → ael}/references/loop-review.md +0 -0
  32. /package/.agents/skills/{ai-engineering-loop → ael}/references/loop-risky.md +0 -0
@@ -1,6 +1,6 @@
1
1
  ---
2
- name: ai-engineering-loop
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.
2
+ name: ael
3
+ description: Use when the user runs /ael, 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
 
@@ -0,0 +1,28 @@
1
+ # Stage 5: Verification
2
+
3
+ - `npx ai-engineering-loop verify --run <runId> [--cmd "<command>"]...` (default `test_unit` from verification.md) runs commands in parallel (`--serial`, `--shell`), binds redacted evidence to the gated diff, and on pass compacts and scaffolds claimed-vs-reality.
4
+ - Iterating (T1/T2): `verify --related` runs `test_related` on changed files. After Judge PASS, `verify --final` runs the full suite once before delivery. Unchanged diff reuses passes (`--fresh` re-runs).
5
+ - Failed commands return non-zero and block the gate. Vague "seems green" is invalid.
6
+ - Fill `.ai-engineering-loop/tasks/claimed-vs-reality.md`: Claimed from change, Reality from command output, optional Layer (`L1`, `L2`, `L3`). Multi-component ACs need L3 evidence or justification if `e2e` is unconfigured. Never spawn DA if file is missing or any row lacks Reality.
7
+ - Hand-authored artifacts: `scaffold verification|findings|delivery --run <runId>`, fill, remove `_templateOnly`, then `validate <file>`.
8
+ - Pass run-summary.md and verification-summary.json to reviewers instead of raw logs.
9
+
10
+ ## Verification Layers & Command Mapping
11
+
12
+ | Layer | Scope | Command (`verification.md`) | Focus |
13
+ |---|---|---|---|
14
+ | **L1** | Static | `typecheck`, `lint`, `build` | Types, lint, build |
15
+ | **L2** | Runtime | `test_unit`, `test_related`, `test_all` | Unit and regression tests |
16
+ | **L3** | End-to-End | `e2e` (optional) | Integrated boundary proof |
17
+
18
+ ## No claim without fresh evidence
19
+
20
+ Before claiming "done", "fixed", "passing", or "ready", run the proving command this iteration; earlier runs and "should work" are not evidence.
21
+
22
+ | Claim | Required evidence |
23
+ |---|---|
24
+ | Tests pass | test output this iteration, exit 0 |
25
+ | Bug fixed | passing red repro, command shown |
26
+ | AC met | claimed-vs-reality cites output |
27
+
28
+ After `verify`, continue from run-summary.md and verification-summary.json.
package/CHANGELOG.md CHANGED
@@ -6,6 +6,17 @@ All notable changes to this project are documented here. Versions follow [Semant
6
6
 
7
7
  _No changes yet._
8
8
 
9
+ ## 2.6.0 - 2026-11-10
10
+
11
+ - **Added:** three-layer verification naming in `loop-verify` (#110): L1 unit, L2 related/integration, L3 end-to-end through the existing optional `e2e` verification key, with a manual flow check plus written evidence when `e2e` is not configured. T0 needs L1-L2, T1 adds L3 when an AC crosses component boundaries, T2 always needs L1-L3.
12
+ - **Added:** `context claimed-vs-reality` scaffolds a 4-column table (`AC | Claimed | Reality from command log | Layer`). Existing 3-column files stay valid for `readyForDa`; empty or "seems green" Reality still fails.
13
+ - **Fixed:** the measure script counts characters the same on Windows (CRLF) as on macOS and Linux.
14
+
15
+ ## 2.5.0 - 2026-11-02
16
+
17
+ - **Changed:** the core host skill is now `ael` (#107), so the slash command is `/ael` on every host (`~/.claude/skills/ael`, `~/.agents/skills/ael`, and each host's own folder). `sync-hosts` and `update` remove the old `ai-engineering-loop` skill files AEL wrote, so the command no longer appears twice; files you edited or added there are kept, and `hosts doctor` reports the leftover folder. Skill sources moved to `skill-src/ael/`.
18
+ - **Added:** `ael` CLI alias next to `ai-engineering-loop` (`ael --version`). The npm package name and the project folder `.ai-engineering-loop/` are unchanged.
19
+
9
20
  ## 2.4.0 - 2026-11-02
10
21
 
11
22
  ### Spec pack: design before code (EGM fork)
package/README.md CHANGED
@@ -75,7 +75,7 @@ npx ai-engineering-loop deliver --run <run-id> --destination pr --summary "..."
75
75
 
76
76
  `deliver` refuses without `--approve` in ASSISTED mode; pass it only after a human approved delivery.
77
77
 
78
- Contributors: the host `ai-engineering-loop` skills are generated. Edit `skill-src/ai-engineering-loop/`, then run `npm run build:skills` (CI checks for drift with `npm run check:skills`). `npm run measure` reports per-tier context and tool calls.
78
+ Contributors: the host `ael` skills are generated. Edit `skill-src/ael/`, then run `npm run build:skills` (CI checks for drift with `npm run check:skills`). `npm run measure` reports per-tier context and tool calls.
79
79
 
80
80
  ### Staying up to date
81
81
 
@@ -183,12 +183,12 @@ Guardrails: **enforced** = `npx ai-engineering-loop hooks install` adds native p
183
183
  Not supported (no native skills): Aider, Continue.
184
184
  <!-- hosts-table:end -->
185
185
 
186
- 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.
186
+ Every host gets the **same** `ael` skill, invoked as `/ael` (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`. Earlier releases named the skill `ai-engineering-loop`; `sync-hosts` removes that old folder when AEL wrote it and `hosts doctor` flags any copy it had to keep. Each host follows the same Goal, verification, review, and approval rules.
187
187
 
188
188
  Install once, then let AEL find your agents:
189
189
 
190
190
  ```bash
191
- npm i -g ai-engineering-loop
191
+ npm i -g ai-engineering-loop # installs the `ai-engineering-loop` and short `ael` commands
192
192
  ai-engineering-loop setup # detects agents (config folder or binary on PATH, never executed), asks, installs
193
193
  ai-engineering-loop hosts list # what is detected / enabled, and where each host reads skills
194
194
  ai-engineering-loop hosts doctor # per host: copies of the skill it sees, identical or not, files to sync
@@ -200,7 +200,7 @@ There is no `postinstall` hook: npm 7+ hides its output, pnpm 10 and Bun block i
200
200
 
201
201
  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`.
202
202
 
203
- `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:
203
+ `sync-hosts` installs the **core** pack by default: the `ael` 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:
204
204
 
205
205
  ```bash
206
206
  npx ai-engineering-loop sync-hosts --pack backend # framework-agnostic backend best practices
package/README.npm.md CHANGED
@@ -72,11 +72,11 @@ npx ai-engineering-loop docs grill-policy --section "When to grill"
72
72
 
73
73
  ## Grok CLI
74
74
 
75
- Inside a Grok TUI session, `/ai-engineering-loop` uses repo-local `.grok/agents/` types. Devil's Advocate and Judge spawn as sibling children (`capability_mode: execute`, no `resume_from`). Do not use `caveman:cavecrew-reviewer` as the loop reviewer.
75
+ Inside a Grok TUI session, `/ael` uses repo-local `.grok/agents/` types. Devil's Advocate and Judge spawn as sibling children (`capability_mode: execute`, no `resume_from`). Do not use `caveman:cavecrew-reviewer` as the loop reviewer.
76
76
 
77
77
  ## Claude Code
78
78
 
79
- Inside Claude Code, `/ai-engineering-loop` uses `.claude/agents/` types via the **Task** tool. Pass only `subagent_type`, `description`, and `prompt`. Do not pass Grok keys (`spawn_subagent`, `capability_mode`, `resume_from`) — extra keys cause Kiro `REQUEST_BODY_INVALID`.
79
+ Inside Claude Code, `/ael` uses `.claude/agents/` types via the **Task** tool. Pass only `subagent_type`, `description`, and `prompt`. Do not pass Grok keys (`spawn_subagent`, `capability_mode`, `resume_from`) — extra keys cause Kiro `REQUEST_BODY_INVALID`.
80
80
 
81
81
  ---
82
82
 
@@ -84,10 +84,10 @@ Inside Claude Code, `/ai-engineering-loop` uses `.claude/agents/` types via the
84
84
 
85
85
  In Antigravity IDE or compatible agentic platforms, invoke the loop directly in chat:
86
86
 
87
- - `/ai-engineering-loop init` — Bootstrap project context only.
88
- - `/ai-engineering-loop status` — Check context health and living freshness.
89
- - `/ai-engineering-loop refresh` — Reconcile drifted context files.
90
- - `/ai-engineering-loop <task>` — Execute the full 8-stage engineering lifecycle.
87
+ - `/ael init` — Bootstrap project context only.
88
+ - `/ael status` — Check context health and living freshness.
89
+ - `/ael refresh` — Reconcile drifted context files.
90
+ - `/ael <task>` — Execute the full 8-stage engineering lifecycle.
91
91
 
92
92
  ---
93
93
 
@@ -63,13 +63,13 @@ The DOT adapter is organized into five specification modules:
63
63
 
64
64
  This adapter composes the DOT skill suite. `task-impact-inquiry` is adapter-neutral and ships in `adapters/quality/skills/task-impact-inquiry/`; `sync-hosts` upserts it to every enabled host. On DOT repos it is mandatory in Stage 1. Other DOT skills (router, workflow) still update-if-exists only.
65
65
 
66
- On a DOT repo (`adapter_type: dot`), **run `ai-engineering-loop`**, not the old 9-phase `dot-dev-workflow`, as the engineering OS. Stage 1 grill **includes** `task-impact-inquiry`. Do not run a second interview. After Judge `PASS`, Stage 8 is `dot-dev-workflow` delivery (GitLab, cherry-pick, Coreview, Mattermost). Canonical DOT copies: `adapters/dot/skills/` (`task-impact-inquiry`: `adapters/quality/skills/`). See `core/grill-policy.md`.
66
+ On a DOT repo (`adapter_type: dot`), **run `ael`**, not the old 9-phase `dot-dev-workflow`, as the engineering OS. Stage 1 grill **includes** `task-impact-inquiry`. Do not run a second interview. After Judge `PASS`, Stage 8 is `dot-dev-workflow` delivery (GitLab, cherry-pick, Coreview, Mattermost). Canonical DOT copies: `adapters/dot/skills/` (`task-impact-inquiry`: `adapters/quality/skills/`). See `core/grill-policy.md`.
67
67
 
68
68
  | Skill | Primary Role & Governance |
69
69
  | :--- | :--- |
70
- | **`ai-engineering-loop`** | Engineering OS (Stages 0-7). Use this for DOT bugfix/feature/refactor. |
70
+ | **`ael`** | Engineering OS (Stages 0-7). Use this for DOT bugfix/feature/refactor. |
71
71
  | **`dot-dev-workflow`** | Stage 8 delivery only after Judge PASS. Not a parallel engineering loop. |
72
- | **`dot-dev-skill-router`** | Routes commit-bound DOT work to `ai-engineering-loop`, then Stage 8. |
72
+ | **`dot-dev-skill-router`** | Routes commit-bound DOT work to `ael`, then Stage 8. |
73
73
  | **`task-impact-inquiry`** | Business blast radius (lifecycle sketch, four pillars, ASCII picture). Canonical: `adapters/quality/skills/task-impact-inquiry/` (adapter-neutral, EN + ID triggers). 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. |
74
74
  | **`backend-development`** | Framework-agnostic backend guidelines (clean naming, database queries, security, error handling). |
75
75
  | **`backend-safety-guardrails`** | 6 architectural backend safety invariants (queue bypass, BigInt, status recalculation loops). |
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: dot-dev-skill-router
3
- description: Route DOT tasks. Commit-bound bugfix, feature, or refactor uses ai-engineering-loop for Stages 0-7, then dot-dev-workflow for Stage 8 delivery. Do not use dot-dev-workflow as a parallel engineering OS.
3
+ description: Route DOT tasks. Commit-bound bugfix, feature, or refactor uses ael for Stages 0-7, then dot-dev-workflow for Stage 8 delivery. Do not use dot-dev-workflow as a parallel engineering OS.
4
4
  ---
5
5
 
6
6
  # DOT Development Skill Router
@@ -10,17 +10,17 @@ Pick the smallest relevant skill. Do not load every skill. **AI Engineering Loop
10
10
  ## Core rules
11
11
 
12
12
  1. Read repository instructions and inspect the affected code before choosing a workflow.
13
- 2. For DOT work that will be committed or opened as an MR, load `ai-engineering-loop`. Stage 1 grill includes `task-impact-inquiry` (four pillars). Stages 6-7 are AEL Devil's Advocate and Judge. Do not run the old 9-phase `dot-dev-workflow` as a second loop. Do not run `task-impact-inquiry` as a second interview after grill.
13
+ 2. For DOT work that will be committed or opened as an MR, load `ael`. Stage 1 grill includes `task-impact-inquiry` (four pillars). Stages 6-7 are AEL Devil's Advocate and Judge. Do not run the old 9-phase `dot-dev-workflow` as a second loop. Do not run `task-impact-inquiry` as a second interview after grill.
14
14
  3. After Judge `PASS`, load `dot-dev-workflow` for Stage 8 delivery only.
15
15
  4. Use `ponytail` (optional, if installed) when the smallest correct solution matters.
16
16
  5. Use `verification-before-completion` (dot-plugin; older installs call it `dot-verification`) before claiming a change is fixed, complete, passing, or ready.
17
17
  6. Commits, push, GitLab issue/MR, Mattermost, deploys, database mutation, and deletion are explicit user-requested side effects. `auto-mr-issue` (optional, if installed) is never automatic.
18
18
  7. Do not invent APIs, test results, design tokens, or behavior. Report blockers as blockers.
19
- 8. If a named skill is not installed, say so and continue with `ai-engineering-loop`; never guess a substitute name.
19
+ 8. If a named skill is not installed, say so and continue with `ael`; never guess a substitute name.
20
20
 
21
21
  ## Skill sources
22
22
 
23
- - **AEL (this package):** `ai-engineering-loop`, `task-impact-inquiry`, `dot-dev-workflow`, `backend-development`.
23
+ - **AEL (this package):** `ael`, `task-impact-inquiry`, `dot-dev-workflow`, `backend-development`.
24
24
  - **dot-plugin:** `verification-before-completion`, `design-openapi-contract`, `design-dbml-database`, `generate-api-test`, `generate-ui-e2e-test`, `generate-module-fsd`, `merge-request`, `gitlab-mr-feedback`, `receiving-code-review`, `fetch-gitlab-issue`, `sonarqube-issues`, `sentry-issues`.
25
25
  - **Optional, if installed:** `ponytail`, `auto-mr-issue`, `product-contract-analysis`, `fig-to-tailwind-extractor`, `figma-token-extractor`, `frontend-design`, `design-taste-frontend`, `ui-ux-pro-max`, `web-design-guidelines`, `webapp-testing`, `backend-safety-guardrails`, `creative-ideation`.
26
26
 
@@ -28,20 +28,20 @@ Pick the smallest relevant skill. Do not load every skill. **AI Engineering Loop
28
28
 
29
29
  | Task | Load in order |
30
30
  |---|---|
31
- | DOT bugfix / feature / refactor that will be committed or opened as MR | `ai-engineering-loop` (grill includes `task-impact-inquiry`; DA + Judge before commit) → `dot-dev-workflow` Stage 8 after Judge PASS |
31
+ | DOT bugfix / feature / refactor that will be committed or opened as MR | `ael` (grill includes `task-impact-inquiry`; DA + Judge before commit) → `dot-dev-workflow` Stage 8 after Judge PASS |
32
32
  | Impact / blast-radius question only (no implementation) | `task-impact-inquiry` |
33
- | New feature, product/UI behavior unclear | `ai-engineering-loop` Stage 1 grill and Goal Contract; add `product-contract-analysis` (optional, if installed) for product questions. Do not run a separate brainstorming loop |
33
+ | New feature, product/UI behavior unclear | `ael` Stage 1 grill and Goal Contract; add `product-contract-analysis` (optional, if installed) for product questions. Do not run a separate brainstorming loop |
34
34
  | Legacy FE + BE module documentation | `generate-module-fsd` |
35
35
  | Raw `.fig` file to standalone HTML + Tailwind | `fig-to-tailwind-extractor`; add `figma-token-extractor` for token/visual-contract audit (both optional, if installed) |
36
36
  | New landing page or visual redesign | `frontend-design` + `design-taste-frontend`; add `ui-ux-pro-max` only for a targeted UI decision (optional, if installed) |
37
37
  | UI/accessibility/design review | `web-design-guidelines`; add `ui-ux-pro-max` for focused UX, stack, typography, or interaction guidance (optional, if installed) |
38
- | DOT API contract or OpenAPI change | `ai-engineering-loop` → `design-openapi-contract` → `verification-before-completion` |
39
- | DOT database schema (DBML) change | `ai-engineering-loop` → `design-dbml-database` → `verification-before-completion` |
40
- | DOT backend behavior/API regression coverage | `ai-engineering-loop` → `generate-api-test` → `verification-before-completion` |
41
- | Backend architecture, clean code, naming, or query optimization | `ai-engineering-loop` → `backend-development` (during Maker) → `verification-before-completion` |
42
- | Backend action, queue, worker, or entity status recalculation | `ai-engineering-loop` → `backend-development` + `backend-safety-guardrails` (optional, if installed) during Maker → `verification-before-completion` |
38
+ | DOT API contract or OpenAPI change | `ael` → `design-openapi-contract` → `verification-before-completion` |
39
+ | DOT database schema (DBML) change | `ael` → `design-dbml-database` → `verification-before-completion` |
40
+ | DOT backend behavior/API regression coverage | `ael` → `generate-api-test` → `verification-before-completion` |
41
+ | Backend architecture, clean code, naming, or query optimization | `ael` → `backend-development` (during Maker) → `verification-before-completion` |
42
+ | Backend action, queue, worker, or entity status recalculation | `ael` → `backend-development` + `backend-safety-guardrails` (optional, if installed) during Maker → `verification-before-completion` |
43
43
  | Local web app repro, browser smoke, or UI regression | `webapp-testing` (optional, if installed) → `verification-before-completion` |
44
- | Executing an existing written plan | `ai-engineering-loop` (paste the plan as the Goal Contract draft). Do not load `executing-plans` as a second loop |
44
+ | Executing an existing written plan | `ael` (paste the plan as the Goal Contract draft). Do not load `executing-plans` as a second loop |
45
45
  | Pre-merge review after AEL already ran | AEL Judge verdict is the gate. Do not re-run a separate devil's-advocate skill unless Judge was skipped |
46
46
  | Code review feedback reception | `receiving-code-review` |
47
47
  | GitLab MR discussions / feedback resolution | `gitlab-mr-feedback` → `receiving-code-review` |
@@ -57,7 +57,7 @@ Pick the smallest relevant skill. Do not load every skill. **AI Engineering Loop
57
57
 
58
58
  ## Avoid
59
59
 
60
- - Do not run `dot-dev-workflow` Phases 1-6 when `ai-engineering-loop` is available.
60
+ - Do not run `dot-dev-workflow` Phases 1-6 when `ael` is available.
61
61
  - Do not chain `task-impact-inquiry` then a full second engineering loop.
62
62
  - Do not invoke `auto-mr-issue` merely because code was committed.
63
63
  - Do not use the full delivery pipeline for a tiny local question unless the user asked to ship.
@@ -1,18 +1,18 @@
1
1
  ---
2
2
  name: dot-dev-workflow
3
- description: DOT Stage 8 delivery after AI Engineering Loop Judge PASS. GitLab issue/MR, one topic-branch MR (extra env cherry-pick only if named this turn), pipeline + Sonar gate, Coreview triage, card to Ready to review, Mattermost. Not a substitute for ai-engineering-loop.
3
+ description: DOT Stage 8 delivery after AI Engineering Loop Judge PASS. GitLab issue/MR, one topic-branch MR (extra env cherry-pick only if named this turn), pipeline + Sonar gate, Coreview triage, card to Ready to review, Mattermost. Not a substitute for ael.
4
4
  ---
5
5
 
6
6
  # DOT Delivery Workflow (Stage 8)
7
7
 
8
8
  This is **not** the engineering OS. On DOT repositories:
9
9
 
10
- 1. Run **`ai-engineering-loop`** for Stages 0-7 (grill, RCA, Maker, verification, Devil's Advocate, Judge).
10
+ 1. Run **`ael`** for Stages 0-7 (grill, RCA, Maker, verification, Devil's Advocate, Judge).
11
11
  2. Run **this skill only after Judge `PASS`** (or the user explicitly asked to ship).
12
12
  3. Stage 1 grill already includes `task-impact-inquiry`. Do not interview again.
13
13
  4. Stages 6-7 are AEL DA + Judge. Do not re-run skill `devils-advocate` as a second pre-commit OS.
14
14
 
15
- If `ai-engineering-loop` is missing on this host, say so and stop. Do not silently run the old 9-phase loop.
15
+ If `ael` is missing on this host, say so and stop. Do not silently run the old 9-phase loop.
16
16
 
17
17
  ## Mapping (old phases → AEL)
18
18
 
@@ -112,7 +112,7 @@ Generate adapter
112
112
  Detected: <remote> <ci>
113
113
  Questions: Q1..Q5 with Recommended
114
114
  Wrote: .ai-engineering-loop/adapter.md (type=<type>)
115
- Next: /ai-engineering-loop for product work. Stage 8 uses this file.
115
+ Next: /ael for product work. Stage 8 uses this file.
116
116
  ```
117
117
 
118
118
  ## Forbidden
@@ -126,7 +126,7 @@ Existing: <workflow yes/no> <lessons yes/no>
126
126
  Questions: Q1..Q6 with Recommended
127
127
  Wrote: .ai-engineering-loop/workflow.md
128
128
  Lessons: .ai-engineering-loop/lessons.md (created or left)
129
- Next: /ai-engineering-loop for product work. Stage 0 reads these files.
129
+ Next: /ael for product work. Stage 0 reads these files.
130
130
  ```
131
131
 
132
132
  ## Forbidden
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: task-impact-inquiry
3
- description: Map business blast radius before code. Use for impact, side effects, sibling data, approval, queues, or when a new developer must learn the current flow. Triggers (EN/ID): check the impact, impact analysis, blast radius, side effects, cek impactnya, analisa pengaruh. Not a substitute for ai-engineering-loop.
3
+ description: Map business blast radius before code. Use for impact, side effects, sibling data, approval, queues, or when a new developer must learn the current flow. Triggers (EN/ID): check the impact, impact analysis, blast radius, side effects, cek impactnya, analisa pengaruh. Not a substitute for ael.
4
4
  ---
5
5
 
6
6
  # Task Impact Inquiry
@@ -9,7 +9,7 @@ Map the **current business flow** and the **blast radius** of a change before an
9
9
 
10
10
  This skill fills AI Engineering Loop Stage 1 grill. It is not a parallel engineering OS.
11
11
 
12
- If Stage 1 grill already produced this matrix and the user confirmed it, stop. Do not interview again. On commit-bound work, continue in `ai-engineering-loop` (freeze the Goal Contract, then Maker). Do not start a second engineering loop from your team's own workflow skill.
12
+ If Stage 1 grill already produced this matrix and the user confirmed it, stop. Do not interview again. On commit-bound work, continue in `ael` (freeze the Goal Contract, then Maker). Do not start a second engineering loop from your team's own workflow skill.
13
13
 
14
14
  Works on any adapter. On `adapter_type: dot` it is mandatory in Stage 1; the DOT-only rules live in `adapters/dot/README.md`.
15
15
 
@@ -1,7 +1,7 @@
1
1
  <!-- Generated from skill-src/ by npm run build:skills; do not edit. -->
2
2
  # AI Engineering Loop (digest)
3
3
 
4
- For hosts with no subagent tool (certification `instruction-only`). Full skill: `~/.agents/skills/ai-engineering-loop/SKILL.md` after `sync-hosts`. Stage details: `npx ai-engineering-loop docs loop-<goal|maker|verify|review|deliver>`.
4
+ For hosts with no subagent tool (certification `instruction-only`). Full skill: `~/.agents/skills/ael/SKILL.md` after `sync-hosts`. Stage details: `npx ai-engineering-loop docs loop-<goal|maker|verify|review|deliver>`.
5
5
 
6
6
  Loop: Specify (0-1), Make (2-4), Review (5-7), Deliver (8). You are Maker. Devil's Advocate (DA) and Judge run in this session as `CONTEXT_ISOLATION_ONLY`, with the same budgets; never claim independent review.
7
7
 
@@ -1548,10 +1548,10 @@ function handleRun() {
1548
1548
  } else {
1549
1549
  console.log(`- Fallback: CONTEXT_ISOLATION_ONLY (${grok.reason})`);
1550
1550
  }
1551
- console.log('- Skill: .agents/skills/ai-engineering-loop/SKILL.md (spawn rules: references/loop-hosts.md, Grok CLI section)');
1551
+ console.log('- Skill: .agents/skills/ael/SKILL.md (spawn rules: references/loop-hosts.md, Grok CLI section)');
1552
1552
  }
1553
1553
 
1554
- const claudeSkill = path.join(CWD, '.claude', 'skills', 'ai-engineering-loop', 'SKILL.md');
1554
+ const claudeSkill = path.join(CWD, '.claude', 'skills', 'ael', 'SKILL.md');
1555
1555
  const claudeAgent = path.join(CWD, '.claude', 'agents', 'devil-advocate.md');
1556
1556
  if (fs.existsSync(claudeSkill) || fs.existsSync(claudeAgent)) {
1557
1557
  console.log('------------------------------------------------------------');
@@ -1560,17 +1560,17 @@ function handleRun() {
1560
1560
  console.log('- Devil\'s Advocate: Task subagent_type=devil-advocate');
1561
1561
  console.log('- Judge: Task subagent_type=judge (sibling, not nested)');
1562
1562
  console.log('- Do not pass spawn_subagent, capability_mode, isolation, resume_from (Kiro 400 REQUEST_BODY_INVALID)');
1563
- console.log('- Skill: .claude/skills/ai-engineering-loop/SKILL.md');
1563
+ console.log('- Skill: .claude/skills/ael/SKILL.md');
1564
1564
  }
1565
1565
 
1566
- const sharedSkill = path.join(CWD, '.agents', 'skills', 'ai-engineering-loop', 'SKILL.md');
1566
+ const sharedSkill = path.join(CWD, '.agents', 'skills', 'ael', 'SKILL.md');
1567
1567
  if (fs.existsSync(sharedSkill)) {
1568
1568
  console.log('------------------------------------------------------------');
1569
1569
  log.bold('Shared .agents/skills hosts (Codex, Gemini CLI, Antigravity, Cursor, Copilot, ...):');
1570
1570
  console.log('- Same skill on every host; spawn rules per host: references/loop-hosts.md');
1571
1571
  console.log('- Devil\'s Advocate: 8 tool calls, diff file, skip css');
1572
1572
  console.log('- Judge: 4 tool calls, ledger + contract only');
1573
- console.log('- Skill: .agents/skills/ai-engineering-loop/SKILL.md');
1573
+ console.log('- Skill: .agents/skills/ael/SKILL.md');
1574
1574
  }
1575
1575
  console.log('------------------------------------------------------------\n');
1576
1576
  }
@@ -30,7 +30,7 @@ If the user asks for ideas, a feature catalog, or "what should we add" without n
30
30
  3. List at most five options. Mark one recommended. Wait for a pick.
31
31
  4. After they pick, grill that one task, then freeze.
32
32
 
33
- `/ai-engineering-loop` on an idea request still stays this loop: menu, then grill. Do not switch to a parallel brainstorm product.
33
+ `/ael` on an idea request still stays this loop: menu, then grill. Do not switch to a parallel brainstorm product.
34
34
 
35
35
  ## Freeze gate
36
36
 
@@ -33,7 +33,7 @@ flowchart TD
33
33
 
34
34
  ### The `init` Operation
35
35
  - **Purpose**: Discovers repository characteristics, extracts manifest scripts, binds archetype profiles, and generates `.ai-engineering-loop/`.
36
- - **Command**: `npx ai-engineering-loop init` (or `/ai-engineering-loop init`).
36
+ - **Command**: `npx ai-engineering-loop init` (or `/ael init`).
37
37
  - **Boundaries**:
38
38
  - `init` **MUST NOT** edit application code, write business logic, author unit tests, or run adversarial reviews.
39
39
  - `init` **MUST NOT** commit to git, change branches, push to remotes, or open PRs.
@@ -44,7 +44,7 @@ flowchart TD
44
44
 
45
45
  ### The `run` Operation
46
46
  - **Purpose**: Consumes the ground truth in `.ai-engineering-loop/` to solve a specific user task.
47
- - **Command**: `npx ai-engineering-loop run` (or `/ai-engineering-loop [task]`).
47
+ - **Command**: `npx ai-engineering-loop run` (or `/ael [task]`).
48
48
  - **Boundaries**:
49
49
  - The Agent reads `.ai-engineering-loop/` (triggering auto-init if missing).
50
50
  - Formulates the [Goal Contract](./goal-contract.md).
@@ -43,9 +43,21 @@ A verification `PASS` is **strictly invalid** without concrete execution evidenc
43
43
  }
44
44
  ```
45
45
 
46
+ ## 3. Verification Layers & Command Mapping
47
+
48
+ Verification terminates through three explicit layers of evidence. Unit tests alone have systematic blind spots for cross-component and integration defects. An acceptance criterion crossing component boundaries requires Layer 3 verification or written justification if Layer 3 is unavailable.
49
+
50
+ | Layer | Scope | Configured Command (`verification.md`) | Purpose |
51
+ |---|---|---|---|
52
+ | **L1: Static / Syntax** | Syntax, static types, style, compilation | `typecheck`, `lint`, `build` | Fast static catch before runtime. Rejects type errors, lint regressions, and compilation breakage. |
53
+ | **L2: Behavioral / Runtime** | Functions, units, modules, regressions | `test_unit`, `test_related`, `test_all` | Fast behavioral feedback at named seams and regression verification. |
54
+ | **L3: End-to-End** | Cross-component flows, integrations, browser/API | `e2e` (optional) | Realistic integrated proof across boundary seams. |
55
+
56
+ When `e2e` is configured in `verification.md`, cross-component acceptance criteria must cite L3 command evidence. If `e2e` is empty, Maker must document in Reality why L3 is not configured.
57
+
46
58
  ---
47
59
 
48
- ## 3. The 4 Verification Gates
60
+ ## 4. The 4 Verification Gates
49
61
 
50
62
  1. **Gate 1: Unit & Integration Tests**: All unit and edge-case tests must pass with 0 failures.
51
63
  2. **Gate 2: Static Type Analysis**: `tsc --noEmit` or compiler type checking must exit with code `0` (zero type errors).
@@ -54,7 +66,7 @@ A verification `PASS` is **strictly invalid** without concrete execution evidenc
54
66
 
55
67
  ---
56
68
 
57
- ## 4. Rejection Triggers
69
+ ## 5. Rejection Triggers
58
70
 
59
71
  The Verification Gate immediately halts and returns to the Maker if:
60
72
  - Any test suite fails or times out.
@@ -66,7 +78,7 @@ The Verification Gate immediately halts and returns to the Maker if:
66
78
 
67
79
  ---
68
80
 
69
- ## 5. Claimed vs Reality (before Devil's Advocate)
81
+ ## 6. Claimed vs Reality (before Devil's Advocate)
70
82
 
71
83
  Write `.ai-engineering-loop/tasks/claimed-vs-reality.md` after verification logs exist:
72
84
 
@@ -74,14 +86,14 @@ Write `.ai-engineering-loop/tasks/claimed-vs-reality.md` after verification logs
74
86
  npx ai-engineering-loop context claimed-vs-reality --run <run-id>
75
87
  ```
76
88
 
77
- This scaffolds one row per frozen acceptance criterion but leaves Claimed and Reality empty. Fill them from the implemented change and actual command output; the scaffold is not verification evidence.
89
+ This scaffolds one row per frozen acceptance criterion but leaves Claimed, Reality, and Layer empty. Fill them from the implemented change and actual command output; the scaffold is not verification evidence.
78
90
 
79
91
  ```markdown
80
92
  # Claimed vs Reality
81
93
 
82
- | AC | Claimed | Reality |
83
- |---|---|---|
84
- | AC-1 | <what Maker said is done> | <command, exit code, assertion or log line> |
94
+ | AC | Claimed | Reality from command log | Layer |
95
+ |---|---|---|---|
96
+ | AC-1 | <what Maker said is done> | <command, exit code, assertion or log line> | L2 |
85
97
  ```
86
98
 
87
99
  Do **not** spawn Devil's Advocate if:
package/lib/bench.js CHANGED
@@ -41,7 +41,7 @@ const DEFAULT_BENCH_TIMEOUT_MS = 20 * 60 * 1000;
41
41
  const INSTRUCTION_CATALOG = Object.freeze([
42
42
  {
43
43
  type: 'skipped-gate',
44
- skill: 'skill-src/ai-engineering-loop/SKILL.template.md',
44
+ skill: 'skill-src/ael/SKILL.template.md',
45
45
  heading: 'Loop',
46
46
  instruction: 'Do not skip Goal Contract, verification, Devil\'s Advocate, or Judge gates; the tier only decides who fills them.',
47
47
  hardening: {
@@ -51,7 +51,7 @@ const INSTRUCTION_CATALOG = Object.freeze([
51
51
  },
52
52
  {
53
53
  type: 'out-of-order-gate',
54
- skill: 'skill-src/ai-engineering-loop/SKILL.template.md',
54
+ skill: 'skill-src/ael/SKILL.template.md',
55
55
  heading: 'Loop',
56
56
  instruction: 'Gate failures override prose.',
57
57
  hardening: {
@@ -61,7 +61,7 @@ const INSTRUCTION_CATALOG = Object.freeze([
61
61
  },
62
62
  {
63
63
  type: 'forged-gate',
64
- skill: 'skill-src/ai-engineering-loop/SKILL.template.md',
64
+ skill: 'skill-src/ael/SKILL.template.md',
65
65
  heading: 'Loop',
66
66
  instruction: 'Never edit `state.json`/`current.json`.',
67
67
  hardening: {
@@ -71,7 +71,7 @@ const INSTRUCTION_CATALOG = Object.freeze([
71
71
  },
72
72
  {
73
73
  type: 'skipped-claimed-vs-reality',
74
- skill: 'skill-src/ai-engineering-loop/SKILL.template.md',
74
+ skill: 'skill-src/ael/SKILL.template.md',
75
75
  heading: 'Invariants (every tier)',
76
76
  instruction: 'Write claimed-vs-reality.md after `gate verification` passes. Do not spawn Devil\'s Advocate if the file is missing or any Claimed row lacks Reality.',
77
77
  hardening: {
@@ -81,7 +81,7 @@ const INSTRUCTION_CATALOG = Object.freeze([
81
81
  },
82
82
  {
83
83
  type: 'edit-before-freeze',
84
- skill: 'skill-src/ai-engineering-loop/references/loop-goal.md',
84
+ skill: 'skill-src/ael/references/loop-goal.md',
85
85
  heading: 'Stage 1: Goal Contract',
86
86
  instruction: 'Do not edit production code until the Goal gate passes.',
87
87
  hardening: {
@@ -91,7 +91,7 @@ const INSTRUCTION_CATALOG = Object.freeze([
91
91
  },
92
92
  {
93
93
  type: 'guard-violation',
94
- skill: 'skill-src/ai-engineering-loop/references/loop-maker.md',
94
+ skill: 'skill-src/ael/references/loop-maker.md',
95
95
  heading: 'Stages 2-4: Maker',
96
96
  instruction: 'before an out-of-scope edit or a destructive command (`rm -rf`, `DROP TABLE`, `git push --force`, `git reset --hard`, `git clean -fd`) run `guard check --tool',
97
97
  hardening: {
@@ -101,7 +101,7 @@ const INSTRUCTION_CATALOG = Object.freeze([
101
101
  },
102
102
  {
103
103
  type: 'scope-drift',
104
- skill: 'skill-src/ai-engineering-loop/references/loop-goal.md',
104
+ skill: 'skill-src/ael/references/loop-goal.md',
105
105
  heading: 'Stage 1: Goal Contract',
106
106
  instruction: 'ASSISTED: the human confirms or edits it',
107
107
  hardening: {
@@ -111,7 +111,7 @@ const INSTRUCTION_CATALOG = Object.freeze([
111
111
  },
112
112
  {
113
113
  type: 'receipt-invalid',
114
- skill: 'skill-src/ai-engineering-loop/references/loop-deliver.md',
114
+ skill: 'skill-src/ael/references/loop-deliver.md',
115
115
  heading: 'Stage 8: Delivery',
116
116
  instruction: 'Commit before `deliver` (its receipt binds `HEAD`',
117
117
  hardening: {
@@ -121,7 +121,7 @@ const INSTRUCTION_CATALOG = Object.freeze([
121
121
  },
122
122
  {
123
123
  type: 'trap-triggered',
124
- skill: 'skill-src/ai-engineering-loop/SKILL.template.md',
124
+ skill: 'skill-src/ael/SKILL.template.md',
125
125
  heading: 'Loop',
126
126
  instruction: 'Gate failures override prose.',
127
127
  hardening: {
@@ -131,7 +131,7 @@ const INSTRUCTION_CATALOG = Object.freeze([
131
131
  },
132
132
  {
133
133
  type: 'terminal-mismatch',
134
- skill: 'skill-src/ai-engineering-loop/references/loop-deliver.md',
134
+ skill: 'skill-src/ael/references/loop-deliver.md',
135
135
  heading: 'Stage 8: Delivery',
136
136
  instruction: 'Only the delivery gate completes the run.',
137
137
  hardening: {
@@ -530,7 +530,7 @@ function buildInstructionViolations(scenarioScores) {
530
530
  return {
531
531
  type,
532
532
  count,
533
- skill: catalog?.skill || 'skill-src/ai-engineering-loop/SKILL.template.md',
533
+ skill: catalog?.skill || 'skill-src/ael/SKILL.template.md',
534
534
  heading: catalog?.heading || 'Loop',
535
535
  instruction: catalog?.instruction || type,
536
536
  hardening: catalog?.hardening || { kind: 'tighten-text', suggestion: `Tighten the skill text that covers ${type}.` }
@@ -792,7 +792,7 @@ function installProjectHostSkills(repo, host, packageRoot) {
792
792
  });
793
793
  const primaryRel = usesSharedSkills(host) ? SHARED_SKILLS_DIR : host.skills.dir;
794
794
  const primary = path.join(repo, primaryRel);
795
- const marker = path.join(primary, 'ai-engineering-loop', 'SKILL.md');
795
+ const marker = path.join(primary, 'ael', 'SKILL.md');
796
796
  if (!fs.existsSync(marker)) {
797
797
  throw benchError(`Project skill install missed ${primaryRel}`, 'BENCH_SETUP');
798
798
  }
@@ -76,8 +76,8 @@ function renderClaimedVsRealityTemplate(goal) {
76
76
  '',
77
77
  '> Generated from the frozen Goal Contract. Fill Claimed and Reality only after implementation and verification. Reality must cite observed command output; this template is not verification evidence.',
78
78
  '',
79
- '| AC | Claimed | Reality from command log |',
80
- '|---|---|---|'
79
+ '| AC | Claimed | Reality from command log | Layer |',
80
+ '|---|---|---|---|'
81
81
  ];
82
82
  for (const criterion of goal.acceptanceCriteria) {
83
83
  const evidence = markdownCell(criterion.evidenceRequired);
@@ -87,7 +87,7 @@ function renderClaimedVsRealityTemplate(goal) {
87
87
  evidence ? `Evidence: ${evidence}` : '',
88
88
  failures ? `Failure cases: ${failures}` : ''
89
89
  ].filter(Boolean).join(' — ');
90
- lines.push(`| ${markdownCell(description)} | | |`);
90
+ lines.push(`| ${markdownCell(description)} | | | |`);
91
91
  }
92
92
  return `${lines.join('\n')}\n`;
93
93
  }
@@ -143,11 +143,15 @@ function parseClaimedVsReality(markdown) {
143
143
  if (/^\|\s*-+\s*\|/.test(trimmed) || /^\|\s*AC\s*\|/i.test(trimmed)) continue;
144
144
  const cells = trimmed.split('|').map((c) => c.trim()).filter((_, i, arr) => i > 0 && i < arr.length - 1);
145
145
  if (cells.length < 3) continue;
146
- rows.push({
146
+ const row = {
147
147
  ac: cells[0],
148
148
  claimed: cells[1],
149
149
  reality: cells[2]
150
- });
150
+ };
151
+ if (cells.length >= 4 && cells[3]) {
152
+ row.layer = cells[3];
153
+ }
154
+ rows.push(row);
151
155
  }
152
156
  return { rows };
153
157
  }
package/lib/docs.js CHANGED
@@ -8,7 +8,7 @@ const fs = require('fs');
8
8
  const path = require('path');
9
9
 
10
10
  // Loop stage references are generated host-neutral copies (issue #35).
11
- const DOC_ROOTS = Object.freeze(['core', 'policies', 'profiles', 'agents', 'adapters', '.agents/skills/ai-engineering-loop/references']);
11
+ const DOC_ROOTS = Object.freeze(['core', 'policies', 'profiles', 'agents', 'adapters', '.agents/skills/ael/references']);
12
12
 
13
13
  function packageRoot() {
14
14
  return path.join(__dirname, '..');
package/lib/doctor.js CHANGED
@@ -16,8 +16,8 @@ const REQUIRED_HOST_ASSETS = [
16
16
  '.claude/agents/judge.md',
17
17
  '.grok/agents/devil-advocate.md',
18
18
  '.grok/agents/judge.md',
19
- '.agents/skills/ai-engineering-loop/SKILL.md',
20
- '.agents/skills/ai-engineering-loop/references/loop-hosts.md',
19
+ '.agents/skills/ael/SKILL.md',
20
+ '.agents/skills/ael/references/loop-hosts.md',
21
21
  '.agents/skills/backend-development/SKILL.md',
22
22
  '.agents/skills/emil-design-eng/SKILL.md',
23
23
  '.agents/skills/animate/SKILL.md',
@@ -11,7 +11,7 @@
11
11
  const fs = require('fs');
12
12
  const path = require('path');
13
13
 
14
- const SOURCE_DIR = 'skill-src/ai-engineering-loop';
14
+ const SOURCE_DIR = 'skill-src/ael';
15
15
  const SKILL_CHAR_LIMIT = 4000;
16
16
  // Compact digest for instruction-only hosts (#60), served by `docs AGENTS`.
17
17
  const DIGEST_SOURCE = 'digest.md';
@@ -10,7 +10,9 @@ const { sha256 } = require('../fsutil.js');
10
10
  const { HOSTS, guardrailSupport, usesSharedSkills } = require('./registry.js');
11
11
  const { certificationLabel } = require('./table.js');
12
12
 
13
- const CORE_SKILL = 'ai-engineering-loop';
13
+ const CORE_SKILL = 'ael';
14
+ // Pre-#107 name of the core skill; a leftover copy shows a second slash command.
15
+ const LEGACY_CORE_SKILL = 'ai-engineering-loop';
14
16
 
15
17
  function realOrSelf(file) {
16
18
  try {
@@ -63,6 +65,8 @@ function hostsDoctor({ home, selection, plan }) {
63
65
  if (!copies.length) problems.push('core skill not installed');
64
66
  if (hashes.size > 1) problems.push(`${copies.length} copies with different content`);
65
67
  if (resync.length) problems.push(`${resync.length} file(s) need sync`);
68
+ const legacy = visibleCopies(host, home, LEGACY_CORE_SKILL).map((c) => c.path);
69
+ if (legacy.length) problems.push(`legacy ${LEGACY_CORE_SKILL} skill left over (duplicate command): ${legacy.join(', ')}`);
66
70
  rows.push({ id: host.id, name: host.name, certification: host.certification, certifiedBy: host.certifiedBy || null, guardrails: guardrailSupport(host), copies, identical: hashes.size <= 1, resync, ok: problems.length === 0, problems, spec: specStatus(host, home) });
67
71
  }
68
72
  return { ok: rows.every((row) => row.ok), hosts: rows };
@@ -84,4 +88,4 @@ function formatHostsDoctor(report) {
84
88
  return lines.join('\n');
85
89
  }
86
90
 
87
- module.exports = { CORE_SKILL, visibleCopies, specStatus, hostsDoctor, formatHostsDoctor };
91
+ module.exports = { CORE_SKILL, LEGACY_CORE_SKILL, visibleCopies, specStatus, hostsDoctor, formatHostsDoctor };
package/lib/sync-hosts.js CHANGED
@@ -143,13 +143,13 @@ function loopReferenceFiles(srcDir, destDir) {
143
143
  }
144
144
 
145
145
  // The host-neutral core skill (#48): one source, byte-identical everywhere.
146
- const CORE_SKILL_SRC = '.agents/skills/ai-engineering-loop';
146
+ const CORE_SKILL_SRC = '.agents/skills/ael';
147
147
 
148
148
  // Every skill a host's skill folder gets: core loop skill, helpers, packs.
149
149
  function skillFolderFiles(skillsDir) {
150
150
  return [
151
- { src: `${CORE_SKILL_SRC}/SKILL.md`, dest: path.join(skillsDir, 'ai-engineering-loop/SKILL.md'), mode: 'upsert' },
152
- ...loopReferenceFiles(CORE_SKILL_SRC, path.join(skillsDir, 'ai-engineering-loop')),
151
+ { src: `${CORE_SKILL_SRC}/SKILL.md`, dest: path.join(skillsDir, 'ael/SKILL.md'), mode: 'upsert' },
152
+ ...loopReferenceFiles(CORE_SKILL_SRC, path.join(skillsDir, 'ael')),
153
153
  ...backendSkillFiles('.agents/skills/backend-development', path.join(skillsDir, 'backend-development')),
154
154
  ...emilKowalskiSkillFiles('.agents/skills', skillsDir),
155
155
  // Adapter-neutral (#64): installed by default, not part of the opt-in quality pack.
package/package.json CHANGED
@@ -1,10 +1,11 @@
1
1
  {
2
2
  "name": "ai-engineering-loop",
3
- "version": "2.4.0",
3
+ "version": "2.6.0",
4
4
  "description": "A visual workspace that helps AI coding agents plan, build, review, and ship reliable software.",
5
5
  "main": "bin/ai-engineering-loop.js",
6
6
  "bin": {
7
- "ai-engineering-loop": "bin/ai-engineering-loop.js"
7
+ "ai-engineering-loop": "bin/ai-engineering-loop.js",
8
+ "ael": "bin/ai-engineering-loop.js"
8
9
  },
9
10
  "files": [
10
11
  "bin/",
@@ -1,20 +0,0 @@
1
- # Stage 5: Verification
2
-
3
- - `npx ai-engineering-loop verify --run <runId> [--cmd "<command>"]...` (default `test_unit` from verification.md) records commands in parallel (`--serial`, `--shell`), binds redacted evidence to the gated diff, and only when all pass gates verification, compacts, and scaffolds claimed-vs-reality.
4
- - Iterating (T1/T2): `verify --related` runs `test_related` on the diff's changed files. After Judge PASS, `verify --final` runs the full suite once; delivery requires it after related-only runs. Unchanged diff: passes are reused (`--fresh` re-runs).
5
- - A failed command is recorded honestly and returns non-zero; it cannot pass the gate. Vague "seems green" is invalid.
6
- - Fill `.ai-engineering-loop/tasks/claimed-vs-reality.md`: Claimed from the actual change, Reality from command output. Do not spawn DA while the file is missing or any Claimed row lacks Reality.
7
- - Hand-authored artifacts: `scaffold verification|findings|delivery --run <runId>`, fill it, remove `_templateOnly`, then `validate <file>`. Templates are never evidence.
8
- - Pass run-summary.md and verification-summary.json to reviewers instead of raw logs.
9
-
10
- ## No claim without fresh evidence
11
-
12
- Before saying "done", "fixed", "passing", or "ready", run the proving command in this iteration and cite its output; earlier runs and "should work" are not evidence.
13
-
14
- | Claim | Required evidence |
15
- |---|---|
16
- | Tests pass | the test command's output this iteration, exit 0 |
17
- | Bug fixed | the red repro now passes, with the command shown |
18
- | AC met | its claimed-vs-reality row cites that output |
19
-
20
- After `verify`, continue from run-summary.md and verification-summary.json, not earlier logs or chat.