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.
npx agentmods add skills/trustmybot/plugin/tmb-agent-setupnpx skills add trustmybot/plugin --skill tmb-agent-setupgit clone --depth 1 https://github.com/trustmybot/pluginWhat 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 | $0.00048 | $0.00889 |
| Opus 5 | $0.00024 | $0.00445 |
| Sonnet 5 | $0.00010 | $0.00178 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
tmb-agent-setup 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TMB Agent Setup
Fixed targets
.codex/agents/tmb_swe.toml.codex/agents/tmb_pr_reviewer.toml
Each generated Agent carries a disabled same-name trajectory-server entry in
its own mcp_servers table. The entry has an inert node --version transport
only because Codex requires a complete transport shape even when the server is
disabled. The Agent also stops before repository access if a TMB tool is still
visible at runtime.
Workflow
- Resolve the absolute Git top-level selected by the user. Pass that exact path
as
project_rooton every TMB call. - Determine whether the user wants to inspect the files or make them present or absent. Ask when the desired action is not explicit.
- Call
agent_materialization_getand report the overall state plus both Agent states. - If the requested state is already satisfied, finish without calling the setter and without asking for a no-op confirmation.
- If either Agent is
conflict, stop and explain that the user must resolve the file manually. Setter, force, overwrite, adopt, automatic backup, and automatic repair are unavailable in this state. - Show the two fixed paths and explain whether each one will be created or
removed. State that the files may appear in
git status; TMB will not stage, commit, or ignore them. - Ask for explicit confirmation. Do not treat the original Skill invocation as confirmation of the file mutation.
- Only after confirmation, call
agent_materialization_setonce withdesired_stateset topresentorabsent. - Call
agent_materialization_getagain. Report success only when both Agents match the requested final state. - When files changed, tell the user to start a new Codex task or CLI session. Do not say the current task has hot-loaded the Agent files.
Confirmation text
For installation in a Chinese conversation, use:
将在当前 Git 项目中创建以下文件：
.codex/agents/tmb_swe.toml
.codex/agents/tmb_pr_reviewer.toml不会修改
.claude、Git 索引、远程仓库或 TMB 规划数据。文件可能出现在git status，是否纳入版本控制由你决定。确认安装吗？
What ships with it
1 file 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.
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 · 82 lines · 48 tokens per session scan A bf859ab1d107
tmb-agent-setup is a skill published in the GitHub repository trustmybot/plugin (6 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 889 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…