Use when preparing releases with versioning, changelog, artifacts, smoke tests, tags, and go/no-go. Triggers:
Use when auditing codebase risks with evidence and prioritized remediation. Triggers:
Produce reusable technical architecture documents from codebase exploration. Use when onboarding, "write up what this does", architecture docs, or handoff.
Use when finding and fixing deadlocks with lock ordering, reproduction, timeouts, or lock-free alternatives. Triggers:
Use when migrating an issue tracker workspace from bd to br with loss-free verification. Triggers:
Coding Agent Session Search - unified CLI/TUI to index and search local coding agent history from Claude Code, Codex, Gemini, Cursor, Aider, ChatGPT, Pi-Agent, Factory, and more.
Use when dispatching scoped Claude Code subagents with worktrees, roles, tools, memory, and evidence gates. Triggers:
Use when auditing closed beads for real shipped evidence, acceptance proof, and truthful closeout. Triggers:
Collect GitHub PR data and generate work reports. Retrieves PR info via gh commands to auto-generate weekly/monthly reports and release notes.
Use when rationalizing file or directory layout and updating references without breaking builds. Triggers:
Use when cleaning repository branches, worktrees, gc state, large objects, and exclusion rules safely. Triggers:
Use when restoring machine responsiveness from high CPU, memory, IO, cache, or runaway process pressure.
Use when Codex needs Fable approval through an ATM/NTM validator pane. Triggers: - codex approval - ask fable - fable plan review
Use when auditing Rust UB risks in unsafe, FFI, raw pointers, layout, or concurrency. Triggers:
Install or run the seven-move operating-loop Workflow for AgentOps plugin users and multi-agent orchestration.
Run a recurring AgentOps loop tick on AGY via an Antigravity sidecar (the schedule builtin + agentapi), capturing per-fire agentapi runtime evidence a validator can read back.
Run the skill-factory final trust gate: operate trust-gate.sh, read skill.trust.json, and enforce --require-cross.
Dispatch unbiased parallel refuters (Fable + Codex, read-only) before landing a large multi-surface change.
Research software tools via source code, GitHub, web. Use when creating skills, learning new tools, finding undocumented features, or bleeding-edge patterns.
Execute development tasks using OpenAI Codex CLI for code generation, refactoring, feature implementation, and bug fixes.
Use when turning tacit expert know-how into a durable skill, playbook, or checklist. Triggers:
Configure Claude Code hooks for PreToolUse, PostToolUse, Stop, Notification. Use when blocking commands, auto-formatting, custom permissions, or writing hooks.
Use when designing Rust CLIs backed by SQLite with migrations, transactions, tests, and data safety. Triggers:
Systematically explore unfamiliar codebases to build working mental models. Use when onboarding to new project, "what does this do", or understanding legacy code.
GitHub issue/PR triage via ru and gh. Use when processing issues, closing PRs (no-contributions policy), or bulk triage. Independent verification required.
Audits and validates skill definitions for quality, completeness, and best practices. Use when reviewing existing skills for proper formatting, evaluating if skills should be…
Use when debugging native programs or ELF binaries with gdb breakpoints, backtraces, and memory inspection. Triggers:
Mid-epic strategic drift audit: code is ground truth, README/PRODUCT.md/plan docs are the measuring stick; emit a cited gap report and a routing decision.
Use when designing fuzz, property, randomized, or corpus-based tests and replaying failures. Triggers:
Use when comparing a project vision to code reality and turning gaps into tracked work. Triggers:
Use when using ru for multi-repo commits, sync, GitHub review, or maintenance automation.
Mine patterns that recur across multiple projects and generalize into reusable artifacts. Use when "I've seen this before", DRY across repos, or building shared libraries.
Local-first issue tracker (beads_rust) for AI agents. Use when tracking tasks, managing dependencies, finding ready work, or syncing issues to git via JSONL.
Graph-aware task triage with bv and br. Use when prioritizing work, finding bottlenecks, tracking dependencies, or managing local issues across projects.
Prepare pull requests by running quality gates, drafting descriptions, and validating tests before submission.
Map your goal to a multi-skill workflow -- suggests Combo chains, generates custom pipelines, and explains each step
Use when optimizing a hot path from saved profiles, measurements, and verified improvements. Triggers:
Run AGY headlessly via scheduled ticks or `agy -p`, capture agentapi JSONL evidence, and validate automated AGY loops or event streams.
Grade agent or model output against Outcomes for holdout-safe evals and runtime comparisons.
Use when designing MCP servers with clear tools, strict schemas, scoped resources, and useful errors. Triggers:
Use ATM as the out-of-session substrate: spawn Claude/Codex panes running /rpi and /evolve over a bead queue, then tend the swarm to convergence.
Converting markdown plans into beads (tasks with dependencies) and polishing them until they're implementation-ready. The bridge between planning and agent swarm execution.
Cross-validate decisions using multiple AI models (Codex, Gemini, Grok). Use when "get a second opinion", evaluating approaches, or high-stakes decisions.
Use when searching code with rg using precise, fast flags instead of slow grep or find patterns. Triggers:
Use when building real-service end-to-end tests with fixtures, cleanup, rate limits, and evidence. Triggers:
Wire MCP servers and AgentOps plugin bundles into the AGY image with least-privilege access, rollback evidence, and validation hooks.
Fully autonomous epic execution. Runs until ALL children are CLOSED. Loops through beads issues, runs /implement on each, validates with /vibe. NO human prompts, NO stopping.
Use when designing or auditing CLI doctor commands, health checks, repair hints, and diagnostic UX. Triggers:
Use when creating GitHub Actions workflows, release automation, checksums, signing, or CI/CD.
Use when adding fast lexical or semantic code search to a Rust project with an ergonomic query API. Triggers:
Use when turning repeated manual operations into safer, observable, reusable automation loops. Triggers:
Use when operating ACFS flywheel health checks, init, and agent loop tooling from ~/acfs/bin/acfs. Triggers:
Consolidate fragmented agent-memory layers into one bd-canonical store, then GC/retire the rest. Triggers: "memory migration", "consolidate agent memory", "beads-first memory".
Use when finding mocks, stubs, fake paths, or placeholders leaking into production code. Triggers:
Use when operating an NTM review or analysis worker with bounded inputs and evidence-backed output. Triggers:
Use when producing a shareable architecture, module, metrics, and health report for a codebase. Triggers:
Alias for $council --mode=debate (adversarial named-persona debate).
A test fixture that intentionally fails Pass-2 checks.
Test fixture skill that satisfies all 15 auditor checks (Pass 1 + Pass 2).
Vibe — reads your session and picks the perfect genre