kunchenguid/firstmatePublic

You can run one coding agent easily. But the moment you want three project tasks done in parallel - fixes, investigations, plans, audits - you become a tab-juggler: babysitting sessions, copy-pasting context between repos, forgetting which terminal had the failing test.

firstmate flips the model. You talk to a single agent - the first mate - and it runs the crew for you: spawning autonomous agents in a visible session backend, giving each a clean git worktree, supervising them to completion, and handing you finished PRs, approved local merges, or standalone investigation reports. For larger fleets, you can opt in to persistent secondmates: second mates that are still ordinary direct reports, but run from their own isolated firstmate homes on this machine or another SSH-reachable host.

firstmate is not a model, not a harness, not a skill, not an MCP server, and not a CLI. firstmate is an agent distro for running a crew of agents. An agent distro is a portable directory of instructions, skills, tooling, policies, and state conventions that turns a general-purpose agent into a specialized one. There is no app to install: the cloned repo is the distro - AGENTS.md, bundled firstmate skills, and helper scripts that any terminal coding agent can follow. Launching a supported harness inside it for your primary session instantiates your first mate - and makes you the captain.

• One liaison - you talk only to the first mate; it dispatches, supervises, escalates only real decisions, and reports plain outcomes.
• A visible crew - every crewmate works in its own tmux window or Herdr tab, or in an experimental Zellij tab, experimental cmux workspace, experimental Tern block, experimental Orca terminal, or experimental T3 Code thread you can watch or interact with; the first mate reconciles.
• Disposable worktrees - each task runs in a clean treehouse git worktree, or an Orca-managed worktree when backend=orca, so parallel work on one repo never collides.
• Two task shapes - ship tasks deliver authorized changes; scout tasks leave standalone investigation reports when the intake contract warrants separate research.
• Explicit project modes - each project ships via no-mistakes, direct-PR, or local-only, with an optional +yolo merge-autonomy flag, an optional branch=<prefix> override for the default fm/ ship-branch prefix, and an optional forge=gerrit binding under which the worker publishes a Gerrit change instead of opening a pull request.
• Self-repo boundary - a home runs as firstmate user/operator by default, so a firstmate bug is diagnosed and patched locally but never pushed, PRed, issued, commented, or forked upstream on its own; publishing to firstmate's own repository needs the config/firstmate-role maintainer opt-in or a per-task captain consent (schema).
• Optional secondmates - opt in to persistent second mates that run from isolated firstmate homes with their own FM_HOME, state, projects, and session lock, either locally or as a whole home on an SSH-reachable host, with guarded updates and recovery that never turns an unavailable remote route into a local replacement.
• Event-driven, zero-token supervision - a bash watcher sleeps on the fleet and wakes the first mate only when something needs you; verified primary harnesses also get a turn-end backstop that blocks or follows up on a blind stop when work is under way and supervision is not live.
• Optional Relay - opt in with one local .env pairing token so firstmate can answer your public mentions on X and Discord alike, act on normal reversible mention requests through the same lifecycle as chat requests, acknowledge spawned work, and post up to three public-safe completion follow-ups within seven days for genuine milestones and the final outcome without changing non-Relay behavior; a final reply promised in a thread becomes durable state that is reconciled from disk, so a restart or a compacted conversation cannot lose it; dry-run preview records would-be replies and dismissals locally before go-live.
• Strict project boundary - the first mate is read-only over your projects except for the narrow guarded and captain-approved operations authorized by hard rule 1, including fleet sync's guarded safe branch pruning; crewmates make every other project change behind the configured merge authority.
• Restart-proof - all state lives on disk and in the active session backend (tmux by hard default, herdr, rex, or cmux when selected or auto-detected, zellij/orca/paseo/t3code/tern when explicitly selected); the next session reconciles after a restart, while ordinary supervision recovers confirmed-dead secondmate agents without waiting for one.

Full detail on every feature lives in docs/architecture.md.

• A verified primary agent harness: Claude Code, Grok, Pi, pi-signed, Oh My Pi (omp), Codex, OpenCode, or Cursor Agent CLI.
• Git and the GitHub CLI, authenticated through gh auth login.
• The CLI and dependencies for your selected runtime backend; tmux is the reference default.

The first mate detects supported missing or outdated tools and offers their install or upgrade after you approve. Backend-specific setup is linked in Documentation.

Claude Code, Grok, and Pi are equal co-primary recommendations for running the primary firstmate session, with pi-signed supported as Pi's distinct signed-wrapper identity. Claude Code uses a tracked Stop hook for tokenless watcher re-arm and rewake, Grok uses background-notify wake cycles, and Pi uses its tracked primary watcher extension. All three have verified turn-end guard paths when launched with their documented setup. Pick whichever one matches your subscription and workflow.

Oh My Pi (omp), a Pi fork, is verified as a primary with the same extension-owned watcher model as Pi and a stronger turn-end guard: its blocking session_stop hook compels a continuation instead of requesting one. Codex and OpenCode are also verified and supported as primary harnesses; Codex uses bounded foreground checkpoints, and OpenCode uses a TUI plugin, so both carry more harness-specific supervision tradeoffs than the three co-primaries. Cursor Agent CLI is verified as a primary too, using a tracked project-scope .cursor/hooks.json whose stop hook parks on the watcher between turns, closest in shape to Claude Code's. Launch it with --trust, or none of its project hooks load; it also has no turn-end hook in headless cursor-agent -p, so run the primary session interactively.

gh auth login
git clone https://github.com/kunchenguid/firstmate
cd firstmate

Then launch one of the co-primary harnesses; AGENTS.md takes over from there:

Claude Code

claude

Grok

grok --trust

Pi

pi
# or, when the signed wrapper is installed
FM_PI_HARNESS=pi-signed pi-signed

Oh My Pi

omp
# or, when starting from inside a Claude Code pane
FM_OMP_HARNESS=omp omp

Start omp with this checkout as its working directory: it auto-discovers the tracked .omp/extensions/*.ts files with no trust dialog, and naming them with -e as well would load each twice.

For Grok, --trust is needed once per clone so project hooks and the turn-end guard load; /hooks-trust inside Grok works too. For Pi, approve the project trust prompt once per clone on first launch so the tracked .pi/extensions/*.ts files auto-load. The /calm toggle on Pi, and on Claude Code behind its default-off early-access function-hooks flag, hides supported transcript chrome, including canonically classified Firstmate operational user rows, and uses a Calm-only animated working boat during active runs while preserving all model context and session data. Calm changes only presentation, not the user-role delivery, ordering, authority, persistence, or exports of the operational inputs it hides. The preference persists for the effective Firstmate home, and toggling it off restores ordinary rendering. Calm's current behavior and supported limits are separate from its version-scoped maintainer evidence. Pi's /supervision-model command pins a cheaper model and a shallower reasoning effort for the supervision branch alone, from the eligible models and thinking levels Pi itself reports, and with no pin the branch normally follows your own conversation's model and effort; see the configuration schema.

> ahoy! look at my github project xyz, then fix the flaky login test and add dark mode

# firstmate checks its toolchain (asking your consent before installing or upgrading anything),
# clones the project under projects/ and spawns two isolated workers in the active backend.
# Minutes later:

  PR ready for review, captain: https://github.com/you/xyz/pull/42
  (fix flaky login test - risk: low - CI green)

> alright merge it

Setup guides for tmux (the default) and every other supported backend (herdr, zellij, Orca, cmux, Paseo, Rex, T3 Code, tern) are linked in Documentation below.

            you (the captain)
                  │  chat: requests, decisions, "merge it"
                  ▼
 ┌─────────────────────────────────────┐
 │ firstmate            (this repo)    │
 │ reads projects/ + firstmate routes  │
 │ writes guarded backlog/briefs/state │
 └──┬──────────────┬───────────────┬───┘
    │ backend sends / status files │
    ▼              ▼               ▼
 ┌────────┐   ┌────────┐      ┌────────┐
 │fm-task1│   │fm-task2│  ... │fm-taskN│   one visible task endpoint each
 │crewmate│   │crewmate│      │crewmate│   one autonomous agent each
 └───┬────┘   └───┬────┘      └───┬────┘
     ▼            ▼               ▼
  treehouse worktree, Orca worktree, or isolated secondmate home
     │
     ├─ ship: project mode ► PR/local merge ► teardown
     │
     └─ scout: report at data/<id>/report.md ► decision inventory ► relay findings ► teardown

You chat with the first mate. It routes each request to a crewmate in its own session endpoint and git worktree, supervises the fleet with a zero-token event-driven watcher, and brings you finished PRs, approved local merges, or investigation reports. Optional secondmates extend this to persistent local or whole-home remote second mates, dispatch profiles let you steer which harness handles which task, and opt-in Relay lets the same fleet answer public mentions. codex-app is not a runtime backend yet; docs/codex-app-backend.md owns the Codex App boundary.

Full architecture - the supervision engine, worktree isolation, secondmates, dispatch profiles, project modes, optional Relay, fleet sync, and self-update - is in docs/architecture.md.

Firstmate ships these user-invocable built-in skills. Claude and grok use the slash form shown here; codex uses the same names with $, such as $afk.

Bearings invocation examples:

• /bearings returns the fresh four-section digest in chat only.
• Owned-contribution follow-up comes from the cached coverage projection; include PRs remains the opt-in for repository-wide live PR enrichment.
• /bearings include PRs keeps chat-only mode and opts into live PR enrichment.
• /bearings file replaces today's data/status-report-<YYYY-MM-DD>.md from scratch and links it from the four-section chat digest.
• /bearings file include PRs combines the dated report with live PR enrichment.

Agent-only reference skills live under .agents/skills/ and are loaded by firstmate at the trigger points named in AGENTS.md.

Firstmate's skills live in two separate places with different audiences:

• .agents/skills/ - agent-loaded skills (this section's table, plus firstmate's agent-only reference skills). Every one of these assumes a live firstmate home and is meaningless, or actively misleading, installed anywhere else, so each carries metadata.internal: true in its frontmatter. That flag hides them from installer discovery (tools like the skills.sh npx skills add installer) without affecting how firstmate itself loads them - frontmatter metadata is inert to the agent's own skill loader.
• skills/ - public, installer-facing skills meant to be installed standalone into any project, independent of firstmate. Each one is a self-contained skill with no dependency on firstmate's paths, tools, or vocabulary. Today that is skills/stow, a generic session-knowledge-sweep skill that routes findings by explicit instruction first, then existing local conventions, then a private .stow-notes.md fallback, and curates tiered entries through decay, local archival, and user-approved on-demand offload proposals. It intentionally shares no code with the firstmate-internal .agents/skills/stow it is named after, so the two can evolve independently.

• docs/architecture.md - maintainer architecture for the crew, supervision, worktrees, secondmates, and project modes.
• docs/configuration.md - environment variables, FM_HOME, runtime backend selection, optional Relay and its X and Discord setup steps, trusted external process-event adapter setup, the files you set, and harness support.
• docs/extension-bindings.md - maintainer architecture for the narrow trusted external process-event-adapter/1 package, binding, handshake, and evidence boundary.
• docs/remote-secondmates.md - current setup, routing, transfer, recovery, and safety behavior for whole-home remote second mates.
• docs/calm.md - current /calm behavior on Pi and Claude Code and its supported presentation limits.
• docs/voice-relay.md - the optional spoken interface: setup on both machines, measured round-trip cost, what a spoken answer may read, and what this build does not do yet.
• docs/fleet-ledger.md - the opt-in activity ledger outside tools can read to follow a home's tasks, and its record contract.
• docs/wedge-alarm.md - configure the active alert for an away-mode escalation delivery that gets stuck.
• docs/usage-warner.md - configure the opt-in local threshold warner for Claude usage windows.
• docs/tmux-backend.md - current setup and limits for the tmux reference backend.
• docs/herdr-backend.md - current setup, CI coverage, safety boundaries, and limits for the Herdr backend.
• docs/zellij-backend.md - current setup and limits for the experimental Zellij backend.
• docs/orca-backend.md - current setup and limits for the experimental Orca backend.
• docs/cmux-backend.md - current setup, socket security, and limits for the experimental cmux backend.
• docs/paseo-backend.md - current setup, terminal-name routing, and limits for the experimental Paseo backend.
• docs/rex-backend.md - current setup, auto-detection, block-id routing, the absence proof, and limits for the experimental Rex backend.
• docs/t3code-backend.md - current setup, sign-in, and limits for the experimental T3 Code backend.
• docs/tern-backend.md - current setup, surfaces capture, native-state degradation, and limits for the experimental tern backend.
• docs/codex-app-backend.md - the current blocked Codex App backend boundary and rollout contract.
• docs/verification/runtime-backends.md - active maintainer verification for runtime backend guarantees.
• docs/gerrit-forge-integration.md - maintainer architecture for the forge axis: why change-shaped review is not a forge variant, the mode/forge/shape composition test, and where responsibility for forge mechanics sits.
• docs/external-review-forge.md - maintainer architecture for forge=external, where a review tool uploads its own snapshot: the no-push invariant and its three layers, the personal backup remote, and the accepted residual.
• docs/gitlab-merge-watch.md - maintainer verification for watching and merging GitLab merge requests on arbitrary instances.
• docs/gerrit-change-watch.md - maintainer verification for watching Gerrit changes read-only, and why the merge path refuses one.
• docs/forgejo-tea-integration.md - maintainer verification for watching and merging Forgejo/Gitea pull requests via tea.
• docs/turnend-guard.md - the primary session's current "no turn ends blind" backstop, scope, loop safety, and compatibility limits.
• docs/verification/supervision.md - active maintainer verification for session-start, guard, continuity, and wedge integrations.
• docs/supervision-protocols/ - rendered primary-harness watcher protocols for Claude, Codex, OpenCode, Pi and pi-signed, omp, Grok, Cursor, and unknown harness fallback.
• docs/scripts.md - the bin/ toolbelt reference.
• docs/documentation-audiences.md - documentation audiences and the machine-checked placement boundary.
• AGENTS.md - the supervisor contract, role boundary, and routing index for conditional procedures.
• CONTRIBUTING.md - how to contribute, including the dev/test commands.

Contributions are welcome - see CONTRIBUTING.md for the workflow, repo conventions, and how to run the tests.

MIT - see LICENSE.