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/rodolfochicone/rc-project/agents-mdgit clone --depth 1 https://github.com/rodolfochicone/rc-projectWrote 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/rodolfochicone/rc-project/agents-md)<a href="https://agentmods.dev/instructions/rodolfochicone/rc-project/agents-md"><img src="https://agentmods.dev/badge/instructions/rodolfochicone/rc-project/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 | $0.01574 | $0.01574 |
| Opus 5 | $0.00787 | $0.00787 |
| Sonnet 5 | $0.00315 | $0.00315 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
rc-project 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 4d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents working in this repository. RC is a pure agent plugin — skills, agents and hooks, plus a few small Node/Bash helpers. No compiled binary, no build step, no CLI.
Project overview
RC drives AI-assisted development — spec → tickets → implement → review → ship — through components
the agent host loads. It ships as a Claude Code plugin, and nothing in the shipped set is coupled to a
host-exclusive tool; all runtime state is plain files under a project's .rc/.
Three primitives, one job each: hooks hold rules that must apply every time, skills hold the disciplines the agent reaches for, agents exist for context isolation. A component in the wrong primitive is the most common defect in this repo — a sequence of skills is not a skill, and an every-time rule written as prose is not enforced.
Repository layout
| Path | Contents |
|---|---|
skills/promoted/<name>/SKILL.md |
The 17 shipped skills. Each: frontmatter + optional references/, assets/, scripts/. |
skills/stacks/<name>/ |
Stack skills, not shipped — loaded by name when working that stack. |
skills/misc/<name>/ |
Kept on disk, not shipped. Zero context cost. |
agents/<name>.md |
The four council archetypes, dispatched by rc-council. |
commands/<name>.md |
Two thin prompt macros with no skill behind them. |
hooks/hooks.json + hooks/scripts/*.sh |
Lifecycle hooks (bash), gated via _lib.sh. |
scripts/*.mjs |
plugin-smoke.mjs (the gate), validate-tasks.mjs, lessons.mjs. |
docs/ |
Human-facing docs. |
.claude-plugin/ |
plugin.json + marketplace.json. |
The budget that shapes everything
Every shipped description loads in every session, against the host's skill-listing budget
(skillListingBudgetFraction, 1% of context by default). Over budget, the host drops descriptions
and the skill goes mute — present by name, nothing to match against. That is why:
- Only
skills/promoted/is inplugin.json. Adding tostacks/ormisc/is free; promoting is the deliberate trade. - Promoted descriptions are capped at 150 characters, trigger plus anti-trigger.
PROMOTED_CEILINGinplugin-smoke.mjsis 17. To cross it: merge one, demote one, or raise the constant on purpose.
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.
- 4d ago First seen · 106 lines · 1,574 tokens per session scan A 01c41fe9693b
rc-project AGENTS.md is an instructions file published in the GitHub repository rodolfochicone/rc-project (19 stars, last pushed 28d ago), licensed MIT. It adds 1,574 tokens to every session, about $0.0079 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
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.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
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).