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 skills/rodolfochicone/rc-project/rcnpx skills add rodolfochicone/rc-project --skill rcgit 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/skills/rodolfochicone/rc-project/rc)<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>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 | $0.00031 | $0.02032 |
| Opus 5 | $0.00015 | $0.01016 |
| Sonnet 5 | $0.00006 | $0.00406 |
| Haiku 4.5 | $0.00003 | $0.00203 |
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.
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 |
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.
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 · 158 lines · 31 tokens per session scan A ee1775d06310
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.
Other skills, from other repositories
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
duckduckgo-search
Free keyless web, news, and image search via ddgs.
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.