A planning skill for inspecting a Git project—a folder whose history and changes are tracked by Git—and recording an approved local planning issue. It uses a project inventory and a searchable model of the project's structure.

Use it when explicitly invoking TMB Bro to inspect a repository, find relevant areas, clarify scope, and capture a local planning issue.

It turns an unclear request into durable project context and planning decisions without starting implementation or changing remote systems.

tmb-bro — Skill by trustmybot

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/trustmybot/plugin/tmb-bro

Any agent

npx skills add trustmybot/plugin --skill tmb-bro

Clone the repo

git clone --depth 1 https://github.com/trustmybot/plugin

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,017 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00070	$0.01017
Opus 5	$0.00035	$0.00508
Sonnet 5	$0.00014	$0.00203
Haiku 4.5	$0.00007	$0.00102

Measured 2d ago against content hash 0748e4a48a61, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tmb-bro 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 2d 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.

adapters/codex/skills/tmb-bro/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TMB Bro

Use TMB as a bounded planning aid. Turn the user's intent and the selected Git worktree into durable local context without starting implementation or changing remote systems.

Planning workflow

Determine the exact Git worktree the user wants to plan against. Pass its absolute top-level path as project_root on every TMB call. Do not substitute the MCP process working directory.
Call runtime_initialize. If it rejects the project, surface the named error and stop; do not create .tmb/, edit .gitignore, or choose another project implicitly.
Call project_inventory. If no repository is recorded or the model is stale for this request, call project_scan, then read the inventory again.
Inspect the smallest useful slice of project context:
- use world_model_search to locate relevant areas;
- use world_model_get for the selected subtree;
- use Codex's normal read-only repository tools when source-level evidence is necessary.
Separate evidence from assumptions. Ask the user when a missing product, scope, or acceptance decision would materially change the plan.
Call planning_label_taxonomy_get before drafting the local issue. Treat the returned strings as the exact labels accepted by this project.
Draft a concise objective and a Markdown description containing context, scope, exclusions, and verifiable acceptance criteria. Show material choices to the user before creating the record when they have not already approved them. When both taxonomy sources are default, preserve the default Feature + Priority: Medium choice unless the user asks for another default label. When either source is configured, ask the user to choose one returned classification and one returned priority unless they already approved exact labels. Never silently choose the first configured label. Include extra labels only when the user explicitly requests them.
Call planning_issue_create. Use classification and priority for the default taxonomy, or labels for the exact configured choices. Never mix those input forms. This creates only a project-local TMB issue; remote issue sync stays off even when the Git repository has a remote.
Record confirmed decisions or unresolved questions with planning_discussion_append. Use only decision, question, or note.
Return the local issue identifier, the decisions captured, open questions, and the explicit stop boundary.

Read the full file on GitHub · 87 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

2d ago First seen · 87 lines · 70 tokens per session scan A 0748e4a48a61

Subscribe to this mod's changes

tmb-bro is a skill published in the GitHub repository trustmybot/plugin (6 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 1,017 once invoked, about $0.0003 per session on Opus 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 2026-08-31.

Git and workflow Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens