TMB Plugin — Claude Code native multi-agent workflow. Free forever.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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 orchestration, review…
Skill Claude CodeCodex
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 cheatcodesearch for ranked candidates, judges which best fits this task and codebase, and recommends it for…
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
How bro raises a concern when doubting the Human's plan — surface inline via discussionappend + ask, or spawn a consultant in analysis-only mode for technical disagreement. Always surface disagreement; always yield to the Human's call. Loaded when bro genuinely disagrees with a request.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
Bro's response when something fails — an MCP tool returns iserror=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 session.
Skill Claude CodeCodex
PR-reviewer's diff-level push-gate review — check this task's diff against its spec, then write the validationrecord verdict that gates the push. Loaded by pr-reviewer when reviewing a committed task. Self-contained.
Skill Claude CodeCodex
Generate a new project-local skill at .claude/skills/ /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 ", "teach swe to also ", "make a skill for ", "we need a checklist when ". Extends the consuming agent's skills: frontmatter…
Skill Claude CodeCodex
SWE's self-review heuristics — load only when about to atomic-close. Mechanical patterns (bare except, missing timeout, mutable defaults, etc.) are caught by scripts/hooks/code-quality-lint.sh; this skill carries the spec-fidelity and scope discipline judgment.