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/minghinmatthewlam/agent-guards/autoreviewnpx skills add minghinmatthewlam/agent-guards --skill autoreviewgit clone --depth 1 https://github.com/minghinmatthewlam/agent-guardsWrote 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/minghinmatthewlam/agent-guards/autoreview)<a href="https://agentmods.dev/skills/minghinmatthewlam/agent-guards/autoreview"><img src="https://agentmods.dev/badge/skills/minghinmatthewlam/agent-guards/autoreview.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 5.1 | $0.00048 | $0.00785 |
| Opus 5 | $0.00024 | $0.00392 |
| Sonnet 5 | $0.00010 | $0.00157 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
autoreview 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 yesterday.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Review
Run the bundled structured review helper as the default code-review closeout. Codex is the default engine; use Claude or a panel only when the user asks or material risk warrants it.
Core Workflow
- Select the real target:
- dirty working tree:
--mode local - branch or PR:
--mode branch --base <actual-base> - committed change:
--mode commit --commit <ref>
- dirty working tree:
- Run
~/.agents/skills/autoreview/scripts/autoreviewwith that target. Pass the task intent and success criteria through--promptor--prompt-filewhenever they are available. - Verify findings against the real code path, demonstrated contracts, and task intent.
- Fix accepted blocking findings at the correct ownership boundary. P0/P1 block by default; keep P2/P3 visible but advisory.
- After blocking fixes, rerun focused proof and autoreview once. Continue further only while a verified P0/P1 remains unresolved.
- Stop when the helper exits successfully. Advisory findings do not require another round.
Read references/commands.md when choosing flags, panels, paths, or parallel test execution. Read references/failure-modes.md when a run stalls, fails, reports Gitcrawl problems, or raises provenance/security questions.
Judgment
- Treat findings as advisory. Reject speculative risks, unrealistic edge cases, and fixes that add more complexity than value.
- Prefer the simplest clear implementation that meets the current task and demonstrated contracts. Flag complexity that materially makes the code harder to understand, maintain, verify, or extend. Do not recommend unrelated cleanup, speculative future-proofing, or scope beyond the stated goal.
- Prefer narrow root-cause fixes; do not broaden the refactor merely to satisfy a reviewer.
- Flag unnecessary layers, duplicate paths, and speculative fallbacks. Prefer deleting or consolidating code.
- Do not assume backward compatibility is required. Require evidence of a public contract, supported consumer, migration guarantee, test, or explicit user requirement before adding compatibility work.
- Do not add fallback paths, dual implementations, compatibility shims, or migrations for hypothetical consumers.
- Do not impose a findings cap. Use priority and impact to distinguish blocking work from advisory observations.
- Keep web search enabled unless the user requests offline review or the material should not leave the local environment.
- Do not override an explicitly requested engine, model, or thinking level.
- Do not push merely to obtain a review.
- Do not substitute review for the repository's verification path; code review does not prove product behavior.
- Multi-reviewer panels are opt-in unless the change is high-risk or the first result needs arbitration.
What ships with it
8 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.
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.
- yesterday Changed · +1 lines c6c18d3d467c
- 6d ago First seen · 51 lines · 48 tokens per session scan A 376f6f8fc237
autoreview is a skill published in the GitHub repository minghinmatthewlam/agent-guards (39 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 785 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…