AI-Rig

Adapter over `codemap-py integrate` — audit, plan, source-wire, locally sync, and demonstrate the codemap-py integration with its supported consumers. Trigger with `/codemap-py:integration check|plan|apply|sync|demo [--runtime {claude,codex,both}] ...`. Default (no args) is `check`. Skip for: running a structural query (use `/codemap-py:query-code`); explicit standalone index rebuild (use `/codemap-py:scan-codebase`).

Scan the Python codebase and build a structural JSON index (import graph + blast-radius metrics). TRIGGER when: user asks to build, refresh, or rebuild the codemap index; user mentions stale index, missing symbols, or re-indexing after significant project changes; phrases: "build codemap", "scan codebase", "refresh structural index", "rebuild import graph".

Read local codemap telemetry logs and produce a diagnostic/usage report. Supports date filtering, session filtering, and optional anonymization before sharing. Trigger with `$codemap-py:debrief-coding [--since <YYYY-MM-DD>] [--session <id>] [--anonymize] [--output <path>]` to analyse recent codemap usage, debug query patterns, investigate errors, or prepare a shareable anonymized report of how codemap skills and the CLI are being used.

Adapter over `codemap-py integrate` — audit, plan, source-wire, locally sync, and demonstrate the codemap-py integration with its supported consumers. Trigger with `$codemap-py:integration check|plan|apply|sync|demo [--runtime {claude,codex,both}] ...`. Default (no args) is `check`. Skip for: running a structural query (use `$codemap-py:query-code`); explicit standalone index rebuild (use `$codemap-py:scan-codebase`).

Query the codemap structural index — module deps/rdeps/central/coupled/path, symbol-level source extraction, function call graph (fn-deps, fn-rdeps, fn-central, fn-blast), plus quality/coverage queries. Trigger with `$codemap-py:query-code <subcommand> ...` for: "what depends on", "who calls", "imports of", "dependency graph", "blast radius of", "list central modules". Skip for: rename intent (use `$codemap-py:rename-refs`); simple grep suffices; non-Python repo. Missing/stale index auto-builds — no manual scan-codebase needed.

Atomic rename of Python symbols or modules via the structural index — static callers, import sites, `__all__` re-exports, Sphinx cross-refs; optional deprecated alias (`--deprecate`) or hard-delete (`--remove-if-no-callers`). Trigger with `$codemap-py:rename-refs symbol <old> <new> [flags]` or `$codemap-py:rename-refs module <old_path> <new_path> [--dry-run]` for: "rename X to Y" (function/class/method/ module), "move module X to Y", "update all references to X". Skip for: non-Python; index not built (run `$codemap-py:scan-codebase` first); local-variable rename; grep-only rename wanted; 1:N symbol splits; package directory rename (use `git mv` directly).

Scan the Python codebase and build a structural JSON index (import graph + blast-radius metrics + symbol table). Explicit invocation only via `$codemap-py:scan-codebase [--root <path>] [--incremental]` — never auto-trigger this from conversation reasoning. Use when the index is missing, stale, or after significant project changes.

Identify which tests need rerunning after a code change — traces static call graph (function-level) or import graph (module-level) to find affected test files, then emits a ready-to-run pytest command. Trigger with `$codemap-py:test-impact <module::symbol | module> [--no-mocks]` for: "which tests are affected", "what tests cover this", "test impact of", "what tests to rerun".

Full-sweep quality audit of .claude/ config — cross-references, permissions, inventory drift, model tiers, docs freshness. Scope tokens select what to audit; --upgrade applies docs-sourced improvements; --adversarial runs foundry:challenger + Codex adversarial review; --efficiency sweeps model tiers, token bloat, spawn patterns, boilerplate duplication, and bin/ extraction candidates (extraction performed separately via /distill executables). Fix level chosen via always-fire follow-up gate after report.

Read local codemap telemetry logs and produce a diagnostic/usage report. Supports date filtering, session filtering, and optional anonymization before sharing. TRIGGER when: analyse recent codemap usage, debug query patterns, investigate errors, or prepare a shareable anonymized report of how codemap skills and CLI are being used.

Query the codemap structural index — module deps/rdeps/central/coupled/path, symbol-level source extraction, function call graph (fn-deps, fn-rdeps, fn-central, fn-blast). TRIGGER: "what depends on", "who calls", "imports of", "dependency graph", "blast radius of", "list central modules". SKIP: rename intent (use /codemap-py:rename-refs); simple grep suffices; non-Python repo. Missing/stale index auto-builds — no manual scan-codebase needed.

Atomic rename of Python symbols or modules via the structural index — static callers, import sites, __all__ re-exports, Sphinx cross-refs; optional deprecated alias (--deprecate) or hard-delete (--remove-if-no-callers). TRIGGER: "rename X to Y" (function/class/method/module), "move module X to Y", "update all references to X". SKIP: non-Python; index not built (/codemap-py:scan-codebase first); local-variable rename; grep-only rename wanted; 1:N symbol splits; package directory rename (git mv).

Identify which tests need rerunning after a code change — traces static call graph (function-level) or import graph (module-level) to find affected test files, then emits a ready-to-run pytest command. TRIGGER when: user asks which tests are affected by a change; phrases: "which tests are affected", "what tests cover this", "test impact of", "what tests to rerun".

Investigation-first debugging — gather evidence, form confirmed root-cause hypothesis, hand off to fix mode with diagnosis file. TRIGGER when: user reports a symptom or failing test with Python traceback, or asks to investigate a runtime/CI failure with reproducible evidence; phrases: "debug this failure", "why is X broken", "find the root cause of <error>", "investigate this CI failure". SKIP when: pure config quality issues (use `/foundry:audit`); broad system-wide diagnosis without traceback (use `/foundry:investigate`); user already knows the fix (use `/develop:fix`); non-Python project.

TDD-first feature development — crystallise API as a demo test, drive implementation to pass it, run quality stack and progressive review loop. TRIGGER when: user asks to build new functionality, add a capability, or implement a feature in a Python project; phrases: "add X", "implement Y", "build Z feature", "create a new module for". SKIP when: bug fixes (use `/develop:fix`); refactoring without new behaviour (use `/develop:refactor`); non-Python projects; `.claude/` config changes (use `/foundry:manage`).

Reproduce-first bug resolution — capture bug in failing regression test, apply minimal fix, run quality stack and review loop. TRIGGER when: user reports a bug, regression, or unexpected behaviour in Python code with a traceback, failing test, or issue number; phrases: "fix this bug", "repair X", "broken since Y", "test failing". SKIP when: CI-only failures without local traceback (use `/develop:debug` first); new features (use `/develop:feature`); `.claude/` config issues (use `/foundry:audit`); non-Python projects.

Analysis-only planning — classify and scope a task without writing code; outputs a structured plan to .plans/active/. TRIGGER when: user wants to understand scope and risks before implementation; phrases: "plan this", "scope out X", "what would it take to Y", "analyse before we start". SKIP when: user already knows what to build and wants code immediately (use `/develop:feature` or `/develop:fix` directly); `.claude/` config planning (use `/foundry:manage`).

Test-first refactoring — audit coverage, add characterization tests, apply changes with safety net, run quality stack and review loop. TRIGGER when: user wants to restructure existing Python code without changing behaviour; phrases: "refactor X", "clean up Y", "extract Z", "restructure this module", "improve code quality". SKIP when: bug fixes (use `/develop:fix`); new features (use `/develop:feature`); mixed refactor+feature — run `/develop:refactor` first, then `/develop:feature`; non-Python projects.

Multi-agent code review of local Python files, directories, or the current git diff covering architecture, tests, performance, docs, lint, security, and API design. Scope: Python source files in local working tree. Python-file-free targets (pure JS/TS/Go/Rust projects) are out of scope.

Iterative brainstorming skill for turning fuzzy ideas into approved tree documents. Diverges into branches, deepens and prunes them over many rounds, saves a tree doc. Run breakdown on the tree to distill it into a spec via guided questions.

Calibration testing for agents and skills. Generates synthetic problems with known outcomes (quasi-ground-truth), runs targets against them, measures recall, precision, confidence calibration — reveals whether self-reported confidence scores track actual quality.

One-time snapshot extracting patterns from work history and accumulated lessons, distills into concrete improvements — new agent/skill suggestions, memory pruning, consolidating lessons into rules/agent updates, or performing bin/ extraction from /audit --efficiency candidates. Roster boundary analysis → /foundry:audit agents (Check 34).

Systematic diagnosis for unknown failures — local environment, tool setup, CI vs local divergence, hook misbehavior, and runtime anomalies. Gathers signals broadly, ranks hypotheses, uses adversarial review (Codex or foundry:challenger) for ambiguous cases, probes each, and reports root cause with a recommended next action. NOT for known code bugs (/develop:debug (requires `develop` plugin)) or config quality (/foundry:audit). TRIGGER when: unknown failure with no Python traceback — hook not firing, CI passes locally but fails remotely, background agent stalled, behavior inconsistent with config; phrases: "not working but config looks right", "hook not triggering", "why isn't X running". SKIP: Python traceback present (use develop:debug (requires `develop` plugin)); known code bug with repro (use develop:fix (requires `develop` plugin)); pure config quality check (use foundry:audit).

Create, update, or delete agents, skills, rules, and hooks with full cross-reference propagation. Trivial edits (typos, small fixes ≤10 words) applied inline without agent; `.md` content-edits delegated to foundry:curator; code file edits (`.js`, `.py`, `.ts`) delegated to foundry:sw-engineer; large cross-ref fan-outs (> 3 files) also delegate. The parent orchestrates MEMORY.md, README, audit, calibration, and the final report. Also manages settings.json permissions atomically with permissions-guide.md. NOT for: validation/quality audit of existing agents/skills (use /foundry:audit); implementing application source code changes outside `.claude/` (use develop:feature or develop:fix — requires `develop` plugin).

Post-install setup for foundry plugin. Run once after installing on a new machine, or after a plugin version upgrade to sync settings and symlinks. Merges statusLine, permissions.allow, enabledPlugins, and advisorModel into ~/.claude/settings.json; symlinks rules, TEAM_PROTOCOL.md, and skills into ~/.claude/.

Analyze GitHub issues, Pull Requests (PRs), Discussions, and repo vitality for an Open Source Software (OSS) project. For any specific item, casts a wide net — finds and lists all related open and closed issues/PRs/discussions, explicitly flags duplicates. Summarizes long threads, extracts reproduction steps, and generates repo vitality stats. Uses gh Command Line Interface (CLI) for GitHub Application Programming Interface (API) access. Complements oss:shepherd (requires `oss` plugin). NOT for PR readiness assessment or code review (use oss:review). TRIGGER when: user provides GitHub issue number (#N), PR number, or github.com URL with issue/PR/discussion path AND asks to analyze, summarize, understand, or triage it; user asks for repo vitality stats or "is this repo healthy". SKIP: user already pasted full thread text inline; oss:resolve already active on same PR; user wants code review (use oss:review); user phrasing is "review PR" meaning code quality assessment, not thread triage (route to oss:review).

Prepare release communication and check readiness. Main mode: notes with optional flags --changelog, --summary, --migration; range as v1->v2. Other modes: prepare (full pipeline: audit → all artifacts), audit (pre-release readiness: blockers, docs alignment, version consistency, CVEs), demo (story-telling release notebook in jupytext # %% format). TRIGGER when: user requests release notes, CHANGELOG entry, migration guide, internal summary, release readiness audit, or release demo; phrases: 'draft release notes', 'prepare release', 'audit release readiness', 'generate CHANGELOG for v1->v2', 'release demo notebook'. SKIP: actual git tagging or PyPI/registry upload (use git tag, gh release create, twine upload directly); release communication for a non-Python project where this skill's pytest-centric audit assumptions do not apply; PR-level review (use /oss:review); thread/issue analysis (use /oss:analyse).

OSS maintainer fast-close workflow for GitHub PRs. Three phases: (1) PR intelligence — reads full thread, linked issues, PR body to synthesize contribution motivation and classify every comment into action items; (2) conflict resolution — checks out PR branch (fork-aware via gh pr checkout), merges BASE into it, resolves conflicts semantically using contributor's intent as priority lens; (3) implements each action item as separate attributed commit via Codex, pushes back to contributor's fork. Supports three source modes: pr (live GitHub comments only), report (latest /review report findings as action items, no GitHub re-fetch), and pr + report (both sources aggregated and deduplicated in one pass). Also accepts bare comment text for single-comment dispatch. NOT for reply drafting to /oss:analyse findings (use /oss:analyse --reply (requires `oss` plugin)). NOT for code diff review of PR changes (use /oss:review). NOT for release preparation (use /oss:release). NOT for fixing local bugs unrelated to a PR (use

Multi-agent code review of GitHub Pull Requests (Python source, documentation (Markdown/RST), and CI/CD config PRs) covering architecture, tests, performance, docs, lint, security, and API design. TRIGGER when: user provides a GitHub PR number (e.g. 42, #42) and asks to review/audit/check it, or provides a saved review-report path with --reply to draft a contributor-facing comment; phrases: 'review PR 123', 'audit this pull request', 'look at PR #42', 'draft a reply for this review report'. SKIP: local file or current git diff review (use /develop:review (requires 'develop' plugin)); non-Python source PRs without Python files (TypeScript-only, Go-only, Rust-only); standalone issue/discussion thread analysis (use /oss:analyse).

Systematic ablation study runner. After research:run finds improvements, fortify identifies component candidates from git diff + diary, creates isolated git worktrees per ablation (main repo never modified), runs metric+guard in each worktree, ranks component importance, and optionally generates reviewer Q&A calibrated to a target venue.

Research-supervisor review of program.md — validates experimental methodology (hypothesis clarity, measurement validity, control adequacy, scope, strategy fit), emits APPROVED / NEEDS-REVISION / BLOCKED verdict before expensive run loop.

Generate a Kaggle competition notebook as a Jupytext `# %%` Python script following the user's established ML research style: PTL for DNN training, best-fit tool selection, EDA→Baseline→Train→Inference pipeline with per-stage lens cells, small single-purpose cells each carrying a why. Tuned to win (leakage-safe CV, metric-aligned modeling) as much as to teach. Writes output to .experiments/kaggle/<name>.py.

Post-run retrospective: reads .experiments/ JSONL, computes Wilcoxon significance, detects dead iterations, flags suspicious jumps, generates next-hypothesis queue for --hypothesis flag.

Sustained metric-improvement loop with atomic commits, auto-rollback, and experiment logging. Iterates with specialist agents, commits atomically, auto-rolls back on regression. Accepts a program.md file path. Supports --resume, --team, --colab, --codex, --researcher, --architect, --journal, --hypothesis.

Non-interactive end-to-end pipeline — auto-configure program.md (accept defaults), run judge+refine loop (up to 3 iterations), then run the campaign. Single command from goal to result.

Research State of the Art (SOTA) literature for an Artificial Intelligence / Machine Learning (AI/ML) topic, method, or architecture. Finds relevant papers, builds a comparison table, recommends the best implementation strategy for the current codebase, and optionally produces a phased implementation plan mapped to the codebase. Owns broad SOTA search end-to-end via foundry:web-explorer; delegates codebase mapping to foundry:solution-architect.

Paper-vs-code consistency audit. After research:scientist implements a method from a paper, verify the implementation matches paper claims across five dimensions — formula matching [F], hyperparameter parity [H], eval protocol [E], notation consistency [N], and citation chain [C]. Reads paper (PDF path / arXiv URL / pasted text), maps claims to codebase, emits verification table with match status and severity.

Minimal codex-native analysis loop. Use for issue/PR/problem analysis before implementation with measurable gates.

Minimal codex-native audit loop. Use to scan codex configuration/workflow drift and emit ranked gaps with measurable gates.

Codex-native code-remediation loop: triage/apply code-review findings, rerun checks, publish unresolved gaps with measurable gates; `$code-remediate #123 +review` remediates a PR from latest matching code-review artifact.