readme-draft

readme-draft is a skill for Claude Code, Codex from getkyo/kyo. It costs 48 tokens per session (4,451 once invoked), scanned A, original, Apache-2.0.

A writing tool that drafts or fully rewrites a README from a structured analysis of a source codebase. A README is the project guide that explains what software does and how to use it.

In plain words
What is it for?
Use it for a new README or a complete rewrite, covering the listed API surface in order and grouping related material into coherent sections.
Why use it?
It organizes documented APIs, important notes, and usage examples without adding claims that are absent from the analysis.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/getkyo/kyo/readme-draft
Any agent
npx skills add getkyo/kyo --skill readme-draft
Clone the repo
git clone --depth 1 https://github.com/getkyo/kyo

Made for: Claude Code, Codex.

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 readme-draft

README.md
[![agentmods](https://agentmods.dev/badge/skills/getkyo/kyo/readme-draft.svg)](https://agentmods.dev/skills/getkyo/kyo/readme-draft)
Your own site
<a href="https://agentmods.dev/skills/getkyo/kyo/readme-draft"><img src="https://agentmods.dev/badge/skills/getkyo/kyo/readme-draft.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,451 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 $0.00048 $0.04451
Opus 5 $0.00024 $0.02226
Sonnet 5 $0.00010 $0.00890
Haiku 4.5 $0.00005 $0.00445

Measured 4d ago against content hash 7b66a13bf329, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

readme-draft 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 4d 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/readme-draft/SKILL.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

readme-draft

Input: the structured output of readme-analyze-source (five sections: spine candidate, callout candidates, API surface inventory, section clusters, running-domain seeds). Output: a draft README.

This skill writes from a curriculum: every API listed in the inventory must be introduced, in order, with one or more worked examples. The spine candidate becomes the opening paragraphs. Callout candidates become inline Note:, Caution:, or Unlike X paragraphs at the points where the surface they describe is introduced. The section clusters become the ## section list — one section per cluster, NOT one per API. The running-domain seeds determine the case classes used in worked examples — pick one early and reuse throughout.

This skill does NOT:

  • Read or compare against an existing README at the output path. If a README exists there, the user wants a full rewrite; you write fresh.
  • Add content beyond what the inventory and callouts specify.
  • Invent capabilities or surfaces.
  • Add hedging, defensive disclaimers, audience disclaimers, or competitor-suggestion paragraphs.
  • Produce one ## section per inventory API (catalog shape). Sections come from the cluster list, not the inventory list.

What you produce

A single Markdown file at <output-readme-path>, structured as follows:

  1. Title (# kyo-<name>) — exactly the module name, no marketing.
  2. Spine paragraphs — verbatim from the spine candidate, or lightly edited for prose flow. NEVER trade specificity for fluency.
  3. Composition opening: ONE code block exercising 3-5 capabilities on the chosen running-domain value, with // comment headers. See "Structural discipline" below.
  4. ## sections IN CLUSTER ORDER (one per cluster from the source-analysis output), each with its APIs as ### sub-sections. APIs from the same cluster MUST appear together under their cluster heading.
  5. Optional sections that the inventory specifically supports (cross-platform behavior, integration points, configuration, exceptions).

Read the full file on GitHub · 242 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. 4d ago First seen · 242 lines · 48 tokens per session scan A 7b66a13bf329

Subscribe to this mod's changes

readme-draft is a skill published in the GitHub repository getkyo/kyo (811 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 4,451 once invoked, about $0.0002 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.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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