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/everyinc/compound-engineering-plugin/agents-mdgit clone --depth 1 https://github.com/EveryInc/compound-engineering-pluginWhat 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 | $0.12196 | $0.12196 |
| Opus 5 | $0.06098 | $0.06098 |
| Sonnet 5 | $0.02439 | $0.02439 |
| Haiku 4.5 | $0.01220 | $0.01220 |
Grade A, and why
compound-engineering-plugin 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 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This repository is the root of the compound-engineering coding-agent plugin and the marketplace/catalog metadata used to distribute it.
It also contains:
- the Bun/TypeScript CLI that converts Claude Code plugins into other agent platform formats
- shared release and metadata infrastructure for the CLI, marketplace, and plugin
AGENTS.md is the canonical repo instruction file. Root CLAUDE.md is a symlink to AGENTS.md so Claude Code and other tools that look for CLAUDE.md still find it at the expected path. Keep that symlink (do not replace it with a regular file): a real root CLAUDE.md makes claude plugin validate --strict fail because this checkout is also the plugin root.
Quick Start
bun install
bun run test # full test suite (also runs in CI; `--parallel` across worker processes)
bun run release:validate # plugin/marketplace consistency (also runs in CI)
bun run plugin:validate # Claude marketplace + plugin schema (also runs in CI; needs `claude` on PATH)
Codex Local Plugin Development
When testing current skill files in Codex, run the repository workflow from the checkout or worktree you intend to test:
bun run codex:dev -- local # link this worktree's skills and remove CE plugin installs
bun run codex:dev -- status # show local/remote state and checkout provenance
bun run codex:dev -- remote # restore the official marketplace-backed plugin
bun run codex:dev -- remove # remove both supported CE installation surfaces
refresh is an idempotent alias for local. Local mode manages only the exact $CODEX_HOME/skills/compound-engineering-local symlink and Compound Engineering plugin IDs; it must not alter unrelated user skills. The symlink includes modified and untracked files from the selected worktree. Start a new Codex session after switching installation modes. Current Codex versions detect direct skill edits automatically; restart only if an edit does not appear. For live local testing, use this workflow instead of adding the repository as a marketplace: a marketplace install caches a snapshot, while local mode links the current skill files.
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 · 361 lines · 12,196 tokens per session scan A b9dd6054ee53
compound-engineering-plugin AGENTS.md is an instructions file published in the GitHub repository EveryInc/compound-engineering-plugin (24,696 stars, last pushed 2d ago), licensed MIT. It adds 12,196 tokens to every session, about $0.0610 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
spec-kit 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.
blog CLAUDE.md
Claude Code instructions for gbmhunter/blog, covering units in latex/katex equations, multiplication in latex/katex equations, katex gotchas (beyond units/multiplication above), images and diagrams and mdx components.
techdrawai-skills CLAUDE.md
Claude Code instructions for MeltFlexDevs/techdrawai-skills, covering notes for agents working in this repository, layout and rules.
thousandeyes-ai-agents-toolkit AGENTS.md
Instructions for thousandeyes/thousandeyes-ai-agents-toolkit, covering agents, scope and intent, repository structure guidance, shared skill mirroring guidance and cursor plugin-specific guidance.
vaultpilot-mcp CLAUDE.md
Claude Code instructions for agenthill/vaultpilot-mcp, covering chat output — walletconnect pairing, crypto/defi transaction preflight checks, pre-sign gate surface sweeps, per-protocol prepare vs. preparecustomcall cutoff and git/pr workflow — project-specific.
constellation-mcp CLAUDE.md
Claude Code instructions for ShiftinBits/constellation-mcp, a project described as: Code Intelligence Platform for AI Coding Assistants.