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 instructions/gabrielamz/web-anatomy/agents-mdgit clone --depth 1 https://github.com/GabrielAmz/web-anatomyWrote 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/instructions/gabrielamz/web-anatomy/agents-md)<a href="https://agentmods.dev/instructions/gabrielamz/web-anatomy/agents-md"><img src="https://agentmods.dev/badge/instructions/gabrielamz/web-anatomy/agents-md.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 | $0.01140 | $0.01140 |
| Opus 5 | $0.00570 | $0.00570 |
| Sonnet 5 | $0.00228 | $0.00228 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
web-anatomy AGENTS.md 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 6d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Web Anatomy
This file tells AI coding agents how to use the Web Anatomy skills pack. It works with any agent that reads .agents/skills/ per the Agent Skills spec.
Install
npx skills add GabrielAmz/web-anatomy
This copies every skill in this repo into .agents/skills/ in your project. The same files are read by:
- Claude Code
- OpenAI Codex
- Cursor
- Windsurf
A skill named write-page installs to .agents/skills/write-page/SKILL.md regardless of which agent loads it.
On Claude Code you can also install as a plugin. Claude Code then knows the installed version and when a newer one ships (update with /plugin update web-anatomy, or enable auto-update for the marketplace). Plugin skills are namespaced, e.g. /web-anatomy:write-page.
/plugin marketplace add GabrielAmz/web-anatomy
/plugin install web-anatomy
Connecting the hosted Web Anatomy MCP for live benchmark data is optional: sign in at https://www.webanatomy.ai/dashboard/mcp to get your token + per-IDE config. The skills run fully without it. To browse the benchmark itself, the public scored sections gallery is at https://www.webanatomy.ai/best-landing-pages/sections.
How to invoke a skill
Just describe what you want. The agent matches your phrasing against the description: field in each SKILL.md and loads the right one.
"Improve this pricing page against strong B2B fintech examples."
→ loads write-page
"Show me strong SaaS pricing examples."
→ loads find-examples
"Research how top AI tools handle testimonial sections."
→ loads research-best-practices
"Build me a new pricing page."
→ loads find-examples (pick an exemplar) → write-page build mode (outline + copy)
"Assemble this into a wireframe I can share."
→ loads build-page
"Help me set up Web Anatomy for my project."
→ loads webanatomy-setup
Or invoke by slug directly:
/webanatomy-setup
/find-examples
/audit-page
/research-best-practices
/write-page
/build-page
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.
- 6d ago First seen · 105 lines · 1,140 tokens per session scan A 0a4296931cac
web-anatomy AGENTS.md is an instructions file published in the GitHub repository GabrielAmz/web-anatomy (8 stars, last pushed 2mo ago), licensed MIT. It adds 1,140 tokens to every session, about $0.0057 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 instructions, from other repositories
mcp AGENTS.md
AGENTS.md instructions for SentientUI/mcp, covering sentientui — ai agent guide, key concepts, auth, tool quick reference and canonical workflows.
funnel-architect-plugin CLAUDE.md
Instructions for ominou5/funnel-architect-plugin, covering funnel architect, how to delegate, workflow, funnel hacking workflow and skills (in skills/).
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.