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/codename-11/arc/agents-mdgit clone --depth 1 https://github.com/Codename-11/ARCWhat 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 | $0.03620 | $0.03620 |
| Opus 5 | $0.01810 | $0.01810 |
| Sonnet 5 | $0.00724 | $0.00724 |
| Haiku 4.5 | $0.00362 | $0.00362 |
Grade A, and why
ARC 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.
This is a copy
88% identical to SubFrame AGENTS.md — 41 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARC - SubFrame Project
This project is managed with SubFrame. AI assistants should follow the rules below to keep documentation up to date.
Note: This file is named
AGENTS.mdto be AI-tool agnostic. CLAUDE.md and GEMINI.md contain a reference to this file.
Core Working Principle
Only do what the user asks. Do not go beyond the scope of the request.
- Implement exactly what the user requested — nothing more, nothing less.
- Do not change business logic, flow, or architecture unless the user explicitly asks for it.
- If a user asks for a design change, only change the design. Do not refactor, restructure, or modify functionality alongside it.
- If you have additional suggestions or improvements, present them as suggestions to the user. Never implement them without approval.
- The user's request must be completed first. Additional ideas come after, as proposals.
Relationship to Native AI Tools
SubFrame enhances native AI coding tools — it does not replace them.
Claude Code works exactly as normal. Built-in features (/init, /commit, /review-pr, /compact, /memory, CLAUDE.md) are fully supported. CLAUDE.md is Claude Code's native instruction file — users can add their own tool-specific instructions freely. SubFrame adds a small backlink reference pointing to this AGENTS.md file using HTML comment markers (<!-- SUBFRAME:BEGIN --> / <!-- SUBFRAME:END -->). SubFrame will never overwrite user content in CLAUDE.md.
Gemini CLI works exactly as normal. Built-in features (/init, /model, /memory, /compress, /settings, GEMINI.md) are fully supported. GEMINI.md is Gemini CLI's native instruction file — same backlink approach as CLAUDE.md. Users can add their own instructions freely and SubFrame won't overwrite them.
Codex CLI gets SubFrame context via a wrapper script at .subframe/bin/codex that injects AGENTS.md as an initial prompt.
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 · 387 lines · 3,620 tokens per session scan A 58badfd9328d
ARC AGENTS.md is an instructions file published in the GitHub repository Codename-11/ARC (3 stars, last pushed 2mo ago), licensed MIT. It adds 3,620 tokens to every session, about $0.0181 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to SubFrame AGENTS.md, differing in 41 lines, and is treated as a copy.
Other instructions, from other repositories
apm python.instructions.md
Python development guidelines.
amfs CLAUDE.md
Instructions for raia-live/amfs, covering amfs memory — agent instructions, available mcp tools, identity, brain tools (agent-scoped) and shared knowledge tools.
copilot-proxy-api CLAUDE.md
Instructions for voidsteed/copilot-proxy-api, covering claude.md, project overview, common commands, architecture and entry points & cli structure.
CodexPotter AGENTS.md
Instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.