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/dotnetpower/infomesh/copilot-instructionsgit clone --depth 1 https://github.com/dotnetpower/infomeshWhat 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 | $0.13682 | $0.13682 |
| Opus 5 | $0.06841 | $0.06841 |
| Sonnet 5 | $0.02736 | $0.02736 |
| Haiku 4.5 | $0.01368 | $0.01368 |
Grade A, and why
infomesh copilot-instructions.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 — 812 lines — stays where its author put it; the contents beside it link to each section on GitHub.
InfoMesh — Copilot Instructions
Project Overview
InfoMesh is a fully decentralized P2P search engine designed exclusively for LLMs. It crawls, indexes, and searches the web via a peer-to-peer network and exposes results through MCP (Model Context Protocol) — no human-facing UI required.
Mission: InfoMesh does not compete with commercial search providers. These companies serve human search at massive scale with ads-based monetization. InfoMesh provides minimal, sufficient search capabilities for LLMs — for free, via MCP — democratizing real-time web access for AI assistants without per-query billing. It is a community-driven public utility, complementary to existing search providers.
Core Principles
| Principle | Description |
|---|---|
| Fully Decentralized | No central server. Every node is both a hub and a participant. |
| LLM-First | No browser UI. Pure text API optimized for LLM consumption. |
| Contribute = Reward | More crawling contribution → more search quota (cooperative tit-for-tat model). |
| Offline-Capable | Local index is searchable without internet. |
| Privacy | Search queries are never recorded centrally. |
Tech Stack
| Layer | Technology | Notes |
|---|---|---|
| Language | Python 3.12+ | Use modern Python features (type hints, match, type statement, StrEnum, etc.) |
| P2P Network | libp2p (py-libp2p) | Optional (pip install 'infomesh[p2p]'). DHT, Noise encryption built-in. Uses trio, not asyncio — see note below |
| DHT | Kademlia | Distributed hash table for index & crawl coordination |
| Crawling | httpx + asyncio | Async-first HTTP client |
| HTML Parsing | trafilatura | Best accuracy for main-content extraction |
| Keyword Index | SQLite FTS5 | Zero-install, embedded full-text search |
| Vector Index | ChromaDB | Semantic search with embeddings |
| MCP Server | mcp-python-sdk | VS Code / Claude / Cursor / Windsurf integration |
| Admin API | FastAPI | Local status & config endpoints |
| Serialization | msgpack | Faster and smaller than JSON |
| Compression | zstd | Level-tunable compression; dictionary mode for similar documents |
| Local LLM | ollama / llama.cpp | Optional local summarization (Qwen 2.5, Llama 3.x, etc.) |
| Logging | structlog | Structured logging for all library code |
| Package Manager | uv | Fast Python package/project manager (replaces pip/venv) |
| Build Backend | hatchling | PEP 517 build backend for PyPI distribution |
| JS Rendering | Playwright | Optional headless Chromium (pip install 'infomesh[browser]') |
| CJK Tokenization | jieba | Optional Chinese segmentation (pip install 'infomesh[cjk]') |
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 · 812 lines · 13,682 tokens per session scan A 77bc01122659
infomesh copilot-instructions.md is an instructions file published in the GitHub repository dotnetpower/infomesh (5 stars, last pushed 3mo ago), licensed MIT. It adds 13,682 tokens to every session, about $0.0684 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
pumpfun-bonkfun-bot CLAUDE.md
Instructions for chainstacklabs/pumpfun-bonkfun-bot, covering agent guide, ground rules, layout, naming inside learning-examples/ and commands.
evmole AGENTS.md
Instructions for cdump/evmole: EVMole extracts structured facts from deployed EVM runtime bytecode.
VaultysClaw CLAUDE.md
Instructions for vaultys/VaultysClaw, covering claude.md, commands, development, demo / simulator and build.
plamen CLAUDE.md
Instructions for PlamenTSV/plamen, covering plamen — security auditor, execution model, reference files and shared.
solana-developer-platform AGENTS.md
Instructions for solana-foundation/solana-developer-platform, covering solana developer platform, repo layout, source of truth, generated files and public vs internal surfaces.
behavioral-prediction-mcp AGENTS.md
Instructions for ChainAware/behavioral-prediction-mcp, covering chainaware subagent index, agent directory, chainaware-wallet-auditor, chainaware-fraud-detector and chainaware-rug-pull-detector.