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/cyranob/web-forager/claude-mdgit clone --depth 1 https://github.com/CyranoB/web-foragerWrote 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/cyranob/web-forager/claude-md)<a href="https://agentmods.dev/instructions/cyranob/web-forager/claude-md"><img src="https://agentmods.dev/badge/instructions/cyranob/web-forager/claude-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 | $0.00093 | $0.00093 |
| Opus 5 | $0.00046 | $0.00046 |
| Sonnet 5 | $0.00019 | $0.00019 |
| Haiku 4.5 | $0.00009 | $0.00009 |
Grade A, and why
web-forager CLAUDE.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 4d 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.
What it actually says
@AGENTS.md
Claude Code
- Keep progress updates brief and report only material findings or changes in direction.
- Complete the requested scope without silently expanding it; ask only when materially different interpretations would produce different work.
- Delegate only substantial, independent work that benefits from parallel execution. Perform routine implementation and validation directly.
- Lead the final response with the outcome, followed by essential evidence, caveats, and next steps.
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.
- 4d ago First seen · 13 lines · 93 tokens per session scan A c3e728d26692
web-forager CLAUDE.md is an instructions file published in the GitHub repository CyranoB/web-forager (10 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session, about $0.0005 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
ddgs AGENTS.md
Instructions for deedy5/ddgs, covering agents.md — guide for coding agents, project overview, build / lint / test commands, setup (creates .venv, installs dev deps) and lint (ruff check + mypy type-check).
memory AGENTS.md
Instructions for sunbeamdotpt/memory, covering sunbeam-memory — agent guide, project overview, runtime modes, semantic memory search (optional) and technology stack.
mcp-deep-search CLAUDE.md
Claude Code instructions for just-every/mcp-deep-search, covering claude.md, project overview, core modules & files, commands and development.
gsc-mcp-server copilot-instructions.md
Instructions for AppsYogi-com/gsc-mcp-server, covering gsc-mcp copilot instructions, project overview, architecture, development commands and code conventions.
jinaai-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/jinaai-mcp-server, covering mcp-ts-template: architectural standard & developer mandate, preamble, i. core architectural principles, 1. the logic throws, the handler catches and 2. structured, traceable operations.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.