@mmerterden/multi-agent-pipeline 16.12.0 → 16.14.0

package/pipeline/skills/shared/README.md

@@ -2,11 +2,11 @@
 
 Single source of truth for skills delivered to both Claude Code (`~/.claude/skills/`) and Copilot CLI (`~/.copilot/skills/`) by the installer.
 
-**Total:** 210 skills (56 core + 154 external). Auto-generated by `scripts/gen-skills-index.mjs`  -  do not edit by hand.
+**Total:** 211 skills (57 core + 154 external). Auto-generated by `scripts/gen-skills-index.mjs`  -  do not edit by hand.
 
 ## Directory layout
 
-- **`core/`**  -  56 `multi-agent*` orchestration skills that are pipeline-critical. Edits here are core-code changes.
+- **`core/`**  -  57 `multi-agent*` orchestration skills that are pipeline-critical. Edits here are core-code changes.
 - **`external/`**  -  154 iOS / Android / generic skills imported from the upstream skill library. Mirrors of third-party guidance.
 - Install destinations (ADR-0009): Claude Code gets NO local copy of `external/` - it loads those skills from the `multi-agent-plugins` marketplace, namespaced (`ai-<stack>-toolkit:<name>`); only the two compliance catalogs from `core/` land in `~/.claude/skills/`. Copilot CLI and Codex CLI receive a flat copy filtered to the enabled stacks. `external/` remains the single authoring source that `build-stack-plugins.mjs` publishes from.
 
@@ -14,7 +14,7 @@ Source layout is logical grouping only  -  skill discovery at runtime is unchang
 
 ## Categories
 
-- [Pipeline Orchestration](#pipeline-orchestration)  -  56
+- [Pipeline Orchestration](#pipeline-orchestration)  -  57
 - [iOS / Apple Ecosystem](#ios-apple-ecosystem)  -  90
 - [Android / Kotlin](#android-kotlin)  -  13
 - [Web](#web)  -  10
@@ -44,6 +44,7 @@ Source layout is logical grouping only  -  skill discovery at runtime is unchang
 | [`multi-agent-feedback`](./core/multi-agent-feedback/) | `core` | Send one message to the maintainer: a bug, an idea or a question. Only the text you type is sent - no logs, no repo names, no paths. Shows t |
 | [`multi-agent-forget`](./core/multi-agent-forget/) | `core` | Remove a saved /multi-agent routine (created by /multi-agent:save): deletes its local-only command and its registry entry. Asks which one an |
 | [`multi-agent-garbage-collect`](./core/multi-agent-garbage-collect/) | `core` | Sweep leftover /tmp scratch (picker state, review diffs, channel payloads, analysis drafts) from past runs. Dry-run first; confirms before d |
+| [`multi-agent-graph`](./core/multi-agent-graph/) | `core` | Build and query this repo's code graph: a deterministic, LLM-free map of symbols, imports and references used to narrow Phase 1's Explore sc |
 | [`multi-agent-help`](./core/multi-agent-help/) | `core` | Multi-agent pipeline usage guide  -  renders in EN or TR per prefs.global.outputLanguage (falls back to promptLanguage for backward compatib |
 | [`multi-agent-ios-coding-standard`](./core/multi-agent-ios-coding-standard/) | `core` | Audit an iOS module against the shared coding-standard registry (99 stable-ID rules), produce a remediation plan, then hand off to dev/dev-l |
 | [`multi-agent-issue`](./core/multi-agent-issue/) | `core` | List unassigned GitHub issues, pick one, auto-assign, and launch the multi-agent pipeline. Use when a GitHub issue should be picked up and s |
@@ -60,7 +61,7 @@ Source layout is logical grouping only  -  skill discovery at runtime is unchang
 | [`multi-agent-refactor`](./core/multi-agent-refactor/) | `core` | Analyse the project: extract adapted best-practices, hunt real bugs + improvement areas, check upstream drift of derived skills, research th |
 | [`multi-agent-resume`](./core/multi-agent-resume/) | `core` | Resume a stopped or failed task from the phase where it left off. Use when a task stopped or failed and should carry on from where it left o |
 | [`multi-agent-resume-local`](./core/multi-agent-resume-local/) | `core` | Continue already-done LOCAL work through the pipeline tail: Review → Build+Test → Commit/PR → Report (technical analysis + Jira test-scenari |
-| [`multi-agent-review`](./core/multi-agent-review/) | `core` | Run parallel review on a branch diff or a Pull Request: 3 models on Claude Code (Fable + Opus + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonn |
+| [`multi-agent-review`](./core/multi-agent-review/) | `core` | Run parallel review on a branch diff or a Pull Request: 3 models on Claude Code (Fable + Opus + Sonnet), 3 models on Copilot CLI (GPT + Opus |
 | [`multi-agent-review-analysis`](./core/multi-agent-review-analysis/) | `core` | Review a written analysis document instead of a diff: resolve it from a path, a Confluence page or a Jira issue, run the deterministic gates |
 | [`multi-agent-review-issue`](./core/multi-agent-review-issue/) | `core` | Assess whether a GitHub issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / sta |
 | [`multi-agent-review-jira`](./core/multi-agent-review-jira/) | `core` | Assess whether a Jira issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / stack |
@@ -258,6 +259,6 @@ Source layout is logical grouping only  -  skill discovery at runtime is unchang
 | [`xcode-build-benchmark`](./external/xcode-build-benchmark/) | `external` | Benchmark Xcode clean and incremental builds with repeatable inputs, timing summaries, and timestamped `.build-benchmark/` artifacts. Use wh |
 | [`xcode-build-fixer`](./external/xcode-build-fixer/) | `external` | Apply approved Xcode build optimization changes following best practices, then re-benchmark to verify improvement. Use when a developer has  |
 | [`xcode-build-orchestrator`](./external/xcode-build-orchestrator/) | `external` | Orchestrate Xcode build optimization by benchmarking first, running the specialist analysis skills, prioritizing findings, requesting explic |
-| [`xcode-compilation-analyzer`](./external/xcode-compilation-analyzer/) | `external` | Analyze Swift and mixed-language compile hotspots using build timing summaries and Swift web diagnostics, then produce a recommend-firs |
+| [`xcode-compilation-analyzer`](./external/xcode-compilation-analyzer/) | `external` | Analyze Swift and mixed-language compile hotspots using build timing summaries and Swift frontend diagnostics, then produce a recommend-firs |
 | [`xcode-project-analyzer`](./external/xcode-project-analyzer/) | `external` | Audit Xcode project configuration, build settings, scheme behavior, and script phases to find build-time improvements with explicit approval |
 

package/pipeline/skills/shared/core/multi-agent-graph/SKILL.md

@@ -0,0 +1,106 @@
+---
+name: multi-agent-graph
+language: en
+description: "Build and query this repo's code graph: a deterministic, LLM-free map of symbols, imports and references used to narrow Phase 1's Explore scope and to keep the knowledge base current. Read-only on code, costs no API tokens. Use when a task needs to know where something lives or what depends on it before reading files."
+user-invocable: true
+argument-hint: "[build | refresh | ask \"<question>\" | affected \"<symbol>\" | report | status]"
+---
+# multi-agent-graph  -  code graph build and query
+
+**Input**: $ARGUMENTS
+
+A code graph is a map of what this repo declares and what refers to what, built by
+regex over comment-stripped source. It exists so Phase 1 can narrow its Explore
+fan-out and Phase 7 can refresh `~/.claude/knowledge/<project>/` without an LLM
+pass. It answers "where does this live" and "what depends on this". It does not
+answer "what calls this at runtime": call graphs and type resolution need a real
+parser, which would be an npm runtime dependency, and ADR-0004 forbids one.
+
+No worktree, no branch, no commit, no pipeline chaining.
+
+## Sub-commands
+
+| Input | Runs | Notes |
+|---|---|---|
+| `build` | `graph-build.mjs --root <repo> --stack <stack>` | Writes `~/.claude/knowledge/<project>/code-graph.json` |
+| `refresh` | same as `build` | A full rebuild takes seconds, so there is no separate incremental path |
+| `ask "<question>"` | `graph-query.mjs "<question>" --budget N` | Token-budgeted traversal; default budget 2000 |
+| `affected "<symbol>"` | `graph-affected.mjs "<symbol>" --depth N` | Reverse traversal: the blast radius of a change |
+| `report` | `graph-report.mjs` | Writes `GRAPH_REPORT.md` beside the graph |
+| `status` | `graph-report.mjs --status` | One line: stack, scale, build time and whether `baseCommit` still matches HEAD. Never read the graph file yourself - it is 22MB on a large repo |
+
+With no argument, run `status`, then offer `build` when no graph exists and
+`refresh` when `baseCommit` differs from the current HEAD.
+
+## Steps
+
+1. **Resolve the repo.** `PROJECT_ROOT` is the current repo root unless the user
+   named another. Derive the graph path once and pass it to every call below:
+
+   ```bash
+   GRAPH_PATH="$HOME/.claude/knowledge/$(basename "$PROJECT_ROOT")/code-graph.json"
+   ```
+
+   The query, affected and report scripts default that path from the CWD's
+   basename, which is not the same thing when the shell sits in a worktree or a
+   sub-package, so a defaulted path can point at a graph that was never built.
+
+2. **Resolve the stack.** Read `state.detectedStack` when a run is in flight;
+   otherwise detect from project markers the way Phase 1 Step 2 does. Only stacks
+   with a file in `$HOME/.claude/scripts/code-graph-rules/` can be built. A stack with
+   no rule file is reported as unsupported, never guessed at.
+
+3. **Run the sub-command.** Every script is read-only on the repo and writes only
+   under `~/.claude/knowledge/`:
+
+   ```bash
+   node $HOME/.claude/scripts/graph-build.mjs --root "$PROJECT_ROOT" --stack "$STACK" --out "$GRAPH_PATH"
+   node $HOME/.claude/scripts/graph-query.mjs "<question>" --graph "$GRAPH_PATH" --budget 2000
+   node $HOME/.claude/scripts/graph-affected.mjs "<symbol>" --graph "$GRAPH_PATH" --depth 2
+   node $HOME/.claude/scripts/graph-report.mjs --graph "$GRAPH_PATH"
+   node $HOME/.claude/scripts/graph-report.mjs --graph "$GRAPH_PATH" --status
+   ```
+
+4. **Validate after a build.** A graph that parses but whose edges point at
+   missing nodes yields silently truncated traversals, so the build is not
+   reported as successful until the validator agrees:
+
+   ```bash
+   node $HOME/.claude/scripts/validate-code-graph.mjs "$GRAPH_PATH"
+   ```
+
+   A non-zero exit fails CLOSED: report the validator's `errors[]` verbatim and
+   do not record the graph as usable.
+
+5. **Report.** One line for a build (`files / nodes / edges / elapsed`), the
+   traversal output as-is for `ask` and `affected`, the report path for `report`.
+
+## What the output is for
+
+`ask` returns ranked nodes plus their neighbourhood within a token budget. Feed
+it to an Explore agent as the starting file set rather than pasting it into a
+final answer: it is a search result, not an explanation.
+
+`affected` returns dependents, which is what `analysis.touchedAreas[]` wants.
+
+## Limits worth stating when reporting
+
+- References resolve only when a name maps to exactly one declaration. A type
+  declared in two files is ambiguous and is deliberately dropped, so `affected`
+  under-reports for duplicated names rather than fanning out to every candidate.
+- Only type-like symbols are reference targets. Functions appear in the graph
+  through their declaring file, not as targets, because a bare lowercase name
+  matched across files is almost never a call to that exact declaration.
+- Comments and string literals are stripped before extraction, so a name that
+  appears only in prose or in a string produces no edge.
+- A nested declaration is a node but never a reference target. A Kotlin sealed
+  case or a Python inner class named `Icon` or `Color` is declared exactly once,
+  so the ambiguity rule above does not catch it, and every file that merely
+  mentions the framework type of that name would otherwise gain an edge to it.
+- On stacks whose exported unit is a function (Node most of all) the symbol
+  layer is thin by design and the import graph between files carries the value.
+  Ask `affected "<file>.mjs"` there, not `affected "<functionName>"`.
+- `affected` at `--depth 1` returns direct symbol references only. An import
+  whose module name matches a declaring file's basename reaches the symbol
+  through that file, so its importers appear at depth 2. Keep the default
+  depth of 2 unless direct references are what you actually want.

package/pipeline/skills/shared/core/multi-agent-sync/SKILL.md

@@ -31,7 +31,7 @@ Run all steps automatically:
 
 ```
 Step 1: DETECT      Compare timestamps, find stale targets
-Step 2: COPILOT     Claude Code -> Copilot CLI (instructions + 53 sub-command skills)
+Step 2: COPILOT     Claude Code -> Copilot CLI (instructions + 54 sub-command skills)
 Step 2b: CODEX      Claude Code -> Codex CLI (1 router skill + 51 specs as refs + 8 agent TOML)
 Step 3: REPO        Claude Code -> pipeline repo (genericized, personal data scrub)
 Step 3d: DEV-TOOLKIT Companion MCP server -> detect movement, ship gates, commit + publish
@@ -98,7 +98,7 @@ If nothing is stale -> report "All targets up to date" and stop.
 ## Codex Sync (Step 2b)
 
 This step does **not** hand-copy files. The Codex tree is a *transform* of the Claude
-tree, not a mirror: the 53 sub-command specs become reference files (Codex silently
+tree, not a mirror: the 54 sub-command specs become reference files (Codex silently
 truncates its skills block  -  see `cross-cli-contract.md` 2.6), every reference to a
 CLI-owned tree is retargeted (`agents/<persona>.md` becomes `.toml`, the dispatcher
 becomes the router skill), the 8 personas are regenerated as TOML with a model +
@@ -207,7 +207,7 @@ When invoked with the `release` argument:
 3. LINT + TEST   ESLint + smoke tests
 4. VERSION       package.json version bump (patch/minor/major)
 5. Commit + TAG  git commit + git tag v{VERSION}
-6. PUSH          git push --tags -> release.yml auto-publish
+6. PUSH          git push --tags; publish is local (release.yml off)
 7. DEV-TOOLKIT   Ship the companion MCP server if it moved (Step 3d gates, then publish)
 8. WEBSITE       Version + features -> {website-host} (maintainer identity, build verified Ready)
 9. COPILOT       Copilot CLI instructions + skills sync
@@ -224,18 +224,18 @@ When invoked with the `release` argument:
 |-------------|-------------|
 | `~/.claude/commands/multi-agent/{cmd}.md` | `~/.copilot/skills/multi-agent-{cmd}/SKILL.md` |
 
-**53 commands are synced** (canonical inventory  -  must match `cross-cli-contract.md` section 1; drift = contract violation):
+**54 commands are synced** (canonical inventory  -  must match `cross-cli-contract.md` section 1; drift = contract violation):
 
 ```
 analysis, analysis-resolve, autopilot, build-optimize, channels,
 complaint-analysis, create-jira, design-check, dev, dev-autopilot, dev-local,
-dev-local-autopilot, diff-explain, feedback, forget, garbage-collect, help,
-ios-coding-standard, issue, jira, kill, language, local, local-autopilot,
-log, manual-test, prune-logs, prune-prompts, purge, refactor, resume,
-resume-local, review, review-analysis, review-issue, review-jira, routines,
-save, scan, search, setup, stack, status, store-ready, sync, test,
-test-accessibility, test-dark-mode, test-dynamic-type, test-screenshots,
-testflight-validation, uninstall, update
+dev-local-autopilot, diff-explain, feedback, forget, garbage-collect,
+graph, help, ios-coding-standard, issue, jira, kill, language, local,
+local-autopilot, log, manual-test, prune-logs, prune-prompts, purge,
+refactor, resume, resume-local, review, review-analysis, review-issue,
+review-jira, routines, save, scan, search, setup, stack, status,
+store-ready, sync, test, test-accessibility, test-dark-mode,
+test-dynamic-type, test-screenshots, testflight-validation, uninstall, update
 ```
 
 **NOT synced**: `refs/*`  -  Lazy-load references, Claude Code specific

package/pipeline/skills/shared/core/multi-agent-uninstall/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: multi-agent-uninstall
 language: en
-description: "Uninstall the pipeline from Claude Code + Copilot CLI. Keychain access tokens are always left untouched; --all-data also clears pipeline settings and logs. Asks for double confirmation. Use when the pipeline should be removed from Claude Code and Copilot CLI."
+description: "Uninstall the pipeline from Claude Code + Copilot CLI. Keychain access tokens are always left untouched; --all-data also clears pipeline settings, logs, per-repo memory and the knowledge base. Asks for double confirmation. Use when the pipeline should be removed from Claude Code and Copilot CLI."
 user-invocable: true
 argument-hint: "[--dry-run] [--all-data] [--claude] [--copilot] [--target=<path>]"
 ---
@@ -17,7 +17,7 @@ Removes the pipeline itself from the system. **Different from `multi-agent-purge
 | `multi-agent-purge` | Active tasks' worktree / branch / log / state (development data) |
 | `multi-agent-uninstall` | The pipeline itself: skills, commands, agents, scripts  -  from every CLI |
 
-Two modes: **standard** (default) removes distributed files and keeps settings + logs; **full cleanup** (`--all-data`) also removes `multi-agent-preferences.json` and `~/.claude/logs/multi-agent/`. Tokens are never touched in either mode.
+Two modes: **standard** (default) removes distributed files and keeps every data root; **full cleanup** (`--all-data`) also removes `multi-agent-preferences.json`, `~/.claude/logs/multi-agent/`, `~/.claude/memory/multi-agent/` and `~/.claude/knowledge/`. Tokens are never touched in either mode. Memory written inside a repo (`$PROJECT_ROOT/.multi-agent/memory/`) is never touched at all.
 
 ## Never deleted (either mode)
 
@@ -30,13 +30,13 @@ Two modes: **standard** (default) removes distributed files and keeps settings +
 1. **Determine the scope**  -  parse `$ARGUMENTS`:
    - No target flag: all installed targets (default)
    - `--claude / --copilot`: selective
-   - `--all-data`: full cleanup (also removes settings + logs)
+   - `--all-data`: full cleanup (also removes settings, logs, per-repo memory and the knowledge base)
    - `--target=<path>`: adapter target (default cwd)
    - `--dry-run`: only report, delete nothing
 
 2. **Ask the cleanup depth** (skip if `--all-data` or `--dry-run` already given)  -  `AskUserQuestion` in `outputLanguage`:
    - `question`: "How much should uninstall remove? Tokens are preserved either way."
-   - `header`: "Scope" · `options`: `{ label: "Standard", description: "Remove pipeline files; keep settings + logs" }`, `{ label: "Full cleanup", description: "Also remove settings + all task logs/state/metrics" }`
+   - `header`: "Scope" · `options`: `{ label: "Standard", description: "Remove pipeline files; keep settings, logs, memory, knowledge" }`, `{ label: "Full cleanup", description: "Also remove settings, logs, per-repo memory and the knowledge base" }`
    - **Full cleanup** adds `--all-data`.
 
 3. **Show a preview** (run the script with `--dry-run`):

package/pipeline/skills/skills-index.md

@@ -3,7 +3,7 @@
 > Auto-generated by `pipeline/scripts/build-skills-index.mjs`  -  do not hand-edit.
 > Regenerate with `node pipeline/scripts/build-skills-index.mjs`.
 
-**210 skills** across 2 groups.
+**211 skills** across 2 groups.
 
 | Group | Name | Platform | Description |
 |-------|------|----------|-------------|
@@ -110,6 +110,7 @@
 | core | `multi-agent-feedback` |  -  | Send one message to the maintainer: a bug, an idea or a question. Only the text you type is sent - no logs, no repo names, no paths. Shows t |
 | core | `multi-agent-forget` |  -  | Remove a saved /multi-agent routine (created by /multi-agent:save): deletes its local-only command and its registry entry. Asks which one an |
 | core | `multi-agent-garbage-collect` |  -  | Sweep leftover /tmp scratch (picker state, review diffs, channel payloads, analysis drafts) from past runs. Dry-run first; confirms before d |
+| core | `multi-agent-graph` |  -  | Build and query this repo's code graph: a deterministic, LLM-free map of symbols, imports and references used to narrow Phase 1's Explore sc |
 | core | `multi-agent-help` |  -  | Multi-agent pipeline usage guide  -  renders in EN or TR per prefs.global.outputLanguage (falls back to promptLanguage for backward compatib |
 | core | `multi-agent-ios-coding-standard` |  -  | Audit an iOS module against the shared coding-standard registry (99 stable-ID rules), produce a remediation plan, then hand off to dev/dev-l |
 | core | `multi-agent-issue` |  -  | List unassigned GitHub issues, pick one, auto-assign, and launch the multi-agent pipeline. Use when a GitHub issue should be picked up and s |
@@ -126,7 +127,7 @@
 | core | `multi-agent-refactor` |  -  | Analyse the project: extract adapted best-practices, hunt real bugs + improvement areas, check upstream drift of derived skills, research th |
 | core | `multi-agent-resume` |  -  | Resume a stopped or failed task from the phase where it left off. Use when a task stopped or failed and should carry on from where it left o |
 | core | `multi-agent-resume-local` |  -  | Continue already-done LOCAL work through the pipeline tail: Review → Build+Test → Commit/PR → Report (technical analysis + Jira test-scenari |
-| core | `multi-agent-review` |  -  | Run parallel review on a branch diff or a Pull Request: 3 models on Claude Code (Fable + Opus + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonn |
+| core | `multi-agent-review` |  -  | Run parallel review on a branch diff or a Pull Request: 3 models on Claude Code (Fable + Opus + Sonnet), 3 models on Copilot CLI (GPT + Opus |
 | core | `multi-agent-review-analysis` |  -  | Review a written analysis document instead of a diff: resolve it from a path, a Confluence page or a Jira issue, run the deterministic gates |
 | core | `multi-agent-review-issue` |  -  | Assess whether a GitHub issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / sta |
 | core | `multi-agent-review-jira` |  -  | Assess whether a Jira issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / stack |
@@ -215,5 +216,5 @@
 | external | `xcode-build-benchmark` |  -  | Benchmark Xcode clean and incremental builds with repeatable inputs, timing summaries, and timestamped `.build-benchmark/` artifacts. Use wh |
 | external | `xcode-build-fixer` |  -  | Apply approved Xcode build optimization changes following best practices, then re-benchmark to verify improvement. Use when a developer has  |
 | external | `xcode-build-orchestrator` |  -  | Orchestrate Xcode build optimization by benchmarking first, running the specialist analysis skills, prioritizing findings, requesting explic |
-| external | `xcode-compilation-analyzer` |  -  | Analyze Swift and mixed-language compile hotspots using build timing summaries and Swift web diagnostics, then produce a recommend-firs |
+| external | `xcode-compilation-analyzer` |  -  | Analyze Swift and mixed-language compile hotspots using build timing summaries and Swift frontend diagnostics, then produce a recommend-firs |
 | external | `xcode-project-analyzer` |  -  | Audit Xcode project configuration, build settings, scheme behavior, and script phases to find build-time improvements with explicit approval |