CATHERINE: Skill for Claude Code

.claude/skills/feature-docs/SKILL.md

feature-docs is a skill for Claude Code from Jm-Paunlagui/CATHERINE. It costs 200 tokens per session (3,361 once invoked), scanned A, original, Apache-2.0.

A documentation guide for explaining a software feature from its user-facing purpose through its frontend, backend, data flow, and security. It includes Mermaid diagrams, which are text-based diagrams rendered in Markdown.

In plain words
What is it for?
Use it to document real features, including their implementation, API contract, technical details, process flows, and security considerations.
Why use it?
It gives a new teammate one document showing how a feature works and how its parts connect, instead of requiring them to piece the explanation together from code.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Jm-Paunlagui/CATHERINE's own configuration. It tells Claude Code how to work on CATHERINE 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 CATHERINE configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Jm-Paunlagui/CATHERINE. 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/Jm-Paunlagui/CATHERINE/main/.claude/skills/feature-docs/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINE

Made for: Claude Code.

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 feature-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/jm-paunlagui/catherine/feature-docs.svg)](https://agentmods.dev/skills/jm-paunlagui/catherine/feature-docs)
Your own site
<a href="https://agentmods.dev/skills/jm-paunlagui/catherine/feature-docs"><img src="https://agentmods.dev/badge/skills/jm-paunlagui/catherine/feature-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 200 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,361 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 5.1 $0.00200 $0.03361
Opus 5 $0.00100 $0.01681
Sonnet 5 $0.00040 $0.00672
Haiku 4.5 $0.00020 $0.00336

Measured 6d ago against content hash 58f60084c135, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

feature-docs 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 6d 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/feature-docs/SKILL.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

feature-docs

Produce a single, self-contained Markdown document that explains a feature the way a senior engineer would hand it off to a new teammate: what it does, how it flows (with diagrams), how the frontend and backend each implement it, how they talk to each other, the details that bite people, and the security posture. Optionally — only when asked — a code review.

The user typically gives you a short prompt and expects you to know the full shape of the deliverable. "I need documentation of the implementation and processes of the Authentication" means: produce the whole document below, grounded in the actual code, not a generic essay.


Step 1 — Resolve which folders to read

The document must describe real code. Before writing anything, figure out where the code lives.

Folder resolution order:

  1. Explicit names in the prompt. If the user names paired folders — e.g. "for the auth-FE and auth-BE", "Name-FE and Name-BE", "the web and api folders" — use exactly those as the frontend and backend roots. The -FE/-BE suffix convention maps to frontend/backend respectively.
  2. Defaults. If no folders are named, look for a frontend root and a backend root using these common names (case-insensitive): frontend → Frontend, frontend, client, web, app, ui, fe; backend → Backend, backend, server, api, service, be.
  3. Single tree / monorepo. If there's no clean FE/BE split (one app, or a monorepo with packages/*), document it as a single codebase and skip the literal "Frontend vs Backend" split — instead use whatever real boundary exists (e.g. components/ vs routes/, or apps/web vs apps/api).
  4. Nothing found / no code at all. If you can't locate the relevant code, say so plainly and ask the user for the path, OR — if they explicitly want a design/spec doc rather than docs of existing code — produce the document from their description and label the diagrams and sections clearly as proposed, not as documentation of shipped code. Never silently invent file paths, function names, or routes.

Read the full file on GitHub · 238 lines

Files

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.

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. 6d ago First seen · 238 lines · 200 tokens per session scan A 58f60084c135

Subscribe to this mod's changes

feature-docs is a skill published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 200 tokens to every session and 3,361 once invoked, about $0.0010 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens