mk:docs-init

mk:docs-init is a skill for Claude Code from ngocsangyem/MeowKit. It costs 66 tokens per session (906 once invoked), scanned A, original, MIT.

A workflow for creating a complete initial documentation set by analyzing a codebase. It is intended for projects without a populated docs/ directory and also creates project-context guidance.

In plain words
What is it for?
Use it to initialize project documentation, describe the codebase, create contributor guidance, and record the project’s technical context.
Why use it?
It gives an undocumented project a consistent starting point based on how its code is actually organized and works.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

Good fit Use it to initialize project documentation, describe the codebase, create contributor guidance, and record the project’s technical context.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ngocsangyem/meowkit/docs-init
Install

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.

Any agent
npx skills add ngocsangyem/MeowKit --skill docs-init
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

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 mk:docs-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/ngocsangyem/meowkit/docs-init/github.svg)](https://agentmods.dev/skills/ngocsangyem/meowkit/docs-init)
Your own site
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/docs-init"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/docs-init/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 mk:docs-init

Your own site · 80×15
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/docs-init"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/docs-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 906 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 $0.00066 $0.00906
Opus 5 $0.00033 $0.00453
Sonnet 5 $0.00013 $0.00181
Haiku 4.5 $0.00007 $0.00091

Measured 8d ago against content hash e731b44fae0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mk:docs-init 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 8d 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/docs-init/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs Init

Generate initial project documentation from codebase analysis.

Scope: Creates docs/ from scratch. For updating existing docs → mk:document-release.

Also run mk:project-context to generate the agent-constitution file (docs/project-context.md). mk:docs-init generates the full documentation suite; mk:project-context generates only the constitution.

When to Use

  • Project has no docs/ directory
  • docs/ exists but is empty or has only stubs
  • User asks to "initialize docs", "create documentation", "generate docs"
  • After mk:bootstrap completes (new project needs docs)

Do NOT invoke when: docs already exist and need updating (use mk:document-release).

Process

  1. Check existing state — does docs/ exist? Are files already populated?
    • If populated docs exist → suggest mk:document-release instead, stop.
  2. Scout codebase — activate mk:scout to analyze project structure. Skip: .claude/, .git/, node_modules/, __pycache__/, dist/, build/
  3. Merge findings — consolidate scout reports into context for doc generation
  4. Generate docs — spawn documenter subagent via Task tool with scout context. Output files (adapt to what the project actually has):
    • README.md — project overview (≤300 lines)
    • docs/project-overview.md — what this project is, who it's for
    • docs/codebase-summary.md — directory map, key modules, entry points
    • docs/code-standards.md — conventions found in codebase
    • docs/architecture/system-architecture.md — component diagram, data flow Optional (generate only if relevant):
    • docs/deployment-guide.md — if CI/CD or Docker config detected
    • docs/design-guidelines.md — if frontend/UI code detected
  5. Size check — run wc -l docs/*.md | sort -rn. Flag files >800 lines.
  6. Report — print generated files list with line counts.

Hard gate: Do NOT write code or implementation. Only documentation.

Gotchas

  • Hallucinating architecture: generating docs about code that doesn't exist → always scout FIRST, generate from findings only
  • Over-documenting small projects: creating 7 docs for a 50-line script → check project size; small projects get README + codebase-summary only
  • Stale on first run: docs describe initial state but drift immediately → tell user to run mk:document-release after each feature ship

Read the full file on GitHub · 96 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. 8d ago First seen · 96 lines · 66 tokens per session scan A e731b44fae0d

Subscribe to this mod's changes

mk:docs-init is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 906 once invoked, about $0.0003 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 2026-09-03.