firstmate is an agent distribution that lets one coding agent coordinate a crew of autonomous agents working in separate git worktrees. It is for running parallel fixes, investigations, plans, and audits while receiving completed pull requests, merges, or reports through one supervising agent. The catalogue entries provide skills, hooks, instructions, and settings for operating this workflow.
Borrowing it
Nothing to install: this file belongs to kunchenguid/firstmate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kunchenguid/firstmate/main/.agents/skills/ship-landing/SKILL.mdgit clone --depth 1 https://github.com/kunchenguid/firstmateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kunchenguid/firstmate/ship-landing)<a href="https://agentmods.dev/skills/kunchenguid/firstmate/ship-landing"><img src="https://agentmods.dev/badge/skills/kunchenguid/firstmate/ship-landing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kunchenguid/firstmate/ship-landing"><img src="https://agentmods.dev/badge/skills/kunchenguid/firstmate/ship-landing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.00813 |
| Opus 5.5 | $0.00010 | $0.00325 |
| Sonnet 5.5 | $0.00005 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
ship-landing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Ship landing
For PR-based ship tasks, the ready signal depends on mode: no-mistakes reports done [at=<epoch>]: PR <url> checks green after CI is green, while direct-PR reports done [at=<epoch>]: PR <url> after opening the PR, each only for a non-draft PR; a lane that deliberately holds a draft declares a wait instead, and bin/fm-pr-check.sh refuses to arm merge monitoring on a draft.
Run bin/fm-pr-check.sh <id> <PR url> with the URL copied from that ready signal or the resolved checks-green fm-crew-state.sh line - it records pr= and the forge's pr_head= when available in the task's meta and arms the watcher's merge poll.
bin/fm-dod-lib.sh owns the named-head gate on that ready signal: a ship done: whose named head exists only in the worker's disposable copy is not ready (bin/fm-crew-state.sh reports blocked, bin/fm-pr-check.sh refuses to register, and a secondmate does not publish that done upstream).
That blocked reading is the gate working, not a stuck worker, so steer the worker on the commit the refusal names rather than waiting.
A forge=external task reports done [at=<epoch>]: review <url> uploaded for review instead: run bin/fm-review-check.sh <id> <review url> rather than bin/fm-pr-check.sh, which arms no merge watch, then always escalate the review URL to the captain whatever the yolo setting, because firstmate can neither observe nor perform its approval or merge.
A direct-PR worker pushes that commit to its PR branch, and a local-only worker commits it on its ship branch.
A no-mistakes worker re-validates it with /no-mistakes so the pipeline stays the one publisher; it never pushes from its copy.
In no-mistakes mode the earlier done [at=<epoch>]: {summary} is the pipeline handoff and is not gated.
Tell the captain the PR's full https://... URL copied from the worker's ready line, the resolved checks-green crew-state line, or the task's pr= metadata, a concise outcome summary, and the no-mistakes risk level when applicable.
A captain instruction to merge is explicit authority; yolo is the only standing routine merge authority.
For any custom state/<id>.check.sh you write yourself, keep it an ordinary single-link mode-0700 file, print one line only when firstmate should wake, print nothing otherwise, finish before FM_CHECK_TIMEOUT, then bind its current bytes with bin/fm-check-register.sh <id> before the watcher may execute it.
Retire a custom check only through bin/fm-check-unregister.sh <id> (or bin/fm-teardown.sh for a spawned task); never hand-compose an rm with $STATE/$ID.
Tear down a ship task only after landing is confirmed. A teardown refusal for uncommitted or unlanded work is a stop-and-investigate result, never an obstacle to bypass. Never force teardown without explicit discard authority. After successful teardown, record completion, retain only the configured recent Done history, and re-evaluate queued work whose blockers and time gates have cleared.
A secondmate is persistent and an empty queue is healthy.
Retire one only on an explicit captain or main-firstmate decision, after loading secondmate-provisioning; its home must contain no work under way, and forced discard still requires explicit captain authority.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago Changed · +1 lines ad929780d4b6
- 27d ago First seen · 30 lines · 26 tokens per session scan A 98b690e5c6d5
ship-landing is a skill published in the GitHub repository kunchenguid/firstmate (8,295 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 813 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-28.
Other skills, from other repositories
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
otto-drive-pr
PR mergeability, CI, and live preview.
voicestudio-maintainer
Triage GitHub issues, review contributor pull requests, diagnose CI, and prepare explicitly requested releases for VoiceStudio's Electron desktop app and Python backend. Use for repository maintenance work, not ordinary VoiceStudio audio generation.
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…