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/forkpoint/agent-lighthouse/agents-mdgit clone --depth 1 https://github.com/ForkPoint/agent-lighthouseWhat 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 | $0.01803 | $0.01803 |
| Opus 5 | $0.00901 | $0.00901 |
| Sonnet 5 | $0.00361 | $0.00361 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
agent-lighthouse 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 2d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repository
Agent Lighthouse scans a website and reports whether AI agents can discover, read, cite and act on it. This file is the contributor guide for anyone — human or agent — changing the code.
One rule sits above the rest, and everything below is a consequence of it:
An audit may only claim what a source documents. If no vendor documents a consumer, the check does not affect a site's score. Ever.
Layout
| Package | What it is |
|---|---|
packages/core |
The audit registry, the scan orchestrator, the gatherer layer. Everything else consumes it. |
packages/cli |
npx @forkpoint/agent-lighthouse <url> |
packages/report |
Terminal, HTML, JSON and Markdown renderers |
packages/mcp |
MCP server exposing a scan as a tool |
packages/website |
The Astro site, built from the registry and docs/evidence/ at build time |
Audits live in packages/core/src/audits/<category>/<slug>.ts, one of eight
categories: access-crawl-control, agent-interfaces, agentic-commerce,
answer-readiness, content-extraction, machine-discovery,
operability-safety, structured-data. An audit's id is category/slug,
capped at 64 characters by packages/core/src/schemas.ts.
Commands
pnpm build # every package; core must build before check:dossiers
pnpm test # vitest, from the repo root only
pnpm typecheck # tsc --noEmit per package
pnpm lint # oxlint
pnpm check:dossiers # registry <-> dossier agreement, both directions
pnpm check:requires # each audit's `requires` matches what its source reads
pnpm changeset # one per user-visible change
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.
- 2d ago First seen · 163 lines · 1,803 tokens per session scan A 16f85880350b
agent-lighthouse AGENTS.md is an instructions file published in the GitHub repository ForkPoint/agent-lighthouse (16 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,803 tokens to every session, about $0.0090 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 instructions, from other repositories
eGEOagents AGENTS.md
Instructions for mverab/eGEOagents, covering openspec instructions, agents.md, project: e-geo (generative engine optimization), quick start and available commands.
claude-rank CLAUDE.md
Instructions for Houseofmvps/claude-rank, covering claude-rank, project overview, architecture, tech stack and conventions.
seohead-seotools AGENTS.md
AGENTS.md instructions for PavloSEO/seohead-seotools, covering agents.md — public repository contract, product model, start here, architecture and invariants.
aitraffic AGENTS.md
AGENTS.md instructions for devanshug2307/aitraffic, covering agents.md, purpose, canonical commands, terminal contract and evidence contract.
aitraffic CLAUDE.md
Claude Code instructions for devanshug2307/aitraffic, covering claude.md and claude code workflow.
notion-geo-audit CLAUDE.md
Claude Code instructions for nycsav/notion-geo-audit, covering notion-geo-audit — project guide, what this is, live surfaces (all launched, public), architecture and build / deploy.