readme-analyze-source

readme-analyze-source is a skill for Claude Code from getkyo/kyo. It costs 40 tokens per session (4,773 once invoked), scanned A, original, Apache-2.0.

A source-code inspection step that reads a module and maps its main use cases, notable code locations, public interfaces, and related groups of features. Its output is used to help write or assess a README.

In plain words
What is it for?
Use it to inspect a module before drafting or reviewing its README, identify code locations for callouts, inventory its API, and group features into understandable sections.
Why use it?
It turns a code directory into a structured outline before documentation work begins, so important interfaces and examples are less likely to be missed.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions subagents.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is bash .claude/skills/readme/readme-check.sh <module-dir>/README.md --callouts.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 readme-analyze-source

README.md
[![agentmods](https://agentmods.dev/badge/skills/getkyo/kyo/readme-analyze-source.svg)](https://agentmods.dev/skills/getkyo/kyo/readme-analyze-source)
Your own site
<a href="https://agentmods.dev/skills/getkyo/kyo/readme-analyze-source"><img src="https://agentmods.dev/badge/skills/getkyo/kyo/readme-analyze-source.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,773 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 $0.00040 $0.04773
Opus 5 $0.00020 $0.02387
Sonnet 5 $0.00008 $0.00955
Haiku 4.5 $0.00004 $0.00477

Measured 6d ago against content hash f77f0a7bab67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

readme-analyze-source 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/readme-analyze-source/SKILL.md · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.

readme-analyze-source

Read the module source directory given in $ARGUMENTS and produce three artifacts: a spine candidate, a list of callout candidates, and an API surface inventory. These artifacts are consumed by readme-draft and readme-analyze-existing. This skill does NOT draft a README, evaluate any existing README, or verify output.

What you produce

## Spine candidate
[use-case-first|type-first]
<spine paragraph here>

## Callout candidates
- <source file>:<line> -- <one-line summary>
- <file-A>:<line-A> + <file-B>:<line-B> -- <cross-API seam summary>
- ...

## API surface inventory
- <load-bearing type/method>: <one-line description of role>
- ...

## Section clusters
- "<Cluster name (use, not API)>" -- <one-sentence mental model>
  - <API in this cluster>: <one-line role>
  - ...
- ...

## Running-domain seeds
- <case class declarations + which clusters they can demonstrate>
- ...

Output these five sections and nothing else. The downstream skills consume this structure directly.


Input

A path to a module source directory (for example, kyo-http/).

This sub-skill MUST NOT read the existing README at the module path even if one exists. The spine candidate produced here is the 0(a)(i) source-only draft that downstream cleanup discipline depends on. Reading the existing README would anchor the spine on its wording and defeat the technique.


Step 1: read the source

Scan these locations in order:

  1. The package object's scaladoc (top of package.scala or package object in the primary source tree).
  2. Top-level scaladocs on the main public types and the primary entry-point companions.
  3. Method-level scaladocs on load-bearing methods (especially those with qualifiers: Unsafe, Lazy, Default, Async).
  4. Test case names under src/test: names shaped "fails when...", "returns empty when...", "throws when..." describe edge behavior.
  5. Implementation comments shaped "// This looks wrong but..." or "// Note:" in source.

Read the full file on GitHub · 347 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. 6d ago First seen · 347 lines · 40 tokens per session scan A f77f0a7bab67

Subscribe to this mod's changes

readme-analyze-source is a skill published in the GitHub repository getkyo/kyo (812 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 4,773 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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 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

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