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/juan294/cc-rpi/agents-mdgit clone --depth 1 https://github.com/juan294/cc-rpiWrote 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/juan294/cc-rpi/agents-md)<a href="https://agentmods.dev/instructions/juan294/cc-rpi/agents-md"><img src="https://agentmods.dev/badge/instructions/juan294/cc-rpi/agents-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 | $0.01023 | $0.01023 |
| Opus 5 | $0.00511 | $0.00511 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
cc-rpi 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 5d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project: cc-rpi
Codex Compatibility
This repository is the cc-rpi blueprint. It is authored for Claude Code,
but this AGENTS.md file makes the same methodology operable in Codex.
Source of truth for this repo:
CLAUDE.md-- repo overview, workflow, commands, git conventions.claude/commands/*.md-- active project-level workflow commandstemplates/commands/*.md-- canonical exported command templates.claude/rules/*.md-- repo-local rulestemplates/rules/*.md-- canonical exported rule templates.claude/skills/*/SKILL.mdandtemplates/skills/*/SKILL.md-- skill content.codex/skills/*/SKILL.md-- Codex-only skills that intentionally stay outside.claude/skills/
Command Dispatch
When the user invokes a slash-style command:
- Use
.claude/commands/<name>.mdwhen it exists in this repo - For blueprint-lifecycle commands that only exist in templates
(
/bootstrap,/adopt,/update,/detach), use the matching file intemplates/commands/ - Read the command file completely before acting
- Follow it as the workflow spec, translating Claude-specific mechanics to Codex equivalents when needed
Claude-to-Codex Translation
/simplify-- prefercodex-simplifywhen available; otherwise run a dedicated post-implementation quality pass for reuse, cleanliness, and efficiency/batch-- use parallel agents and isolated worktrees for[batch-eligible]work/worktreeorEnterWorktree-- implement in an isolated worktreeTask/Exploreagents -- use Codex subagents or equivalent parallel exploration with the same role splitAskUserQuestion-- ask the user directly only when the repo cannot answer safely/clearand/compact-- treat as context-management guidance
Rules and Skills
- Always follow
CLAUDE.md - Always read
.claude/rules/rpi-details.md - Read
.claude/rules/git-recipes.mdfor git-heavy tasks - Read
.claude/rules/contributing.mdwhen changing docs, templates, or patterns - Run
scripts/install.shafter pulling cc-rpi to refresh the user-level commands, orscripts/install.sh --checkto see whether they have drifted - Load
.claude/skills/drawio/SKILL.mdwhen diagram work is requested - Load
.codex/skills/codex-simplify/SKILL.mdwhen a Codex session needs a/simplify-style cleanup pass
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.
- 5d ago First seen · 86 lines · 1,023 tokens per session scan A 9762e8ac19df
cc-rpi AGENTS.md is an instructions file published in the GitHub repository juan294/cc-rpi (5 stars, last pushed 4d ago), licensed MIT. It adds 1,023 tokens to every session, about $0.0051 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 2026-08-31.
Other instructions, from other repositories
ai-dial-core CLAUDE.md
Claude Code instructions for epam/ai-dial-core, covering claude.md, build & run, set credentials via environment variables, build (skip tests) and run all tests.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.