Borrowing it
Nothing to install: this file belongs to gpt-cmdr/ras-commander. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gpt-cmdr/ras-commander/main/AGENTS.mdgit clone --depth 1 https://github.com/gpt-cmdr/ras-commanderWrote 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/gpt-cmdr/ras-commander/agents-md)<a href="https://agentmods.dev/instructions/gpt-cmdr/ras-commander/agents-md"><img src="https://agentmods.dev/badge/instructions/gpt-cmdr/ras-commander/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/gpt-cmdr/ras-commander/agents-md"><img src="https://agentmods.dev/badge/instructions/gpt-cmdr/ras-commander/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04311 | $0.04311 |
| Opus 5.5 | $0.01724 | $0.01724 |
| Sonnet 5.5 | $0.00862 | $0.00862 |
| Haiku 4.5 | $0.00431 | $0.00431 |
Grade A, and why
ras-commander 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 22d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ras-commander Agent Contract
This file is the canonical shared instruction contract for repository-local coding agents.
Harness Loading
- Codex reads this file directly.
- Claude Code must import this file from the matching
CLAUDE.md. - The
AGENTS.mdhierarchy is the shared source of truth. Read the nearest file first, then inherit parentAGENTS.mdfiles. CLAUDE.mdfiles are loaders and Claude-specific adapters. They must not become a second documentation system.- Shared rules belong in the
AGENTS.mdhierarchy or a shared skill corpus. Do not leave a rule that Codex also needs only in.claude/rules/. .claude/rules/is a Claude preload layer. It can restate or accelerate shared guidance, but it is not the canonical shared contract..claude/MANIFEST.mdis the current Claude component registry. It is useful for discovery, but it is not the source of truth for shared behavior..claude/agents/contains Claude-native delegation roles. Keep them thin and point them back to shared instructions..claude/settings.jsonand.codex/hooks.jsonare thin hook adapters that call shared hook logic underscripts/agent_hooks/.- Primary first-class harnesses in this repository are Claude Code and Codex.
Current Codex Skill Status
- Codex auto-loads
AGENTS.md. - Codex skill discovery can be enabled locally by generating
.agents/skills/links:python scripts/agent_framework/sync_codex_skill_bridge.py
- The bridge links explicitly allowlisted shared-domain skills from
.claude/skills/and Codex-native adapter skills from.agents/native-skills/. - A shared skill must declare
shared_corpus: true,harness_scope: shared, acceptedsource_owner, and acceptedsecurity_reviewmetadata before the bridge exposes it to Codex. - A Codex-native adapter skill must declare
shared_corpus: false,harness_scope: codex_only, acceptedsource_owner, and acceptedsecurity_reviewmetadata. - Skills marked
shared_corpus: falseorharness_scope: claude_onlyare excluded. .agents/skills/*entries are generated symlinks or Windows junctions, not source files. Do not edit them directly.- Shared skill sources remain
.claude/skills/until a later migration changes that explicitly. - Codex-only provider handoff skills, such as Claude Code QAQC invocation, live in
.agents/native-skills/.
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.
- 22d ago Changed · +10 lines · +163 tokens per session aa95880bb0f1
- 25d ago Changed · +55 lines · +797 tokens per session 0194018305e3
- 1mo ago Changed · +9 tokens per session 3a0ed4705f47
- 1mo ago Changed · +11 lines · +125 tokens per session c837c865c632
- 1mo ago Changed · +25 lines · +350 tokens per session 31f86c327e6e
- 1mo ago First seen · 175 lines · 2,867 tokens per session scan A 344e436df651
ras-commander AGENTS.md is an instructions file published in the GitHub repository gpt-cmdr/ras-commander (88 stars, last pushed today), licensed MIT. It adds 4,311 tokens to every session, about $0.0172 per session on Opus 5.5. 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 2026-09-03.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.