rook-release: Skill for Claude Code

.claude/skills/clean-layers/SKILL.md

clean-layers is a skill for Claude Code from bringfire/rook-release. It costs 82 tokens per session (2,571 once invoked), scanned A, original, MIT.

A tool for comparing a Rhino file’s layer structure with the rules in `.rook/conventions.yaml` and suggesting cleanup changes. Rhino is software for 3D modelling and design.

In plain words
What is it for?
It is for auditing, proposing, and—after approval—applying Rhino layer organisation fixes.
Why use it?
It shows where a file differs from the agreed layer standards before anything is changed.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is bringfire/rook-release's own configuration. It tells Claude Code how to work on rook-release itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rook-release configures →

Part of the rook plugin — 9 skills shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to bringfire/rook-release. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bringfire/rook-release/main/.claude/skills/clean-layers/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/bringfire/rook-release

Made for: Claude Code.

Or install rook, the plugin that ships this one along with the rest of its 9 skills.

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 clean-layers

README.md
[![agentmods](https://agentmods.dev/badge/skills/bringfire/rook-release/clean-layers/github.svg)](https://agentmods.dev/skills/bringfire/rook-release/clean-layers)
Your own site
<a href="https://agentmods.dev/skills/bringfire/rook-release/clean-layers"><img src="https://agentmods.dev/badge/skills/bringfire/rook-release/clean-layers/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.

agentmods 80×15 button for clean-layers

Your own site · 80×15
<a href="https://agentmods.dev/skills/bringfire/rook-release/clean-layers"><img src="https://agentmods.dev/badge/skills/bringfire/rook-release/clean-layers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,571 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00082 $0.02571
Opus 5.5 $0.00033 $0.01028
Sonnet 5.5 $0.00016 $0.00514
Haiku 4.5 $0.00008 $0.00257

Measured 1mo ago against content hash 5edd28a90653, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

clean-layers 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 1mo 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.

.claude/skills/clean-layers/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clean Layers

Compare the currently open Rhino file's layer structure against the project's .rook/conventions.yaml and propose targeted changes to bring it into compliance. Never makes changes without user approval.

This is the execution side of the convention system. /capture-convention captures the policy; this skill enforces it.

Prerequisites

  • A Rhino file must be open
  • A .rook/conventions.yaml must exist in the project directory (created by /capture-convention or written by hand)
  • Rook MCP tools must be available (rhino_ping returns pong)

If no conventions.yaml exists, tell the user: "No convention file found. Run /capture-convention first to define your layer standards, or place a .rook/conventions.yaml in your project directory."

Workflow

Step 0: Preflight

  1. Call rhino_ping. If no response, stop.

  2. Call rhino_document to get the file name and path.

  3. Look for .rook/conventions.yaml relative to the file's directory. If the file is at C:\Projects\MyProject\model.3dm, check C:\Projects\MyProject\.rook\conventions.yaml. Also check the current working directory.

  4. Read and parse the conventions.yaml. If it fails to parse, report the error and stop.

  5. Offer to create a backup copy. Layer cleanup is a multi-step operation and Ctrl+Z may not cleanly revert everything. Offer: "Before making changes, I can save a backup copy of {filename} as {filename_without_ext}_BACKUP.3dm in the same directory. If anything goes wrong, you can delete the modified file and rename the backup. Create a backup? (recommended)"

    If the user accepts, use rhino_command or rhino_execute to SaveAs to the backup path, then SaveAs back to the original path so the working file stays at its original location. Or simply copy the .3dm file on disk before any Rhino mutations begin.

    If the user declines, proceed without backup — their choice.

  6. Tell the user: "I'll compare {filename} against the {convention name} convention. This is an audit — no changes until you approve."

Read the full file on GitHub · 257 lines

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. 1mo ago First seen · 257 lines · 82 tokens per session scan A 5edd28a90653

Subscribe to this mod's changes

clean-layers is a skill published in the GitHub repository bringfire/rook-release (6 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 2,571 once invoked, about $0.0003 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 52 tokens

glance-canonical-layouts

Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).

android/skills · 56 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens