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 commands/policyengine/policyengine-claude/audit-seogit clone --depth 1 https://github.com/PolicyEngine/policyengine-claudeWrote 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/commands/policyengine/policyengine-claude/audit-seo)<a href="https://agentmods.dev/commands/policyengine/policyengine-claude/audit-seo"><img src="https://agentmods.dev/badge/commands/policyengine/policyengine-claude/audit-seo.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 | $0.00033 | $0.00854 |
| Opus 5 | $0.00016 | $0.00427 |
| Sonnet 5 | $0.00007 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
audit-seo scanned grade A 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Deployed URL (`--url`, or a CNAME / `vercel.json` / Pages URL you locate): `WebFetch` it, or `curl -sL <URL>`. `curl` returns the raw pre-JS shell — that is what Googlebot indexes first. How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO audit: $ARGUMENTS
Read-only. Run every check yourself in one pass — no subagents. Report findings; make no code changes.
Options
--url <URL>— audit a deployed page directly (fetch its served HTML).--repo OWNER/NAME— shallow-clone to/tmp/seo-audit-targetand audit its builtindex.html.--local— print findings only; skip the GitHub-issue prompt.- No args — audit the current working directory's built output.
Step 1: Get the HTML the crawler sees
- Deployed URL (
--url, or a CNAME /vercel.json/ Pages URL you locate):WebFetchit, orcurl -sL <URL>.curlreturns the raw pre-JS shell — that is what Googlebot indexes first. - Local: build if needed (
bun install && bun run build, elsenpm), then readdist/index.htmlorbuild/index.html(check afrontend/subdir too for monorepos).
Step 2: Meta, Open Graph, canonical (check directly)
<title>(unique, ≤60 chars) and<meta name="description">(≤160 chars).- Open Graph:
og:title,og:description,og:image(absolute URL),og:url,og:type. - Twitter:
twitter:card,twitter:title,twitter:image. <link rel="canonical">present and absolute (see Step 4 for which URL).- Structured data (
application/ld+json) where the page warrants it.
Step 3: Crawlability
curl -sL <origin>/robots.txtand/sitemap.xml— present, reachable, and the sitemap lists real URLs.- SPA shells (Vite/CRA) ship a near-empty
<body>; confirm prerendering/SSG (or Next.js SSR) so crawlers receive real content and headings, not just a loading div. - Exactly one
<h1>, sane heading hierarchy, andlangset on<html>.
Step 4: PolicyEngine-specific atoms
- Dual-mode canonical. PE tools run both standalone (Vercel/Pages) and embedded as an iframe/zone on policyengine.org. The
canonicalmust point to the ONE indexable home (the standalone deploy) so the two copies don't compete as duplicate content. - Multi-zone paths. When the tool is a path-mounted zone under policyengine.org, its canonical /
og:url/ sitemap URLs must use the publicpolicyengine.org/<path>URL — never the raw Vercel host or_zones/asset URL. See thepolicyengine-toolsskill (multi-zone integration). .github.ioSearch Console (legacy note). Project sites underpolicyengine.github.io/<repo>can't be independently verified in Search Console (the org owns the apex), so their standalone indexing was always weak. New tools deploy to Vercel — treat anygithub.iotarget as legacy.
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.
- 3d ago First seen · 47 lines · 33 tokens per session scan A f11c1fa62bc5
audit-seo is a command published in the GitHub repository PolicyEngine/policyengine-claude (32 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 854 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.