claude

tm

TerMinal software-factory workflow for Claude Code: in-repo tickets and sessions, PR/MR flow with a human merge gate, six-axis code review, cadence checks, agent creation, and autonomous factory orchestration — namespaced as /tm:* in every repo.

8 on GitHubby TerMinalv0.1.0MITupdated 1 month agoworkflow
/

Plugin tm from marketplace terminal in trevormil/TerMinal. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (35)

  • check

    Run a scheduled cadence agent from its contract (tm-agent-spec <kind>) — isolated worktree, SHA-gated no-op on re-runs, then reports findings or proposes a ticket+MR. Use on /check <kind>, a scheduled-agent run, or wiring a launchd schedule.

  • code-review

    Compatibility launcher for the code-review agent. Delegates a GitHub/GitLab PR review to Codex: deterministic preflight does recon, then Codex scores six axes into one artifact at $TERMINAL_REVIEWS_DIR/<pr>/<sha>.md in the per-project sidecar. Use on /code-review or 'review this PR'.

  • digest

    Human-review digest for a PR/MR — chunks the diff into a noise-filtered, risk-ranked, code-first review surface (green/red diffs, 🟢/🟡/🔴, design-decision callouts) WITHOUT abstracting the code away. Deterministic chunker + one bounded codex pass. Sits alongside /code-review (the gate) and /iterate

  • document-audit

    Audit docs/ and ~/.claude/docs/ for rot — broken refs, stale runbooks, ADR contradictions, architecture drift, orphan CLAUDE.md. Reports only; never auto-edits. Use on /document-audit or 'check doc health'.

  • document

    Sweep recent changes and propose doc updates (ADRs, runbooks, learnings, architecture, per-folder CLAUDE.md), one candidate at a time. Use on /document, 'capture decisions', or natural post-commit/post-PR pauses.

  • emergency-fix

    FORCE-MODE hotfix: smallest patch → commit → push DIRECTLY to main → follow-up ticket. Needs TERMINAL_FORCE_MAIN=1 (hook-enforced). Use on /emergency-fix or 'this is breaking prod' / 'hotfix' / 'we need to revert now'.

  • enqueue-request

    Enqueue a one-off TerMinal automation-inbox request (can create Activity, tickets, HITL, agent runs, or background tasks). Use on /enqueue-request or to queue a durable local automation request.

  • factory

    Continuous autonomous orchestrator: reconcile, route tickets by owner agent, run stacked PR/MR passes, optionally discover/refill, park HITL, never merge. Use on /factory or 'work the backlog autonomously'.

  • knowledge-rag

    Add or update TerMinal Knowledge Base entries backed by the lyonzin/knowledge-rag local RAG MCP server. Use when the user wants category-specific RAG knowledge, semantic/vector search over docs, URL/document ingestion into the Knowledge Base, or help configuring the Knowledge Base tab's RAG item typ

  • knowledge

    Capture durable project or global knowledge into TerMinal's Knowledge Base. Use on /knowledge, when saving links/media/snippets/references, or when the user asks to remember useful context visually.

  • listener-inbox

    Queue local TerMinal automation listener events. Use when an integration, script, agent, or user wants to drop a JSON request into TerMinal's local automation inbox to trigger Activity, tickets, HITL, agent runs, or background tasks.

  • loop-driver

    Run a long-running, self-driving agent loop (the 'let the model drive' pattern) with separated planner/generator/evaluator roles, an on-disk contract, and taste scoring. Use when the user runs /loop-driver, says 'loop on this', 'let it run for a while', 'set up a generator/evaluator loop', or wants

  • loop-evaluator

    The evaluator role in a /loop-driver. Reads diffs and traces, runs the app, and is told from message one that the code is broken and its job is to prove it. Grades the contract and scores taste. Use when the user assigns this session as the evaluator/reviewer in a generator/evaluator loop, or runs /

  • loop-implementer

    The generator role in a /loop-driver. Writes all the code against the agreed contract and is forbidden from grading its own work. Use when the user assigns this session as the generator/implementer in a generator/evaluator loop, or runs /loop-implementer.

  • loop-planner

    The planner role in a /loop-driver. Turns a vague human goal into a gradable contract of testable assertions and never touches code. Use when the user assigns this session as the planner in a generator/evaluator loop, or runs /loop-planner.

  • merge-sync

    Reconcile tickets/backlog with reality: close tickets whose PRs merged, scrub merged URLs, sweep status drift. Edits ticket files only, never merges. Use after merging a stack or whenever PRs have landed.

  • migrate-agents

    Convert .agents/agents.json entries into the script-first shape — one <id>.sh + <id>.json per agent. Non-destructive (agents.json untouched). Use on /migrate-agents or to convert prompt-style agents into bash scripts.

  • new-agent

    Create or update a TerMinal agent from a natural-language request — writes a script-first .agents/<id>.sh + <id>.json sidecar. Use on /new-agent, 'create an agent', or wanting a reusable button/scheduled agent.

  • new-inbox-source

    Design or implement a durable TerMinal automation-inbox source (adapter, poller, webhook bridge, file watcher). Use on /new-inbox-source or when building a service that repeatedly enqueues requests.

  • new-knowledge

    Create or update TerMinal Knowledge Base entries in the repo sidecar knowledge.json or global ~/.config/TerMinal/knowledge.json. Use on /new-knowledge or when the user asks to save links, media, files, snippets, or durable references.

  • new-persistent-agent

    Create a global TerMinal persistent memory agent. Use when the user runs /new-persistent-agent or asks for a memory-aware agent that keeps its own INSTRUCTIONS.md, MEMORY.md, STATE.md, JOURNAL.md, and artifacts directory.

  • new-schedule

    Create a TerMinal cron schedule from a natural-language request — appends a launchd-backed entry to ~/.config/TerMinal/schedules.json. Use on /new-schedule or 'run this agent on a cadence'.

  • new-snippet

    Create or update a TerMinal quick snippet (repo sidecar snippets.json or global). Use on /new-snippet or wanting a reusable quick prompt / one-click launcher item.

  • pr-creation

    Take owner-compatible backlog tickets from idea to open PR/MR: knowledge phase → branch/worktree → TDD → checks → follow-up tickets → push/open/link. Does not auto-run code review. Use on /pr-creation or 'start work on a ticket'.

  • remote-terminal

    Register this session with TerMinal Remote so it can be followed and steered from the phone. Use on /remote-terminal, 'sync this to my phone', 'I'm heading out — keep me posted', or before starting long work you want to supervise while away.

  • revert-main

    FORCE-MODE: git revert HEAD on main, run the suite, push directly. Needs TERMINAL_FORCE_MAIN=1 (hook-enforced). Use on /revert-main or 'revert main' / 'undo the last commit' / 'roll back HEAD'.

  • security-scan

    Deterministic local security checks — dependency CVE audit (bun/npm) by default, optional SAST (semgrep) and opt-in gitleaks — summarized for code-review's Security axis. Use on /security-scan or as a pre-push gate.

  • session-end

    Close a work session: reconcile the live session doc, clean up dead code/branches, run a refactor pass, file follow-up tickets, capture docs, mark closed. Use on /session-end or 'wrapping up'.

  • session-start

    Open a work session: allocate an id, seed a live session doc by scanning the repo for relevant tickets/state, and generate a TDD-first checklist. Use on /session-start \"<goal>\" or to kick off work.

  • stacked-mr

    Autonomous AFK mode: build a stack of owner-scoped PRs/MRs, then batch-review them to the bar. Human merges. Use on /stacked-mr or 'stack PRs'.

  • terminal-widget

    Add or edit repo-specific TerMinal sidebar widgets (shell commands the terminal polls) via .TerMinal/widgets.json. Use on /terminal-widget or to surface repo state (counts, status, metrics) in the sidebar.

  • test-suite

    Delegate an ad-hoc test run to Codex and report results in chat (no artifact) — the cheap inner-loop step; the code-review agent is the checkpoint. Use on /test-suite or 'run the tests'.

  • ticket

    Create and manage backlog tickets in the per-project sidecar ($TERMINAL_BACKLOG_DIR/NNNN-slug.md); atomic ids, list/update/close. Portable. Use on /ticket, 'file/list/close a ticket', or describing work to track.

  • unblock-ci

    FORCE-MODE: main CI is red — apply the narrowest of revert bad SHA / pin dep / skip documented-flaky test, pushed directly to main. Needs TERMINAL_FORCE_MAIN=1. Use on /unblock-ci or 'main CI is broken' / 'green main'.

  • vibe

    Enter vibe mode — fast, gates-off exploration in a disposable worktree to generate breadth and signal, never shipped directly. Use when the user says /vibe, 'vibe this', 'explore fast, skip the gates', 'prototype N approaches', or wants throwaway iteration to learn the shape of a problem before buil

Subagents (17)

  • 1000x-ai-engineer
  • auto-docs
  • changelog
  • code-review
  • coverage
  • dead-code
  • deps-quality
  • digest
  • drift
  • forge
  • health
  • perf
  • pipelines
  • scripts
  • testing
  • ticket-ideas
  • watchdog

Hooks (3)

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/block-main-merge.sh

  • Stop

    ${CLAUDE_PLUGIN_ROOT}/hooks/stop-notify.sh

  • Stop

    ${CLAUDE_PLUGIN_ROOT}/hooks/remote-check.sh

View source on GitHub

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows

18 skills

MiniMax-AI/skills 13,828

Maintain tm?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted