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/tripcher/canon/agents-mdgit clone --depth 1 https://github.com/tripcher/canonWhat 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 | $0.03773 | $0.03773 |
| Opus 5 | $0.01886 | $0.01886 |
| Sonnet 5 | $0.00755 | $0.00755 |
| Haiku 4.5 | $0.00377 | $0.00377 |
Grade A, and why
canon 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 yesterday.
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 — 540 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - AI Agent Development Guide
Project: mcp-canon
Purpose: MCP server providing architectural patterns and best practices to LLM agents via RAG
License: MIT
Overview of Project
mcp-canon is a Model Context Protocol (MCP) server that provides architectural consultant capabilities to AI agents. It uses Retrieval-Augmented Generation (RAG) to serve best practices and coding guidelines from a vector database.
Key Features
- Bundled knowledge base with pre-indexed guides for Python, Docker, Kubernetes, etc.
- Custom indexing capability for creating your own knowledge bases from Markdown files
- HTTP server mode for remote access and multi-client scenarios
- Offline-first design — all data is local, no external API calls required
Core Architecture
┌──────────────────────────────────────────────────────────────────┐
│ DEV ENVIRONMENT (Indexing) │
│ Sources (MD/PDF/URL) → Docling → LangChain Chunking → LanceDB │
└──────────────────────────────────────────────────────────────────┘
↓
┌──────────────────────────────────────────────────────────────────┐
│ USER ENVIRONMENT (Runtime) │
│ MCP Client → FastMCP Server → SearchEngine → LanceDB Vectors │
└──────────────────────────────────────────────────────────────────┘
Technologies
Language
- Python 3.11+ (supports 3.11, 3.12, 3.13)
Main Frameworks & Libraries
| Component | Library | Purpose |
|---|---|---|
| MCP Protocol | mcp |
Communication with LLM clients |
| Vector Database | lancedb |
Embedded vector storage |
| Embeddings | fastembed |
ONNX-based text vectorization (nomic-embed-v1.5-Q default) |
| CLI | typer |
Command-line interface |
| Data Validation | pydantic |
Schema validation |
| HTTP Server | uvicorn + starlette |
Streamable HTTP (optional) |
| Document Parsing | docling |
PDF/DOCX/HTML conversion (indexing only) |
| Text Splitting | langchain-text-splitters |
Markdown chunking (indexing only) |
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.
- yesterday First seen · 540 lines · 3,773 tokens per session scan A a2f4d4330c32
canon AGENTS.md is an instructions file published in the GitHub repository tripcher/canon (0 stars, last pushed 5mo ago), licensed MIT. It adds 3,773 tokens to every session, about $0.0189 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
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
spellbook AGENTS.md
Instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
open-supermarkets AGENTS.md
Instructions for abracadabra50/open-supermarkets, covering agent integration guide, supported frameworks, quick integration, 1. add as skill and 2. agent calls commands.
helm copilot-instructions.md
Instructions for PetePeter/helm, covering gamepad-cli-hub — copilot instructions, project purpose, system overview, data flow pipeline and key controls.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
sruja AGENTS.md
Instructions for sruja-ai/sruja, covering ⚡ quick reference (top 5 commands), architecture setup (ai agent workflow), step 1: understand the codebase, step 2: classify the architecture and step 3: generate ide context.