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/molten-bot/agent_00/reviewnpx skills add Molten-Bot/agent_00 --skill reviewgit clone --depth 1 https://github.com/Molten-Bot/agent_00Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/molten-bot/agent_00/review)<a href="https://agentmods.dev/skills/molten-bot/agent_00/review"><img src="https://agentmods.dev/badge/skills/molten-bot/agent_00/review.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00041 | $0.00373 |
| Opus 5 | $0.00020 | $0.00187 |
| Sonnet 5 | $0.00008 | $0.00075 |
| Haiku 4.5 | $0.00004 | $0.00037 |
Grade A, and why
review 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 5d 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.
What it actually says
Review Pull Requests
Inspect the effective diff against its merge base. Read the original task, PR metadata, discussion, changed code, callers, tests, configuration, migrations, and checks that affect the change.
Do not edit files, commit, push, or rewrite the pull request.
Prioritize actionable correctness, regression, security/privacy, data-loss, compatibility, concurrency, error-handling, performance, and missing-test risks. Verify claims from repository evidence. Do not report speculative concerns or pre-existing issues unrelated to the change.
Order findings by Critical, High, Medium, then Low. Every finding must identify a changed file and line, explain a concrete problem the author can fix, and be concise enough to drive a repair pass.
Return exactly two markdown sections, **Positive** and **Negative**, with bullet points only. Include at most three positive bullets and six negative bullets. If there are no findings, use exactly - No material issues found. under Negative.
End with a fenced JSON object using this shape:
{"status":"findings","mergeReady":false,"summary":"short verdict","positives":["short positive point"],"findings":[{"severity":"Medium","path":"path/to/file.go","line":123,"title":"specific actionable finding"}]}
status must be exactly one of clean, findings, or blocked; never copy a list of choices into the value. Keep the JSON consistent with the markdown. Set status to clean and mergeReady to true only when there are no material findings or blockers.
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.
- 5d ago First seen · 25 lines · 41 tokens per session scan A e40a0ddcaf2c
review is a skill published in the GitHub repository Molten-Bot/agent_00 (5 stars, last pushed 8d ago), licensed MIT. It adds 41 tokens to every session and 373 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
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
map-wayfind
Decision-frontier wayfinding: build and work a durable map of open design decisions BEFORE planning, for large or foggy efforts where /map-plan would force premature decomposition. Use when a task is too big or too vague to decompose — many unknowns, tangled decisions, or "I'm not even sure what to build yet" — and…
map-fast
Minimal workflow for small, low-risk changes — no planning, no learning.