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/coralogix/canopy/claude-mdgit clone --depth 1 https://github.com/coralogix/canopyWrote 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/coralogix/canopy/claude-md)<a href="https://agentmods.dev/instructions/coralogix/canopy/claude-md"><img src="https://agentmods.dev/badge/instructions/coralogix/canopy/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 | $0.00885 | $0.00885 |
| Opus 5 | $0.00443 | $0.00443 |
| Sonnet 5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
canopy 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 6d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Canopy is infrastructure for building agent-native applications with pluggable runtimes. The core abstraction is the Workspace — an isolated directory-based workspace that defines an agent's behavior, memory, and capabilities through .md files and runtime configuration.
How it works: Developers author a template folder (CLAUDE.md, skills, agents, tool configs). Canopy infra provisions a Workspace directory for every user from that template, handles triggers (scheduler, chat, webhooks), and spawns isolated runtime instances per user. The runtime returns results as stdout; Canopy captures and routes the output. Claude Code is the default runtime; any coding agent can be configured via CANOPY_RUNTIME.
Philosophy: Documents are database. Skills are functions. The LLM is the CPU. Code is only for I/O.
Doc purpose: These docs are an implementation spec — copy this folder into your project, point Claude at it, and it can build the entire Canopy platform for your agent.
Status: Documentation + templates + CLI (cli/). 90+ tests, CI via GitHub Actions, PyPI-ready packaging.
Repository Structure
specs/01-architecture.mdthroughspecs/07-adoption-guide.md— Framework specification docstemplates/— Starter templates (CLAUDE.md.template, skill.md.template, tool-config.md.template, settings.json.template, workspace-structure.md, version.json)examples/— Example agent templates (codebase-navigator,release-pilot,daily-standup)cli/— Developer CLI for managing workspaces (create, run, connect, delete)
Core Architecture
Configurable Runtime: Every Workspace is a directory. Canopy spawns a runtime process against that directory per trigger. The runtime handles context loading, skills, agents, MCP tools, memory, hooks, and sandboxing. No custom runtime code. Runtime is configurable via CANOPY_RUNTIME (default: claude-code) — see specs/06-runtime.md.
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.
- 6d ago First seen · 48 lines · 885 tokens per session scan A b1471a286b17
canopy CLAUDE.md is an instructions file published in the GitHub repository coralogix/canopy (89 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 885 tokens to every session, about $0.0044 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.