cdkd: Skill for Claude Code

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

check-docs is a skill for Claude Code from go-to-k/cdkd. It costs 38 tokens per session (1,448 once invoked), scanned A, original, Apache-2.0.

A documentation consistency checker for README.md, CLAUDE.md, and the docs/ folder. It compares recent code changes with the documentation that describes them.

In plain words
What is it for?
Use it after code changes to decide whether documentation needs review, especially when changing source files, command-line options, public types, or state storage details.
Why use it?
It helps catch documentation that no longer matches changed commands, public interfaces, data layouts, or other user-facing behaviour.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions .claude-plugin; mentions AGENTS.md.

This is go-to-k/cdkd's own configuration. It tells Claude Code how to work on cdkd 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 cdkd configures →

View source ↗ go-to-k/cdkd
Reuse

Borrowing it

Nothing to install: this file belongs to go-to-k/cdkd. 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/go-to-k/cdkd/main/.claude/skills/check-docs/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/go-to-k/cdkd

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 check-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/go-to-k/cdkd/check-docs/github.svg)](https://agentmods.dev/skills/go-to-k/cdkd/check-docs)
Your own site
<a href="https://agentmods.dev/skills/go-to-k/cdkd/check-docs"><img src="https://agentmods.dev/badge/skills/go-to-k/cdkd/check-docs/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 check-docs

Your own site · 80×15
<a href="https://agentmods.dev/skills/go-to-k/cdkd/check-docs"><img src="https://agentmods.dev/badge/skills/go-to-k/cdkd/check-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,448 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00038 $0.01448
Opus 5.5 $0.00015 $0.00579
Sonnet 5.5 $0.00008 $0.00290
Haiku 4.5 $0.00004 $0.00145

Measured 1mo ago against content hash 62a220cc950f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

check-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 1mo 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/check-docs/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Consistency Check

You are checking whether documentation is up to date with recent code changes in this repository.

Steps

  1. Identify what changed: git diff main...HEAD --name-only (or git diff HEAD~5 --name-only if on main).

  2. Decide whether a deep review is needed (short-circuit). Most internal refactors and bug fixes do not affect anything the docs describe. A deep review IS required if the diff touches any of:

    • src/index.ts — public exports.
    • src/cli/options.ts, src/cli/commands/** — the CLI surface described in docs/getting-started.md and the per-command pages under docs/.
    • src/types/** — public type definitions.
    • src/state/** — bucket name, key layout, lock layout, schema version, all documented verbatim in docs/state-management.md, docs/troubleshooting.md, docs/stack-outputs.md and .claude/rules/state-schema.md. A path-layout change invalidates dozens of shell snippets across them.
    • Any NEW file under src/** — it must be reachable from the key-file index in .claude/rules/code-layout.md and its layout-*.md satellites.
    • package.json — dependency changes described in .claude/rules/package-and-release.md.
    • README.md, AGENTS.md, docs/**, .claude/rules/**, plugins/** — the docs themselves. plugins/** is a TRIGGER, not only a step-3 target: a plugins-only diff matches nothing else, and step 3 reads changed SOURCE files.
    • Any src/** file matched by a paths: glob in a .claude/rules/ satellite — in practice nearly every src file. A comment-only or message-only edit does NOT exempt it: those files assert DECISIONS about the code, and a reworded message is exactly what invalidates one.

    If none apply, write "no docs-visible surface touched" and stop.

  3. For each changed source file, determine what documentation is affected:

    • Any src/** change → the .claude/rules/ satellites whose paths: glob matches it. DERIVE them — for f in .claude/rules/*.md; do echo "$f"; sed -n '/^paths:/,/^---$/p' "$f"; done, or the per-area row in .claude/rules/code-layout.md — never recall them, and use the sed range rather than grep -A<n>, which truncates a file declaring several globs. Then read what each SAYS about the code you changed, not just whether it names your new files: nothing mechanical watches a rule file that asserts a decision.
    • src/cli/ → CLI options/commands in docs/getting-started.md and the per-command pages.
    • src/synthesis/, src/assets/, src/deployment/, src/analyzer/ → the matching section of docs/architecture.md.
    • src/provisioning/ → docs/provider-development.md and docs/provider-rules.md, plus .claude/rules/providers.md. For a NEW SDK provider also docs/supported-resources.md + docs/import.md. If the provider gates a stabilization wait on process.env['CDKD_NO_WAIT'], its resource type MUST appear in the per-type wait-semantics table in docs/cli-deploy.md and in the noWaitOption help + JSDoc in src/cli/options.ts (enforced by tests/unit/provisioning/no-wait-doc-coverage.test.ts).
    • src/state/ → docs/state-management.md.
    • New exports in src/index.ts → public API docs.
    • package.json dependency changes → .claude/rules/package-and-release.md.
    • New integration tests → docs/testing.md and docs/integ-fixture-conventions.md.
    • Any behaviour change → plugins/cdkd-skills/skills/cdkd/SKILL.md, the DISTRIBUTED plugin surface, written for an audience that never reads this repo. Grep it for the subject you changed. If you edit it, bump the version in BOTH plugins/cdkd-skills/.claude-plugin/plugin.json and .claude-plugin/marketplace.json in the same PR — nothing enforces that, and an un-bumped edit ships to nobody.

Read the full file on GitHub · 106 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. 1mo ago Changed 62a220cc950f
  2. 1mo ago Changed · +2 lines 580b7a6619bd
  3. 1mo ago Changed · -1 lines · -1 tokens per session 4e0179ab946c
  4. 1mo ago Changed · +39 lines scan B → A b08f16f4860d
  5. 1mo ago Changed · -8 lines scan A → B 42073cda0c6a
  6. 1mo ago Changed · +1 lines 424da8f78391
  7. 1mo ago Changed f8867cd5fff6
  8. 1mo ago Changed · +2 lines 96d1999b6073
  9. 1mo ago Changed f2a878ce9947
  10. 1mo ago First seen · 71 lines · 39 tokens per session scan A 7f0ea8693e3b

Subscribe to this mod's changes

check-docs is a skill published in the GitHub repository go-to-k/cdkd (156 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 1,448 once invoked, about $0.0002 per session on Opus 5.5. 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

aws-cdk-mcp-server-mcp

AWS Cloud Development Kit (CDK) best practices, infrastructure as code patterns, and security compliance with CDK Nag.

Friz-zy/ai-capability-registry · 33 tokens

agent-squad-python

Use when building or modifying a Python app that uses the agent-squad Python package — async multi-agent orchestration for Python 3.11+: orchestrator, agents (BedrockLLMAgent, AnthropicAgent, OpenAIAgent, SupervisorAgent, GroundedAgent, ChainAgent, and more), classifier routing (Bedrock, Anthropic, OpenAI), storage…

2FastLabs/agent-squad · 113 tokens

agent-squad-swift

Use when building or modifying a Swift app that uses the AgentSquad Swift framework — on-device multi-agent orchestration for iOS 16+ / macOS 14+: orchestrator, agents (Agent, GroundedAgent), classifier routing, LLM clients (OpenAI-compatible), tools (native + MCP), tool UIs/widgets, on-device storage, tracing, and…

2FastLabs/agent-squad · 91 tokens

agent-squad-typescript

Use when building or modifying a Node.js / TypeScript app that uses the agent-squad npm package — multi-agent orchestration: orchestrator, agents (all built-in types + GroundedAgent), classifier routing (Bedrock / Anthropic / OpenAI), storage (in-memory / DynamoDB / SQL), retrievers (Amazon KB / Dakera), and tools…

2FastLabs/agent-squad · 87 tokens

nx-plugin-for-aws

Scaffold and build cloud-native applications on AWS using @aws/nx-plugin generators. Use when the user wants to create workspaces, generate projects, or scaffold infrastructure with the Nx Plugin for AWS.

awslabs/nx-plugin-for-aws · 46 tokens

aws-serverless-patterns

AWS Lambda, API Gateway, DynamoDB, Step Functions, EventBridge patterns and best practices. Use when building or reviewing serverless backends, CDK infrastructure, or Lambda functions.

seandkendall/kiro-config · 43 tokens