docs-check

A contributor check that compares the plugin's structure and behavior with cached Claude Code documentation. It focuses on whether documented changes could cause compatibility problems.

In plain words
What is it for?
Use it to check all plugin surfaces or focus on agents, skills, hooks, configuration, or the plugin manifest and marketplace files.
Why use it?
It separates genuine documentation or schema drift from outdated local assumptions before a release.

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/slbug/claude-ruby-grape-rails/docs-check
Any agent
npx skills add slbug/claude-ruby-grape-rails --skill docs-check
Clone the repo
git clone --depth 1 https://github.com/slbug/claude-ruby-grape-rails

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,644 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 $0.00045 $0.01644
Opus 5 $0.00023 $0.00822
Sonnet 5 $0.00009 $0.00329
Haiku 4.5 $0.00005 $0.00164

Measured 2d ago against content hash f0372e62945d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-check 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 2d 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-check/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin Documentation Compatibility Check

Audience: Agents, Not Humans

Imperative-only. Validate plugins/ruby-grape-rails/ against current cached Claude Code docs. Contributor maintenance — NOT user-facing.

When to Use

Question Answer this skill gives
Did Claude docs change in a way that breaks our plugin? yes
Is this warning a real compatibility issue or stale local guidance? yes
What new Claude feature is now documented and relevant? yes
Is naming style / line count / repo preference unrelated to docs? NO — out of scope

Usage

Command Scope
/docs-check all surfaces
/docs-check --quick skip docs fetch, structural drift only
/docs-check --focus=agents agents only
/docs-check --focus=skills skills only
/docs-check --focus=hooks hooks only
/docs-check --focus=config plugin manifest + marketplace only

Execution Flow

1. Run Deterministic Baseline

Run all three, in order, to catch structural schema issues without docs interpretation:

Command Covers
claude plugin validate --strict plugins/ruby-grape-rails shipped plugin manifest + components
claude plugin validate --strict . .claude-plugin/marketplace.json, which the plugin-directory run skips
claude plugin validate --strict .claude contributor-only components under .claude/, validated as a bare component directory

--strict promotes unrecognized-field and missing-metadata warnings to errors. npm run validate runs the same three via scripts/validate-plugin.sh; CI runs them as separate lint-job steps.

2. Refresh Cached Docs (Unless --quick)

From repo root: bash ./scripts/fetch-claude-docs.sh.

--quick skips fetching; limits run to structural drift checks against existing cache.

3. Inventory Plugin Surfaces

Identify in-scope surfaces per --focus:

Surface Paths
agents plugins/ruby-grape-rails/agents/*.md
skills plugins/ruby-grape-rails/skills/*/SKILL.md
hooks plugins/ruby-grape-rails/hooks/hooks.json
config plugins/ruby-grape-rails/.claude-plugin/plugin.json, .claude-plugin/marketplace.json

Read the full file on GitHub · 191 lines

Files

What ships with it

2 files 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. 2d ago First seen · 191 lines · 45 tokens per session scan A f0372e62945d

Subscribe to this mod's changes

docs-check is a skill published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 1,644 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 2026-08-31.