kunchenguid

Agent-only reference for firstmate harness operations. Use before spawning or recovering a crewmate or secondmate, handling a trust dialog, sending a harness-specific skill invocation, interrupting or exiting an agent, resuming an exited agent, or verifying a…

Agent-only playbook for stuck or missing ordinary Firstmate direct reports. Use when the session-start digest reports an ordinary direct report's endpoint dead or its metadata has no window, or after a stale wake, looping pane, repeated confusion, an…

Enter the away posture when the captain invokes /afk, says they are going afk, `state/.afk-contract` or `state/.afk` exists, an incoming message starts with `FM_INJECT_MARK`, or any `state/.subsuper-*` marker is involved. It writes the durable away-posture…

Generate a "pick up where I left off" fleet digest from firstmate's live fleet state. Use when the captain invokes /bearings or asks for a bearings report, morning brief, status report, catch-up, "where did I leave off", or "what's in the works". Plain…

Sweep the current session for uncaptured durable knowledge, file it to disk, persist the open work records this session knows are unfiled or now wrong, and curate the home's tiered, decaying startup memory before a context reset. Use when the captain invokes…

Agent-only reference for changing firstmate's shared, tracked material per AGENTS.md section 1. Use before editing any of that material, whether working as firstmate directly or as a crewmate briefed on a firstmate-repo task. Covers the knowledge-placement…

The firstmate-repository publication boundary. Load before dispatching, promoting, relaunching, or delivering any task whose project is the firstmate repository itself, when a firstmate bug or improvement idea surfaces in ordinary use, before granting or…

Load when locating, interpreting, or changing Firstmate home, config, data, state, project, or generated runtime paths.

Use when changing PR body rendering, home-path redaction, artifact path publication, pipeline-attestation markers, or pre-push attestation.

Use when changing recursive gate containment, run worktree placement, bare-gate Git calls, GitHub PR targeting, or post-receive hooks.

Use when changing review sessions, finding decisions, the review fix-round carry, review schema retries, agent timeouts, local Test behavior and its live-validation contract, approval overrides and parked gates, or intent conformance.

Use when changing daemon startup, singleton ownership, shutdown, logging, event subscriptions, lifecycle commands, or the daemon's login-shell environment.

Use when changing CI readiness, forge check collection, reruns, CI timeouts, CI step findings and fix rounds, or PR lifecycle monitoring.

Validate your code changes through the no-mistakes pipeline - automated code review, tests, lint, docs, push, PR, and CI - before they reach the configured push target. Use when the user asks to run no-mistakes, gate or ship or validate their changes, push…

Use when changing local branch synchronization, custody recovery, post-review head binding, rebasing or rebase.strategy, private-mirror reconciliation, or force-push safety.

Use when changing test evidence collection, publication, paths, retention, or scratch-directory cleanup.

Use to close contributor PRs that have been waiting on the author for stale-days with no author push, comment, or review. Parameterized owner, disclosure line, and stale days. Firstmate-mark and bot comments do not reset the clock.

Use at Grok Ship intake and whenever work is handed to a crewmate.

Use at the start of every triage wake. Run fetch.py with the charter flags and work only the returned issue and PR numbers, in order.

Use before any final triage decision when the repo has a VISION.md. Read it in full. Per-rule aligns / does not align / cannot tell, with evidence. Claims are not enough. Cannot-tell / inconclusive / undecided is no verdict and blocks auto-merge.

Use when the captain explicitly says ahoy or /ahoy, or asks for a session recap of what happened since they last spoke, plus any visibly unanswered decisions. A standalone captain message whose main ask is "ahoy" is an invocation. History-only. Do not gather…

Use after a ship cloud agent pushes a branch, before any pull request.

Turn complex or visual agent responses into rich, reviewable HTML artifacts the user can annotate and send feedback on, using the lavish-axi CLI. Use when about to give a plan, comparison, diagram, table, code diff, report, or anything easier to grasp…

Provider-specific auth sources, quota windows, endpoint shapes, error recovery, and quirks for the quota-axi providers with dedicated sections below; Muse is covered in the README provider notes.

Cache storage locations, permissions, context scoping, isolation rules, and lifecycle management in quota-axi.

Rules, checklist, credential selection machinery, multi-source handover, delegated refresh contract, and test discipline for onboarding new quota providers or modifying existing provider adapters in quota-axi.

Report local Claude, Codex, Cursor, GitHub Copilot, Grok, Kimi, Z.AI, Alibaba, OpenCode Go, Antigravity, Command Code, MiniMax, MiMo, DeepSeek, OpenRouter, ElevenLabs, Devin, Muse, and Higgsfield quota windows via the quota-axi CLI - remaining effective…

Rules and algorithms for quota interpretation, pace calculation, runway derivation, selection signals, and output tier rendering (TOON, JSON, TUI) in quota-axi.

Release automation, CI workflows, release-please configuration, contribution gate, and lockfile formatting in quota-axi.

Use when implementing any feature or bugfix, before writing implementation code

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a…

Code quality dashboard. Wraps existing project tools (type checker, linter, test runner, dead code detector, shell linter), computes a weighted composite 0-10 score, and tracks trends over time. Use when: "health check", "code quality", "how healthy is the…

Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root…

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture",…

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff".…

Read or change compact-adviser settings for Codex - the mode (hint or off), the minimum context before a checkpoint is judged, the context budget, TypeSafe request logging, and the TypeSafe API key. Use when the user asks about compaction advice, the /compact…

Use when modifying or testing `packages/codex-plugin` or Codex `/compact` behavior.

Use when changing or evaluating judge prompts, scoring thresholds, usage floors, or judgment eval corpora.

Turn complex or visual agent responses into rich, reviewable HTML artifacts (HTML files) the user can annotate and send feedback on, using the lavish-axi CLI. Use when about to give a plan, comparison, diagram, table, code diff, report, or anything easier to…

Use this skill to generate well-branded interfaces and assets for Lavish, either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.

Turn a long-form video transcript into ranked, captioned vertical shorts. Use when proposing soundbite candidates, following the user's target-length setting, deciding whether to override the user's layout/theme/caption defaults, and selecting keywords to…

Use this skill to generate well-branded interfaces and assets for Short Pipe, either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.

Use when the user asks to run GNHF, says they are going to sleep or leaving and wants an agent-managed coding run, asks to supervise, steer, or review an active GNHF run, or gives feedback on GNHF results.

Agent eXperience Interface (AXI) — ergonomic standards for building CLI tools that agents use via shell execution. Use when building, modifying, or reviewing any agent-facing CLI.

Control a Chrome browser session through the chrome-devtools-axi CLI - navigate, snapshot, click, fill forms, run JavaScript, inspect console and network, take screenshots, audit performance. Use whenever a task needs a real browser: opening or testing a web…

Summon Kun to solve your problems. Use on /kun or when asked how Kun thinks, builds, or solves problems.