readme-verify

readme-verify is a skill for Claude Code from getkyo/kyo. It costs 0 tokens per session (3,785 once invoked), scanned A, original, Apache-2.0.

A final README checker that runs several consistency and coverage checks, including whether code examples compile.

In plain words
What is it for?
Use it to verify a newly drafted or edited README through script checks, forward-reference review, reader walkthroughs, source coverage, and catalogue-detection checks.
Why use it?
It catches broken examples, unclear references, missing public features, and README sections that only list facts without teaching the reader.

Skill for Claude Code

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash .claude/skills/readme/readme-check.sh <readme-path> --chunks --callouts --intro-order.

Good fit Use it to verify a newly drafted or edited README through script…

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

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

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-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/getkyo/kyo/readme-verify.svg)](https://agentmods.dev/skills/getkyo/kyo/readme-verify)
Your own site
<a href="https://agentmods.dev/skills/getkyo/kyo/readme-verify"><img src="https://agentmods.dev/badge/skills/getkyo/kyo/readme-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,785 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 $0.00000 $0.03785
Opus 5 $0.00000 $0.01893
Sonnet 5 $0.00000 $0.00757
Haiku 4.5 $0.00000 $0.00379

Measured 7d ago against content hash 3f8e65f502bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

readme-verify 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 7d 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-verify/SKILL.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

readme-verify

Final gate. The README is either a fresh draft from readme-draft or the post-edit output from readme-edit. This skill does not modify the README; it verifies and reports.

Five gates run in this order. If a gate fails, report the failure and stop. Downstream gates run only when upstream gates pass cleanly.

Gate 4 (source-coverage) and Gate 5 (catalog detection) are the load-bearing gates. Gates 1-3 check self-consistency, skim experience, and structural shape; they pass even when the README is missing entire chapters of public surface (Gate 4 catches that) or reads as a catalog rather than teaching (Gate 5 catches that). Gate 5 is the mechanical sibling of readme-critique: it surfaces signals; the critique skill makes the gestalt judgment.

Gate 0: sbt doctest (MANDATORY, hard gate, runs first)

This gate is non-negotiable. EVERY fenced ```scala block in the README must compile via the project's sbt-kyo-doctest plugin. The script-level checks below are NOT a substitute. A README that the structural-script declares clean can still contain fabricated API names, hallucinated type syntax, dead val placeholders, or .copy calls on private[kyo] constructors. Only the compiler catches those.

Run:

sbt '<module-sbt-name>/doctest' 2>&1 | tee /tmp/doctest-verify.log

For kyo-data that is sbt 'kyo-dataJVM/doctest'. For kyo-http that is sbt 'kyo-httpJVM/doctest'. Use the project name git grep -nE "^lazy val ..kyo-<name>." build.sbt resolves to ; do not invent the sbt module name.

Parse the log's last summary line:

[info] doctest: total=N compiled=N cacheHits=N failures=N

Pass conditions (ALL must hold):

  • sbt exit code == 0.
  • failures=0 in the summary.
  • The string doctest: validation failed does NOT appear anywhere in the log.

Fail conditions (ANY triggers BLOCK):

  • sbt exit code != 0.
  • failures= value > 0.
  • The phrase doctest: validation failed appears.
  • Doctest reports "skipped: not wired to kyo-doctest" AND the module SHOULD be wired (kyo-* modules under the kyo monorepo are wired by default unless explicitly disabled via .disablePlugins(KyoDoctestPlugin); if the verify agent encounters "skipped" for such a module, that is a build-config bug, not a pass).

Read the full file on GitHub · 216 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. 7d ago First seen · 216 lines · 0 tokens per session scan A 3f8e65f502bb

Subscribe to this mod's changes

readme-verify is a skill published in the GitHub repository getkyo/kyo (812 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,785 tokens. 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

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