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 skills add rodolfochicone/rc-project --skill rc-gangit 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-gan)<a href="https://agentmods.dev/skills/rodolfochicone/rc-project/rc-gan"><img src="https://agentmods.dev/badge/skills/rodolfochicone/rc-project/rc-gan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rodolfochicone/rc-project/rc-gan"><img src="https://agentmods.dev/badge/skills/rodolfochicone/rc-project/rc-gan.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00084 | $0.01011 |
| Opus 5 | $0.00042 | $0.00505 |
| Sonnet 5 | $0.00017 | $0.00202 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
rc-gan 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 9d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GAN Harness (generator ↔ evaluator)
make verify proves a change is correct. It says nothing about whether a UI is well-designed, a CLI is pleasant, or copy lands. This skill closes that gap with an adversarial loop: a generator builds/improves the artifact, an independent evaluator exercises the running result and scores it against an explicit rubric, and the loop iterates on the evaluator's concrete feedback until the score clears a threshold or stops improving. The two roles are kept separate on purpose — nothing grades its own work, and the evaluator is fresh each round so it never anchors on the last verdict.
Required Inputs
- Target: what to build or improve (a feature, a screen, a command's UX, a document).
- Optional rubric: dimensions + weights. If absent, derive one in Phase 0.
- Optional --threshold (default
7.0on a 1–10 scale) and --max-iterations (default8).
Phase 0 — Spec & rubric
Before iterating, write down what "good" means so scoring is not vibes:
- Expand the target into a short spec: what it must do and the quality bar it must hit.
- Define a weighted rubric of 3–5 dimensions summing to 1.0. Pick dimensions that fit the artifact, e.g. for a UI:
design 0.3 · craft 0.3 · functionality 0.2 · originality 0.2; for a CLI:ergonomics 0.4 · clarity 0.3 · correctness 0.2 · discoverability 0.1. Each dimension scored 1–10; final = Σ(score × weight). - State how the artifact will be exercised (run it for real): a web UI via a browser/dev server, a CLI by running commands, a doc by reading it against its goal. Evaluation is of the running thing, never of the source alone.
The loop
Repeat until stop condition. Track score per iteration.
- Generate — implement or improve the artifact to satisfy the spec and address the previous iteration's feedback. Keep it real and runnable; leave the artifact in a runnable state. Run the project's correctness gate (
make verifyor equivalent) so quality work never ships a broken build. - Evaluate (fresh & independent) — spawn a separate reviewer (a subagent / fresh context — do not reuse the generator's reasoning). It must:
- Actually exercise the running artifact against the "how to exercise" plan from Phase 0.
- Score each rubric dimension 1–10 with one concrete justification each, then compute the weighted total.
- Write specific, addressable defects ("the primary button has no hover state", "
--helpdoesn't list thesyncsubcommand"), not vague notes. Penalize generic AI-slop (default gradients, lorem-ipsum, boilerplate layouts).
- Decide:
- Pass — weighted score ≥ threshold → stop, report success.
- Plateau — score improved by < 0.3 for 2 consecutive iterations → stop; report the plateau and the best version (more iterations won't help; escalate to the user).
- Cap — reached
--max-iterations→ stop; report the best version and remaining gaps. - Otherwise feed the evaluator's defects into the next Generate.
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.
- 9d ago First seen · 53 lines · 84 tokens per session scan A 8f5b53cba540
rc-gan is a skill published in the GitHub repository rodolfochicone/rc-project (19 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,011 once invoked, about $0.0004 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
taiyi-dev
A software-development stage that implements planned tasks using test-driven development, or TDD: write a failing test, make it pass, then improve the code. It checks the task plan, dependencies, file boundaries, and required completion evidence.
taiyi-test
A project workflow skill for verifying an implementation and producing a TEST.md record. TDD means writing a failing test, implementing the change, and then making the test pass; this skill checks that process and other regression cases.
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
taiyi-diagram-arch
A workflow for turning written system or product architecture into readable, version-controlled diagrams using Mermaid or exported SVG and PNG files. Architecture diagrams show components, boundaries, data flows, and deployment relationships.
taiyi-restyle
A planning guide for breaking a large user-interface redesign into smaller, independently reviewable tasks. A user interface is the part of an application that people see and use.
taiyi-diagram-pipeline
A pipeline that creates and updates architecture diagrams in three stages: a C4 model from the code, an engineering architecture diagram, and an exported PNG image. C4 is a way to describe software architecture at several levels of detail.