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/isaac-levine/forage/claude-mdgit clone --depth 1 https://github.com/isaac-levine/forageWrote 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/isaac-levine/forage/claude-md)<a href="https://agentmods.dev/instructions/isaac-levine/forage/claude-md"><img src="https://agentmods.dev/badge/instructions/isaac-levine/forage/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 5.1 | $0.00919 | $0.00919 |
| Opus 5 | $0.00460 | $0.00460 |
| Sonnet 5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
forage 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 5d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forage
Self-improving tool discovery for AI agents. An MCP server that lets agents find, install, and learn to use new tools without human intervention or restarts.
Project Overview
Forage is a gateway/proxy MCP server. It's installed once and acts as a hub — when an agent discovers and installs a new tool through Forage, Forage starts it as a subprocess, wraps its capabilities, and emits list_changed notifications so the agent can use it immediately.
Core Flow
- Agent calls
forage_search("postgres database")to find tools - Agent calls
forage_install("@modelcontextprotocol/server-postgres", { confirm: true })to install - Forage starts the server as a child process, wraps its tools, notifies the agent
- Agent calls
forage_learn(...)to persist instructions in CLAUDE.md - Next session: Forage auto-starts from
~/.forage/manifest.json
Architecture
src/
├── server.ts # MCP server entry — tool registration + proxy lifecycle
├── cli.ts # CLI: init, search, list
├── tools/ # One file per MCP tool (search, evaluate, install, learn, status, uninstall)
├── registries/ # API clients for Official MCP Registry, Smithery, npm
├── proxy/
│ ├── manager.ts # Spawns/stops child MCP servers via StdioClientTransport
│ └── wrapper.ts # Namespaces child tools as foraged__<server>__<tool>
├── rules/
│ ├── detector.ts # Detects CLAUDE.md, AGENTS.md, .cursor/rules/
│ └── writer.ts # Adds/removes tool blocks with <!-- forage:name --> markers
└── persistence/
├── manifest.ts # ~/.forage/manifest.json read/write
└── log.ts # ~/.forage/install-log.json audit trail
Tech Stack
- TypeScript with ES modules (
"type": "module") @modelcontextprotocol/sdk— MCP server and client- Node.js >= 18 (uses native
fetch,AbortSignal.timeout) - No runtime dependencies beyond the MCP SDK (which bundles Zod)
Development
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.
- 5d ago First seen · 91 lines · 919 tokens per session scan A 512ad0cd6405
forage CLAUDE.md is an instructions file published in the GitHub repository isaac-levine/forage (16 stars, last pushed 6mo ago), licensed MIT. It adds 919 tokens to every session, about $0.0046 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
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.