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/codemie-ai/codemie-code/agents-mdgit clone --depth 1 https://github.com/codemie-ai/codemie-codeWhat 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 | $0.03958 | $0.03958 |
| Opus 5 | $0.01979 | $0.01979 |
| Sonnet 5 | $0.00792 | $0.00792 |
| Haiku 4.5 | $0.00396 | $0.00396 |
Grade A, and why
codemie-code AGENTS.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| `child_process.exec` directly | `exec()` from `src/utils/exec.ts`; npm/spawn helpers in `src/utils/processes.ts` | How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Canonical instruction file for AI agents working in the CodeMie Code repository. This is the shared source of truth. CLAUDE.md should stay minimal and import this file.
Purpose
- CodeMie Code is an umbrella project with multiple agent plugins and provider integrations.
- This file defines the repo-specific workflow, architecture guardrails, policies, and quick references agents should use before changing code.
Core Rules
1. Check Guides First
Before searching the codebase for patterns or implementation details:
- Identify the task type and likely guides.
- Load the relevant P0 guides from
.ai-run/guides/. - Search the codebase only after confirming the guides do not already answer the question.
Why this is mandatory:
- Guides contain curated patterns, conventions, and architectural decisions.
- Guide-first work reduces duplicated investigation and avoids anti-patterns.
Knowledge sources and precedence:
.ai-run/guides/owns workflow and policy: git workflow, quality gates, testing rules, security policies, coding standards.openwiki/(generated, see the OpenWiki section below) owns codebase facts: architecture, CLI surface, plugins, configuration behavior.- On disagreement: guides win for process; source code wins for facts. Report stale guides instead of working around them.
2. Tests Only On Explicit Request
Only write or run tests when the user explicitly asks for it.
Explicit triggers:
- "write tests"
- "run tests"
- "create unit tests"
- "add test coverage"
- "execute test suite"
Do not proactively write, run, or suggest tests otherwise.
3. Git Operations Only On Explicit Request
Only perform git operations when the user explicitly asks for them.
Explicit triggers:
- "commit these changes"
- "create a commit"
- "push to remote"
- "create a branch"
- "create a pull request"
Do not proactively commit, push, branch, or suggest git operations.
4. Environment
- This is a Node.js project. No virtual environment activation is needed.
- Required runtime: Node.js
>=20.0.0. - npm is the package manager.
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 · 296 lines · 3,958 tokens per session scan A 193ba95c2a56
codemie-code AGENTS.md is an instructions file published in the GitHub repository codemie-ai/codemie-code (276 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3,958 tokens to every session, about $0.0198 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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
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.
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 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).
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.