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.
curl -O https://raw.githubusercontent.com/bringfire/rook-release/main/.claude/skills/capture-convention/SKILL.mdgit clone --depth 1 https://github.com/bringfire/rook-releaseWrote 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/bringfire/rook-release/capture-convention)<a href="https://agentmods.dev/skills/bringfire/rook-release/capture-convention"><img src="https://agentmods.dev/badge/skills/bringfire/rook-release/capture-convention/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/bringfire/rook-release/capture-convention"><img src="https://agentmods.dev/badge/skills/bringfire/rook-release/capture-convention.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 | $0.00112 | $0.02259 |
| Opus 5.5 | $0.00045 | $0.00904 |
| Sonnet 5.5 | $0.00022 | $0.00452 |
| Haiku 4.5 | $0.00011 | $0.00226 |
Grade A, and why
capture-convention 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.
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture Convention
Analyze the currently open Rhino file, identify its organizational patterns,
confirm intent with the user, and write a .rook/conventions.yaml that
cleanup skills can consume.
The convention file separates policy (what "correct" looks like) from execution (what cleanup skills do). This skill captures the policy.
Prerequisites
- A Rhino file must be open (the reference file to capture from)
- The file should represent the user's intended structure — either a clean template or a working file whose patterns they want to formalize
- Rook MCP tools must be available (
rhino_pingreturns pong)
Workflow
Step 0: Preflight
- Call
rhino_ping. If no response, stop and tell the user to open Rhino. - Call
rhino_documentto get the file name, units, and tolerance. - Confirm with the user: "I'll analyze {filename} to extract your layer conventions. This file will be the reference — is that the right one?"
Wait for confirmation before proceeding. If the user wants a different file, tell them to open it first.
Step 1: Scan
Call all five audit tools in parallel — they're independent reads:
rhino_layers— full layer tree with properties (color, plotColor, plotWeight, linetype, material, visibility, locked)rhino_materials— all materials with usage countsrhino_linetypes— all linetypes with usage countsrhino_block_layer_census— which layers each block's geometry lives onrhino_layer_dependencieson any layers that look like they might be undeletable (high object count, many block references)
This gives you the complete picture of the file's structure. Don't present raw data to the user — analyze it first.
Step 2: Analyze
From the scan data, identify these patterns. Work through them internally before presenting to the user.
Category structure:
- Are there numbered top-level layers? (
01-...,02-...) - What roles do they serve? (materials, options, entourage, utility, coordination)
- Are there stray top-level layers outside the category system?
What ships with it
1 file 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.
- 1mo ago First seen · 245 lines · 112 tokens per session scan A 014e2aef4aec
capture-convention is a skill published in the GitHub repository bringfire/rook-release (6 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 2,259 once invoked, about $0.0004 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.
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.
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.
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).
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.
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).
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.