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 skills add minghinmatthewlam/agent-guards --skill skills-auditgit 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/skills-audit)<a href="https://agentmods.dev/skills/minghinmatthewlam/agent-guards/skills-audit"><img src="https://agentmods.dev/badge/skills/minghinmatthewlam/agent-guards/skills-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/minghinmatthewlam/agent-guards/skills-audit"><img src="https://agentmods.dev/badge/skills/minghinmatthewlam/agent-guards/skills-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.00488 |
| Opus 5 | $0.00030 | $0.00244 |
| Sonnet 5 | $0.00012 | $0.00098 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
skills-audit 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 9d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Skills
Perform a read-only, evidence-backed audit of the requested skills. Default to decision-relevant findings, not an exhaustive ceremony.
Discover
Inspect the paths in scope, including when relevant:
~/.agents/skills/,~/.claude/skills/, and~/.claude/commands/;- repo-local
.agents/skills/and.claude/skills/; - custom paths named by the user.
Deduplicate synced or linked copies and identify the source of truth. Note agent system, folder resources, frontmatter, and broken links or scripts.
Evaluate
Read references/checklist.md and apply only relevant checks. Use references/categories.md when classification helps reveal mixed responsibilities or a repository-level coverage gap; do not force classification when it adds no decision value.
Prioritize:
- incorrect, stale, conflicting, or unsafe instructions;
- duplicated guidance likely to drift;
- always-loaded detail better routed through references or scripts;
- weak trigger descriptions;
- missing real-world failure guidance;
- rigid procedures that prevent capable agents from adapting;
- missing skills only when repository evidence shows repeated value.
Numeric scores are optional comparison aids, not required output. Never penalize a short behavioral skill for lacking unnecessary resources.
Report
Use concisely. Include every material finding, ordered by impact, with exact file evidence and the smallest useful change. Group clean or low-priority skills rather than producing filler.
Distinguish observed evidence from inference. Do not impose a fixed findings count.
Apply Mode
Audit first. If the user asks for changes, edit only the approved scope, preserve useful non-obvious guidance through progressive disclosure, validate the changed skills, and report proof.
Gotchas
- Do not audit installed mirrors as independent skills when they share one source.
- Do not optimize for line count at the cost of deleting real failure knowledge.
- Do not treat a large command reference as always-loaded context when it is properly routed.
- Do not recommend generic new skills without repository evidence that they would recur.
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.
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.
- 9d ago First seen · 52 lines · 60 tokens per session scan A 7e758613cecd
skills-audit is a skill published in the GitHub repository minghinmatthewlam/agent-guards (40 stars, last pushed 8d ago), licensed MIT. It adds 60 tokens to every session and 488 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 2026-08-30.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…