tmb

Plugin tmb from marketplace trustmybot in trustmybot/plugin. Commands read from the repo's manifest — yesterday.

Skills (13)

• tmb-agent-setup

  Inspect, install, or remove TrustMyBot's two fixed project-level Codex Agents. Use only when the user explicitly invokes $tmb:tmb-agent-setup and confirms the exact project-local file changes.

• tmb-bro

  Inspect a Git project with TMB's project-local inventory and world model, clarify a request, and capture an approved local planning issue plus Bro-authored decisions. Use only when the user explicitly invokes $tmb:tmb-bro for repository understanding or planning; stop before implementation, task orc

• tmb_audit

  How bro audits, verifies or checks a component or an architecture — start from its outputs, state the invariants they must satisfy, prove each against live data, and report violations architecture-first. Loaded when the Human asks for an audit, a verification, a check, or an architecture review.

• tmb_cheatcode

  When bro hits a wall — a task leans on a capability the project plainly lacks — and an existing published skill, MCP toolkit, or plugin would close the gap better than hand-rolled code. Bro names the gap, calls cheatcode_search for ranked candidates, judges which best fits this task and codebase, an

• tmb_comment-triage

  Bro's PR/MR comment triage — resolve the PR, fetch the comment threads, judge which are task-worthy, and dispatch SWE per ratified group. Loaded by bro when /monitor surfaces PR/MR comments.

• tmb_concerns-protocol

  How bro raises a concern when doubting the Human's plan — surface inline via discussion_append + ask, or spawn a consultant in analysis-only mode for technical disagreement. Always surface disagreement; always yield to the Human's call, and when the Human said not to ask, record the concern with the

• tmb_docs-conventions

  Loaded when editing prompt files (agents, skills, CLAUDE.md, workflow markdown) or updating user-visible docs. Carries the editing judgment — what to delete, what to preserve, and where ripples land when a rename or restructure happens.

• tmb_planning

  Bro's code-touching flow — verify world model, triage the requirement (reuse vs build), propose branch, write spec, dispatch SWE, verify on return, atomic-close. Loaded on the first code-touching ask of a session.

• tmb_push-gate

  Bro's push-gate orchestration — reaping unsigned commits, spawning pr-reviewer per task, and the all-pass push + PR-create + post-merge cleanup path. Loaded by bro when the push hook blocks or the Human asks for review-before-push.

• tmb_recovery

  Bro's response when something fails — an MCP tool returns is_error=true (halt + surface), the trajectory-server is unreachable (degraded sqlite3 readonly fallback), or the world model is unavailable (retry, identify the lock holder, reconnect the binding). Loaded reactively on the first failure of a

• tmb_review

  PR-reviewer's diff-level push-gate review — check this task's diff against its spec, then write the validation_record verdict that gates the push. Loaded by pr-reviewer when reviewing a committed task. Self-contained.

• tmb_skill-creator

  Generate a new project-local skill at <project>/.claude/skills/<name>/SKILL.md and attach it to existing agents. Loads when the user asks to capture a repeatable behavior — e.g. "create a skill that codifies <our convention>", "teach swe to also <run mypy / use black / etc.>", "make a skill for <rev

• tmb_swe-checklist

  SWE's self-review heuristics — load only when about to atomic-close. Mechanical patterns (bare except, missing timeout, mutable defaults, etc.) are caught by the plugin's code-quality-lint hook; this skill carries the spec-fidelity and scope discipline judgment.

Slash commands (6)

• /tmb:README
• /tmb:agent-create

  Create or copy an agent into <project>/.claude/agents/ and (optionally) spawn it on a consultant question.

• /tmb:monitor

  Pull review comments from a GitHub PR or GitLab MR and plan/dispatch SWE work to address them

• /tmb:onboard

  Configure or change identity, branching model, PR target, remotes, issue-sync, and the Bash sandbox. Server-driven — bro orchestrates AskUserQuestion rounds.

• /tmb:roundtable

  Multi-agent deliberation on a topic with checkbox/radio AUQ ratification

• /tmb:scan

  Populate the world model — a kuzu graph of the project's directories — by walking the project root for git repos and pulling each dir's README.md into a summary. Single phase — no background fill required for the primary navigation surface.

Subagents (3)

• README
• pr-reviewer

  Push gate. Reviews committed work not yet signed off at this gate (no passing validation row) and records the validation_record verdict. Read-only on files; no Edit/Write tool by design.

• swe

  Executor. Implements task specs in isolated worktrees with atomic close.

MCP servers (1)

• trajectory-server

  runs: node --experimental-sqlite ${CLAUDE_PLUGIN_ROOT}/mcp/trajectory-server/dist/index.js

Hooks (30)

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" ensure-gitignore

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" mcp-health-check

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" deferred-tools-drift-warn

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" plugin-hooks-marker

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" session-start-persona

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" session-start-prescan

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" ensure-kuzu-installed

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" substrate-preflight

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" orphan-scan

• UserPromptSubmit

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" user-prompt-persona

• UserPromptSubmit

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" activation-routine

• UserPromptSubmit

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" session-log-capture

• UserPromptSubmit

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" prompt-intent-hints

• UserPromptSubmit

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" roundtable-slash-detect

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" containment-guard

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" git-guards

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" git-push-guard

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" swe-boundary

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" no-worktree-branch-create

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" stay-on-base-guard

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" branch-up-to-date-with-remote

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" commit-msg-lint

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" no-remote-auth-guard

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" remote-id-guard

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" agent-spawn-dispatch

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" trajectory-gates

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" askuserquestion-length-lint

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" roundtable-auq-shape

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" swe-brief-gate

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/dispatch.sh" no-source-edit-from-main

Similar plugins