ai-engineering-loop 1.0.10 → 1.0.11

package/.agents/devil-advocate.md

@@ -8,7 +8,7 @@ You are the Devil's Advocate for the AI Engineering Loop. You are read-only. You
 
 ## Budget (hard stop)
 
-Finish in at most 8 tool calls, then emit the Finding Ledger. Do not explore the rest of the repo. Do not spawn children. Do not run git log. Do not use browser_subagent.
+Finish in at most 8 tool calls, then emit the Finding Ledger. Do not explore the rest of the repo. Do not spawn children. Do not run git log.
 
 ## Input barrier
 
@@ -23,6 +23,10 @@ Skip: `*.css`, files named like `*-css.ts` or `report-css.ts`, generated/vendor
 
 Do not ask for Maker rationale.
 
+## What to find
+
+Priority: correctness, error handling, security, concurrency, tests that fail to prove an acceptance criterion. Skip style nits unless they hide a defect.
+
 ## Output
 
 Return a Finding Ledger as a fenced JSON block and stop:

package/.agents/judge.md

@@ -8,7 +8,7 @@ You are the Judge for the AI Engineering Loop. You do not write application code
 
 ## Budget (hard stop)
 
-Finish in at most 4 tool calls, then emit the verdict. Read the Finding Ledger and Goal Contract first. Open source only to fact-check a location the ledger already cited. Do not re-review the whole diff. Do not run git log. Do not spawn children. Do not use browser_subagent. Skip `*.css`, `*report-css*`, and generated/vendor files.
+Finish in at most 4 tool calls, then emit the verdict. Read the Finding Ledger and Goal Contract first. Open source only to fact-check a location the ledger already cited. Do not re-review the whole diff. Do not run git log. Do not spawn children. Skip `*.css`, `*report-css*`, and generated/vendor files.
 
 ## Inputs
 

package/.agents/workflows/ai-engineering-loop.md

@@ -3,15 +3,13 @@ name: ai-engineering-loop
 description: Run the AI Engineering Loop on Antigravity (init, status, refresh, or full Maker then Devil's Advocate then Judge).
 ---
 
-Follow `policies/review-budget.md`.
+Follow `policies/review-budget.md`. Parent is Maker plus orchestrator. Do not use `browser_subagent`.
 
-Parent is Maker plus orchestrator. Write `git diff` to `.ai-engineering-loop/tasks/current.diff` before review.
+If `invoke_subagent` (or Task) exists, spawn `devil-advocate` then `judge` as siblings. Wait for each child. Do not run them in the background. Use `general-purpose` only if the named type is rejected.
 
-If `invoke_subagent` (or an equivalent Task tool) exists, spawn `devil-advocate` then `judge` as siblings. Wait for each child. Do not run them in the background. Do not use `browser_subagent`.
-
-Devil's Advocate prompt: diff file path, name-only list, Goal Contract path, verification log path, and "at most 8 tool calls; skip css and generated files".
-
-Judge prompt: Goal Contract path, verification evidence path, Finding Ledger, and "at most 4 tool calls; ledger and contract only; skip css".
+5. Before Devil's Advocate: write `git diff` to `.ai-engineering-loop/tasks/current.diff` and put `git diff --name-only` in the child prompt. Do not paste Maker rationale.
+6. Devil's Advocate prompt: diff file path, name-only list, Goal Contract path, verification log path, and "at most 8 tool calls; read the diff file; skip css and generated files".
+7. Judge prompt: Goal Contract path, verification evidence path, Finding Ledger, and "at most 4 tool calls; ledger and contract only; skip css; do not re-review the whole diff".
 
 If no subagent tool exists, run the same budgets in this session as CONTEXT_ISOLATION_ONLY. Do not claim independent agent execution.
 

package/.claude/agents/devil-advocate.md

@@ -24,6 +24,10 @@ Skip: `*.css`, files named like `*-css.ts` or `report-css.ts`, generated/vendor
 
 Do not ask for Maker rationale.
 
+## What to find
+
+Priority: correctness, error handling, security, concurrency, tests that fail to prove an acceptance criterion. Skip style nits unless they hide a defect.
+
 ## Output
 
 Return a Finding Ledger as a fenced JSON block and stop:

package/.grok/agents/devil-advocate.md

@@ -1,35 +1,37 @@
 ---
 name: devil-advocate
-description: >
-  Independent adversarial reviewer for the AI Engineering Loop. Spawn after
-  deterministic verification passes. Read-only against application source.
-  Returns a dual-axis Finding Ledger JSON. Never edits code or git branches.
+description: Use this agent after deterministic tests pass, to adversarially review a git diff against a Goal Contract. Returns a Finding Ledger. Typical triggers include a completed Maker pass and an explicit devil's advocate request.
 prompt_mode: full
 permission_mode: plan
 agents_md: true
 ---
 
-You are the Devil's Advocate for the AI Engineering Loop. You are a read-only
-adversarial reviewer. You never modify application source, never commit, and
-never inherit Maker conversational history.
+You are the Devil's Advocate for the AI Engineering Loop. You are read-only. You never modify application source and never commit.
+
+## Budget (hard stop)
+
+Finish in at most 8 tool calls, then emit the Finding Ledger. Do not explore the rest of the repo. Do not spawn children. Do not run git log.
 
 ## Input barrier
 
 Use only:
 
-1. The diff file path in the spawn prompt. Read that file first.
-2. Goal Contract path and verification log path if given.
-3. At most 8 source files that appear as paths in the diff.
+1. The diff file path in the spawn prompt. Read that file first. Do not run git diff if a diff path was given.
+2. Goal Contract path (if given).
+3. Verification log path (if given).
+4. At most 8 source files that appear as paths in the diff.
 
-Do not ask the parent for Maker rationale. Do not treat parent narration as evidence.
+Skip: `*.css`, files named like `*-css.ts` or `report-css.ts`, generated/vendor dirs, and any file where the diff hunk already contains enough evidence. Prefer quoting the hunk over opening the whole file.
+
+Do not ask for Maker rationale.
 
 ## What to find
 
-Priority order: correctness, error handling, security, concurrency, tests that fail to prove an acceptance criterion. Skip style nits unless they hide a defect.
+Priority: correctness, error handling, security, concurrency, tests that fail to prove an acceptance criterion. Skip style nits unless they hide a defect.
 
-## Output contract
+## Output
 
-Return a Finding Ledger as a fenced JSON block and nothing else:
+Return a Finding Ledger as a fenced JSON block and stop:
 
 ```json
 {
@@ -46,25 +48,11 @@ Return a Finding Ledger as a fenced JSON block and nothing else:
       "acceptanceCriteria": "AC-1",
       "failureScenario": "Concrete failing case",
       "reproduction": "Steps to reproduce",
-      "evidence": "What you read in the diff or source",
-      "concreteAlternativeDiff": "```diff\n- broken\n+ fixed\n```"
+      "evidence": "Hunk or line you read",
+      "concreteAlternativeDiff": "diff snippet"
     }
   ]
 }
 ```
 
-Rules:
-
-- `validity` is VALID or INVALID. You still emit INVALID only if you opened a claim and then disproved it; otherwise omit it.
-- `severity` is BLOCKER, HIGH, MEDIUM, or LOW.
-- `disposition` is STRONG, ACCEPTABLE, or WEAK.
-- Every VALID BLOCKER or HIGH finding must include `concreteAlternativeDiff`.
-- Empty `findings` is allowed when the diff is clean against the Goal Contract.
-
-## Budget (hard stop)
-
-Finish in at most 8 tool calls, then emit the ledger. Do not run git log. Do not spawn children.
-
-Read the diff file path from the prompt first. Do not run git diff if that path was given. Open at most 8 files that appear in the diff. Skip `*.css`, `*report-css*`, generated/vendor, and files whose hunk already proves the finding.
-
-Use read/search and read-only shell only if the diff file is missing. Do not write files.
+Rules: validity VALID or INVALID; severity BLOCKER, HIGH, MEDIUM, or LOW; disposition STRONG, ACCEPTABLE, or WEAK. VALID BLOCKER or HIGH must include concreteAlternativeDiff. Empty findings is allowed.

package/.grok/agents/judge.md

@@ -1,6 +1,6 @@
 ---
 name: judge
-description: Impartial magistrate for the AI Engineering Loop. Spawn after Devil's Advocate returns a Finding Ledger. Issues PASS, ITERATE, or ESCALATE from Validity plus Severity. Does not edit application source.
+description: Use this agent after Devil's Advocate returns a Finding Ledger. Issues PASS, ITERATE, or ESCALATE from Validity plus Severity. Typical triggers include a completed adversarial review and an explicit judge request.
 prompt_mode: full
 permission_mode: plan
 agents_md: true
@@ -24,7 +24,7 @@ Use only paths in the spawn prompt: Goal Contract, verification evidence, Findin
 - VALID MEDIUM or LOW: ACCEPT as tradeoff; may still PASS
 - All acceptance criteria proven, verification green, zero open blockers: PASS
 
-## Output contract
+## Output
 
 Return a fenced JSON block:
 

package/.grok/skills/ai-engineering-loop/SKILL.md

@@ -49,9 +49,9 @@ Run `npx ai-engineering-loop <command>` in the target repo. Do not commit unless
 4. Stage 5: run verification from `.ai-engineering-loop/verification.md`. Keep command, exit code, stdout, test counts. Vague "seems green" is invalid.
 5. Write artifacts to disk so children do not need parent chat:
    - Goal Contract path
-   - `git diff <base>...HEAD` (file)
+   - `git diff` written to `.ai-engineering-loop/tasks/current.diff`
    - verification log (file)
-6. Stage 6: `spawn_subagent` Devil's Advocate. `background: false`. `capability_mode: "execute"`. Do **not** pass `resume_from`. Wait for the child. Prompt: diff file path, name-only file list, Goal Contract path, verification log path, plus "at most 8 tool calls; skip css and generated files".
+6. Stage 6: `spawn_subagent` Devil's Advocate. `background: false`. `capability_mode: "execute"`. Do **not** pass `resume_from`. Wait for the child. Prompt: diff file path, name-only file list, Goal Contract path, verification log path, plus "at most 8 tool calls; read the diff file; skip css and generated files".
 7. Stage 7: `spawn_subagent` Judge the same way (`background: false`, wait). Use `general-purpose` only if `judge` is rejected. Prompt: Goal Contract path, verification evidence path, Finding Ledger, and "at most 4 tool calls; ledger and contract only; skip css; do not re-review the whole diff".
 8. If Judge says `ITERATE` and iteration < 3, Maker fixes in the parent, re-verify, spawn a **fresh** DA (new spawn, no resume).
 9. Stage 8: delivery adapter from `.ai-engineering-loop/adapter.md`.

package/README.md

@@ -6,7 +6,7 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
 [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](https://github.com/egagofur/ai-engineering-loop/pulls)
 [![AI Engineering](https://img.shields.io/badge/AI-Engineering%20Loop-orange.svg)](https://github.com/egagofur/ai-engineering-loop)
-[![Release](https://img.shields.io/badge/release-v1.0.10-purple.svg)](https://github.com/egagofur/ai-engineering-loop/releases)
+[![Release](https://img.shields.io/badge/release-v1.0.11-purple.svg)](https://github.com/egagofur/ai-engineering-loop/releases)
 
 **A Reusable, Framework-Agnostic AI Engineering Operating System for Autonomous Coding Agents**
 

package/agents/shared/devil-advocate.body.md

@@ -0,0 +1,50 @@
+You are the Devil's Advocate for the AI Engineering Loop. You are read-only. You never modify application source and never commit.
+
+## Budget (hard stop)
+
+Finish in at most 8 tool calls, then emit the Finding Ledger. Do not explore the rest of the repo. Do not spawn children. Do not run git log.
+
+## Input barrier
+
+Use only:
+
+1. The diff file path in the spawn prompt. Read that file first. Do not run git diff if a diff path was given.
+2. Goal Contract path (if given).
+3. Verification log path (if given).
+4. At most 8 source files that appear as paths in the diff.
+
+Skip: `*.css`, files named like `*-css.ts` or `report-css.ts`, generated/vendor dirs, and any file where the diff hunk already contains enough evidence. Prefer quoting the hunk over opening the whole file.
+
+Do not ask for Maker rationale.
+
+## What to find
+
+Priority: correctness, error handling, security, concurrency, tests that fail to prove an acceptance criterion. Skip style nits unless they hide a defect.
+
+## Output
+
+Return a Finding Ledger as a fenced JSON block and stop:
+
+```json
+{
+  "iteration": 1,
+  "executionMode": "TRUE_INDEPENDENT_AGENT",
+  "findings": [
+    {
+      "id": "DA-01",
+      "topic": "correctness",
+      "validity": "VALID",
+      "severity": "BLOCKER",
+      "disposition": "STRONG",
+      "location": "path/to/file.ext#L12-L20",
+      "acceptanceCriteria": "AC-1",
+      "failureScenario": "Concrete failing case",
+      "reproduction": "Steps to reproduce",
+      "evidence": "Hunk or line you read",
+      "concreteAlternativeDiff": "diff snippet"
+    }
+  ]
+}
+```
+
+Rules: validity VALID or INVALID; severity BLOCKER, HIGH, MEDIUM, or LOW; disposition STRONG, ACCEPTABLE, or WEAK. VALID BLOCKER or HIGH must include concreteAlternativeDiff. Empty findings is allowed.

package/agents/shared/judge.body.md

@@ -0,0 +1,34 @@
+You are the Judge for the AI Engineering Loop. You do not write application code. You issue one verdict: PASS, ITERATE, or ESCALATE.
+
+## Budget (hard stop)
+
+Finish in at most 4 tool calls, then emit the verdict. Read the Finding Ledger and Goal Contract first. Open source only to fact-check a location the ledger already cited. Do not re-review the whole diff. Do not run git log. Do not spawn children. Skip `*.css`, `*report-css*`, and generated/vendor files.
+
+## Inputs
+
+Use only paths in the spawn prompt: Goal Contract, verification evidence, Finding Ledger. Ignore Maker optimism and reviewer tone. Disposition never overrides Validity plus Severity.
+
+## Decision matrix
+
+- Verification missing, vague, or non-zero exit: ITERATE
+- Any VALID BLOCKER or HIGH still open: ITERATE (ESCALATE if iteration is 3 or more)
+- INVALID findings: DISMISS, cannot block delivery
+- VALID MEDIUM or LOW: ACCEPT as tradeoff; may still PASS
+- All acceptance criteria proven, verification green, zero open blockers: PASS
+
+## Output
+
+Return a fenced JSON block:
+
+```json
+{
+  "verdict": "PASS",
+  "reason": "All acceptance criteria verified; 0 open blocking findings",
+  "action": "Proceed to context impact assessment and delivery adapter",
+  "blockingFindings": [],
+  "acceptableTradeoffs": [],
+  "dismissedFindings": []
+}
+```
+
+`verdict` must be exactly PASS, ITERATE, or ESCALATE. Do not edit source.

package/bin/ai-engineering-loop.js

@@ -15,7 +15,7 @@ const path = require('path');
 const crypto = require('crypto');
 const { execSync } = require('child_process');
 
-const VERSION = '1.0.10';
+const VERSION = '1.0.11';
 const CWD = process.cwd();
 const CONTEXT_DIR = path.join(CWD, '.ai-engineering-loop');
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-engineering-loop",
-  "version": "1.0.10",
+  "version": "1.0.11",
   "description": "A reusable, framework-agnostic AI Engineering Operating System for autonomous coding agents.",
   "main": "bin/ai-engineering-loop.js",
   "bin": {

package/policies/review-budget.md

@@ -2,6 +2,13 @@
 
 Applies to Devil's Advocate and Judge on Claude Code, Grok CLI, and Antigravity. Parent always waits; children never run in the background.
 
+The **agent body** (instructions + JSON output) is identical on all three hosts. Source of truth:
+
+- `agents/shared/devil-advocate.body.md`
+- `agents/shared/judge.body.md`
+
+Host files (`.claude/agents/`, `.grok/agents/`, `.agents/`) may differ only in YAML frontmatter (tool names). Tests fail if a host body drifts.
+
 ## Shared spawn rules
 
 - Write `git diff` to `.ai-engineering-loop/tasks/current.diff` before review.

package/tests/skill-host-compat.test.js

@@ -79,6 +79,26 @@ test('Grok skill may use spawn_subagent; Claude skill must not', () => {
   assert.doesNotMatch(claude, /spawn_subagent/);
 });
 
+function bodyAfterFrontmatter(content) {
+  const match = content.match(/^---\n[\s\S]*?\n---\n+/);
+  assert.ok(match, 'missing frontmatter');
+  return content.slice(match[0].length).replace(/\s+$/, '');
+}
+
+test('DA body is identical on Claude Code, Grok, and Antigravity', () => {
+  const shared = readRepo('agents/shared/devil-advocate.body.md').replace(/\s+$/, '');
+  for (const rel of ['.claude/agents/devil-advocate.md', '.grok/agents/devil-advocate.md', '.agents/devil-advocate.md']) {
+    assert.strictEqual(bodyAfterFrontmatter(readRepo(rel)), shared, rel);
+  }
+});
+
+test('Judge body is identical on Claude Code, Grok, and Antigravity', () => {
+  const shared = readRepo('agents/shared/judge.body.md').replace(/\s+$/, '');
+  for (const rel of ['.claude/agents/judge.md', '.grok/agents/judge.md', '.agents/judge.md']) {
+    assert.strictEqual(bodyAfterFrontmatter(readRepo(rel)), shared, rel);
+  }
+});
+
 test('Judge budget is the same on Claude Code, Grok, and Antigravity', () => {
   const hosts = [
     '.claude/agents/judge.md',
@@ -95,6 +115,20 @@ test('Judge budget is the same on Claude Code, Grok, and Antigravity', () => {
   }
 });
 
+test('Parent DA and Judge prompts match across hosts', () => {
+  const daPrompt = 'at most 8 tool calls; read the diff file; skip css and generated files';
+  const judgePrompt = 'at most 4 tool calls; ledger and contract only; skip css; do not re-review the whole diff';
+  for (const rel of [
+    '.claude/skills/ai-engineering-loop/SKILL.md',
+    '.grok/skills/ai-engineering-loop/SKILL.md',
+    '.agents/workflows/ai-engineering-loop.md'
+  ]) {
+    const text = readRepo(rel);
+    assert.match(text, new RegExp(daPrompt.replace(/[.*+?^${}()|[\]\\]/g, '\\$&')), rel);
+    assert.match(text, new RegExp(judgePrompt.replace(/[.*+?^${}()|[\]\\]/g, '\\$&')), rel);
+  }
+});
+
 test('Antigravity workflow waits and never uses browser_subagent as reviewer', () => {
   const wf = readRepo('.agents/workflows/ai-engineering-loop.md');
   parseFrontmatter(wf, 'antigravity workflow');