Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kevintsai1202/teaching-site-skillsnpx agentmods add skills/kevintsai1202/teaching-site-skills/web-content-auditWrote 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/kevintsai1202/teaching-site-skills/web-content-audit)<a href="https://agentmods.dev/skills/kevintsai1202/teaching-site-skills/web-content-audit"><img src="https://agentmods.dev/badge/skills/kevintsai1202/teaching-site-skills/web-content-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/kevintsai1202/teaching-site-skills/web-content-audit"><img src="https://agentmods.dev/badge/skills/kevintsai1202/teaching-site-skills/web-content-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00201 | $0.02777 |
| Opus 5 | $0.00101 | $0.01388 |
| Sonnet 5 | $0.00040 | $0.00555 |
| Haiku 4.5 | $0.00020 | $0.00278 |
Grade A, and why
web-content-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 12d 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.
This is a copy
86% identical to pr-review — 272 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Content Audit
Schema authority: cross-file consistency rules (3-place sync for materials, task ID stability, quiz renumber trap) are codified in
_shared/domain-primitives.md§13. Audit scripts in this skill operationalise those rules.Filename convention (English-first): audit reports land under
data/audit-*.md; scripts underscripts/audit-*.mjs.
This skill produces audit scripts that read source files and deployed data, compare them, and emit a human-readable report. The goal is not to gatekeep deployment (that's verification's job) — it's to surface drift that humans should review.
When to Invoke
- Before a major content release (catch outline ↔ course-data ↔ visuals drift before students see it).
- After adding/removing units / materials / quiz items (re-check the three-place sync rule).
- Before handing off a corporate edition to a client (confirm the condensed COURSE matches its source).
- When the user senses "something's off" but can't see a runtime bug — audit is for the invisible drift.
- When planning the next iteration (e.g. "which sections need new illustrations?").
Do NOT invoke when the question is "does the page render correctly?" — that's web-visual-verification.
Audit vs Verify — Operating Mode Difference
| Trait | Audit | Verify |
|---|---|---|
| Output | Markdown report (human reads) | Pass/fail (CI gates) |
| Tools | File reads, regex, JSON diffs, optionally Playwright | Playwright + asserts |
| Failure mode | Always exits 0; report tells human what's worth fixing | Exits non-zero on bad state |
| When run | Manually, at milestones | On every PR / pre-deploy |
| Mental model | "Show me what's drifted" | "Don't let this regress" |
If your script ends with assert.* or process.exit(1), it's not an audit — move it to web-visual-verification.
The Five Audit Categories
Audit 1: Cross-Artifact Reference Resolution
The classic teaching-site bug: course-data.js:materials[] references a file the disk doesn't have, or getMaterialUrl() is missing a rule.
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.
- 12d ago First seen · 237 lines · 201 tokens per session scan A 62d31c79f288
web-content-audit is a skill published in the GitHub repository kevintsai1202/teaching-site-skills (50 stars, last pushed 4mo ago), licensed MIT. It adds 201 tokens to every session and 2,777 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to pr-review, differing in 272 lines, and is treated as a copy.
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…
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…
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…