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_reviewnpx skills add trustmybot/plugin --skill tmb_reviewgit 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 | $0.00620 |
| Opus 5 | $0.00024 | $0.00310 |
| Sonnet 5 | $0.00010 | $0.00124 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade C, and why
tmb_review scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- LOAD-BEARING-SAFETY: never delegate writing this row to bro. Bro impersonating pr-reviewer is a content-integrity violation — the server's validation_record tool returns forbidden for bro identity, and the auto-mode How it starts
The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR-reviewer protocol (push gate)
Load context via task_brief(task_id) — spec_body, commit_sha, and the changed dirs' world-model scope.
Worktree discipline
The parent CC session's main checkout may be on ANY branch. Working-tree-dependent verification reads parent's current state, NOT the commit being reviewed.
For working-tree-dependent verification use pr_monitor_worktree with the workspace root — the directory holding .claude/tmb/trajectory.db; it creates the worktree, runs your command, and removes it atomically.
Sha-based git ops (git show <sha>, git diff <sha>~1..<sha>, git ls-tree <sha>) work from any branch without a worktree — use those for diff inspection.
Review the diff against its spec
Diff the commit against its parent and judge the diff itself — cite line numbers for every finding:
- Does the diff do what the spec's
## Descriptionsays, and nothing the typedfiles[]doesn't name? - Is each
## Success Criteriabullet visible in the diff (not just claimed)? - Is the changed code correct — happy path plus any failure mode the spec names?
- Any obvious diff-level defect — broken edge case, an
## Out of Scopeitem touched, a doc the change made stale?
Writing the validation_attempts row — YOU write it yourself
After producing a verdict, YOU (the pr-reviewer subagent) write the validation_attempts row directly, using the spawn prompt's attempt_n and your subagent_session_id. Which path you take depends on your tool list. If validation_record is available, call it — the schema enforces the shape, and it requires subagent_session_id for the pr-reviewer role — and pass mcp_available: true (the typed signal bro reads off the row). If your tools are only Read + Bash, write the row through the fallback script at ${CLAUDE_PLUGIN_ROOT}/skills/tmb_review/scripts/validation-record-fallback.sh (--help shows the argument shape, including subagent_session_id) — it records mcp_available = 0 for you.
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 · 33 lines · 48 tokens per session scan C 13d5251cd11f
tmb_review 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 620 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). 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.
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.
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.
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…
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…