rc

rc is a skill for Claude Code, Codex from rodolfochicone/rc-project. It costs 31 tokens per session (2,032 once invoked), scanned A, original, MIT.

An agent plugin for AI-assisted software development, made up of skills, agents, and hooks. Its project records are plain Markdown files stored in a .rc/ folder and versioned with the code.

In plain words
What is it for?
Use it to understand or organize the plugin's skills, agents, hooks, and project artifacts. It also describes installation and how these parts should be used.
Why use it?
It gives recurring rules, focused working methods, and isolated review tasks a defined place. This helps an AI coding agent follow project practices consistently without needing a separate service or database.

Skill for Claude CodeCodex

Part of the rc plugin — 32 skills, 2 commands, 4 agents, 5 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/rodolfochicone/rc-project/rc
Any agent
npx skills add rodolfochicone/rc-project --skill rc
Clone the repo
git clone --depth 1 https://github.com/rodolfochicone/rc-project

Made for: Claude Code, Codex.

Or install rc, the plugin that ships this one along with the rest of its 32 skills, 2 commands, 4 agents, 5 hooks.

Wrote 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.

agentmods badge for rc

README.md
[![agentmods](https://agentmods.dev/badge/skills/rodolfochicone/rc-project/rc.svg)](https://agentmods.dev/skills/rodolfochicone/rc-project/rc)
Your own site
<a href="https://agentmods.dev/skills/rodolfochicone/rc-project/rc"><img src="https://agentmods.dev/badge/skills/rodolfochicone/rc-project/rc.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,032 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.02032
Opus 5 $0.00015 $0.01016
Sonnet 5 $0.00006 $0.00406
Haiku 4.5 $0.00003 $0.00203

Measured 5d ago against content hash ee1775d06310, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rc 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.

skills/promoted/rc/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RC

An agent plugin for AI-assisted development: skills, agents and hooks, loaded by the host. No CLI, no daemon, no database. Every artifact is plain markdown under a project's .rc/, versioned with the code.

Three primitives, one job each. When a component sits in the wrong one, the tell is in the table:

Primitive Job It's in the wrong place when
hooks deterministic rules that hold every time it is written as prose in a skill and the agent skips it under pressure
skills the disciplines the agent reaches for it is a sequence of other skills
agents context isolation — fan-out, adversarial review it has a catalog entry instead of being spawned from inside a skill

Installation

Install through your host's plugin mechanism; skills, agents and hooks are auto-discovered. Claude Code: /plugin marketplace add rodolfochicone/rc-project, then /plugin install rc@rc-project. GitHub read access is required for the private repo (gh auth login or GH_TOKEN).

The skills

Only skills/promoted/ ships. skills/stacks/ and skills/misc/ stay on disk, editable and greppable, out of the context budget — see Buckets below.

This skill itself carries disable-model-invocation: true: it is a reference for you, so the model never needs to reach it mid-task, and stripping it from the listing costs the budget nothing. That is the second lever after the buckets — a skill only ever invoked by hand pays zero context load.

The build path, in order. Each phase reads what the last one wrote:

Skill Use it to
rc-spec interview an idea into a spec — product intent, then technical design, with ADRs
rc-tickets break that spec into independently implementable tickets with blocking edges
rc-implement build the tickets in dependency order, least code first, then the gate
rc-tdd drive the test side: red → green, one vertical slice, at agreed seams
rc-code-review review on three lenses (standards, spec, delete-list) and fix what it confirms
rc-git ship it: branch, push, PR — confirming each outward-facing step

Read the full file on GitHub · 158 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 5d ago First seen · 158 lines · 31 tokens per session scan A ee1775d06310

Subscribe to this mod's changes

rc is a skill published in the GitHub repository rodolfochicone/rc-project (19 stars, last pushed 29d ago), licensed MIT. It adds 31 tokens to every session and 2,032 once invoked, about $0.0002 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.