Code, review, and ship9 commands

/yaw-implement

triggers: "implement the plan", "build this", "execute the plan"

Execute an agreed plan end to end - write code, run checks, confirm it works. Use after a plan is agreed, not for open-ended exploration.

/yaw-review

triggers: "review my changes", "any bugs in this", "spot bugs in recent changes"

Review the most recent changes for bugs, performance, and UX issues before committing or opening a PR. Returns a punch list with file:line, what's wrong, and a suggested fix.

/yaw-address-all

triggers: "address all of these", "fix everything", "work the list"

Implement every actionable item from the most recent enumerated list the agent surfaced - punch list, findings, TODOs, gaps - end to end without per-item confirmations.

/yaw-coverage

triggers: "what is untested", "find missing test cases", "what edge cases am I missing"

Find untested branches, edge cases, and failure paths in a module or feature. Returns a list of missing test cases with rationale - does not write tests unless asked.

/yaw-full-pass

triggers: "full pass over X", "review this whole module", before a release or after a big refactor

End-to-end sweep over a module, feature, or subsystem. Reads everything carefully, reports surprises as solid / fragile / worth fixing now / file for later.

/yaw-pre-pr

triggers: "ready to pr", "pr check", "is this ready for review"

Pre-PR audit: lint, typecheck, tests, plus a short diff-readiness pass. Auto-detects the project's commands from package.json. Outputs a PR-ready/blocked checklist with file:line for each blocker.

/yaw-ship-ready

triggers: "is this ready to ship", "ship-ready audit", "can I merge this"

Audit a branch or feature for shippability. Done / missing / blocked checklist covering golden path, error UI, loading states, empty states, destructive confirmations, and hygiene.

/yaw-commit-push

triggers: "commit and push", "stage commit push", "lint commit push"

Runs the pre-commit checklist (lint:fix, tsc, tests), stages the right files selectively, commits with a generated message, pushes to origin. For routine non-release commits - not a release flow.

/yaw-consolidate

triggers: "land my work", "consolidate this", "clean up these commits"

Land scattered or tangled work cleanly. Auto-detects the right git mechanics (solo vs fleet, protected vs unprotected base, work isolated vs tangled in a shared checkout) and prompts only on the genuine decisions.

Session, cost, and watching5 commands

/yaw-status

triggers: "what yaw mode am I in", "is the overlay active"

Report current Yaw state: mode (off / augment / fresh), model, effort tier, and how to change them.

/yaw-handoff

triggers: "snapshot this session", "save state for tomorrow", "handoff"

Snapshot the current session (cwd, branch, recent commits, files touched, pending tasks, open decisions, next step) to ~/.claude/handoffs/ and stdout, for resume in a fresh tab.

/yaw-throttle-status

triggers: "am I throttled", "are we rate limited", "should I switch tier"

Report the current backend (Anthropic-direct vs typed.cloud), model, effort tier, and whether the session is being rate-limited. Recommends tier drops per the throttle-recovery playbook when 429s fire.

/yaw-cost

triggers: "how much did this session cost", "token usage", "session cost breakdown"

Per-session token and dollar breakdown. Sums tokens by model, multiplies by published pricing, breaks out main vs sub-agents. On typed.cloud, reports tokens only.

/yaw-watch

triggers: "wait for it to finish", "watch this run", "babysit this deploy"

Poll-until-done for long-running operations: gh runs, kubectl rollouts, deploys, builds, log tails. Dispatches to the ci-watch agent for gh runs; polls native commands for the rest.

Memory and rules hygiene4 commands

/yaw-memory-prune

triggers: "prune my memories", "clean up memory", "garbage collect memory"

Find stale memory entries (broken refs, way-out-of-date versions, contradicted by recent commits) and propose deletions. Never auto-deletes.

/yaw-explainer

triggers: "explain rule X", "why does Y rule exist", "where did the Z rule come from"

Given a rule name or memory slug, explain what it means with concrete examples from recent git history - the WHY, not just the WHAT.

/yaw-friction-report

triggers: "what corrections did I make", "what should I add to my rules"

Scan recent session transcripts for friction signals (corrections, "actually", "no, not that", name disputes) and propose rule updates that would have prevented them.

Audits and bundle tuning5 commands

/yaw-session-audit

triggers: "is my yaw config healthy", "audit my session config", "what is stale"

Static-hygiene audit for Yaw Mode session state: stale memories, divergent configs, broken cross-references, orphaned skills/agents, settings drift. The companion to /yaw-tool-usage-audit.

/yaw-tool-usage-audit

triggers: "which MCPs am I skipping", "audit my tool usage", "run the tool routing audit"

Scan Claude Code transcripts to report which MCP servers earned their loadout vs were skipped via bash fallback. Computes per-server use rate over a time window.

/yaw-bundle-tune

triggers: "tune my bundle", "which mcps should I drop", "which mcps should I add"

Propose Yaw MCP bundle drops/adds from /yaw-tool-usage-audit data. Low use-rate servers are drop candidates; high bash-fallback counts are add candidates. Outputs a sample bundle config.

/yaw-skill-coverage

triggers: "what skills am I missing", "what should I automate", "what would benefit from a skill"

Scan recent transcripts to find repeated workflows that lack a skill (3+ occurrences, no existing match). Proposes new skill names and trigger phrases.

/yaw-mcp-route-nudge

triggers: "should I use an mcp for this", "is there an mcp for this", "is this a bash fallback"

Given a planned Bash command, check whether a loaded MCP server would do it better. Suggests the MCP equivalent if loaded, or the install package if not.

Scaffolding2 commands

/yaw-new-skill

triggers: "scaffold a skill", "create skill", "make a new skill"

Scaffolder for new Yaw skills. Asks 3 questions (name, purpose, trigger phrases), writes a properly-formatted SKILL.md under ~/.claude/skills/ with the standard frontmatter and section scaffold.

/yaw-new-agent

triggers: "scaffold an agent", "create subagent", "new agent"

Scaffolder for custom Claude Code subagents. Creates ~/.claude/agents/ if missing, asks 3 questions (name, purpose, tool restrictions), writes <name>.md with proper YAML frontmatter and a body scaffold.

These 25 skills are the runtime surface of Yaw Mode. For the rule files, safety hooks, sub-agents, and the overlay mechanism itself, see Claude Code Yaw Mode.