review-docs

review-docs is a skill for Claude Code from openshift-eng/ai-helpers. It costs 30 tokens per session (3,698 once invoked), scanned A, original, Apache-2.0.

A documentation review process that checks claims against local source code and, when needed, related repositories or teams.

In plain words
What is it for?
Use it to verify agent documentation before a documentation change or review, including component-specific claims and cross-repository details.
Why use it?
It helps catch documentation that is inaccurate, outdated, or unsupported by the code.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the agentic-docs plugin — 4 skills, 2 commands, 1 hook shipped together

Good fit Use it to verify agent documentation before a documentation change or review…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openshift-eng/ai-helpers/review-docs
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.

Any agent
npx skills add openshift-eng/ai-helpers --skill review-docs
Clone the repo
git clone --depth 1 https://github.com/openshift-eng/ai-helpers

Made for: Claude Code.

Or install agentic-docs, the plugin that ships this one along with the rest of its 4 skills, 2 commands, 1 hook.

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 review-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/review-docs.svg)](https://agentmods.dev/skills/openshift-eng/ai-helpers/review-docs)
Your own site
<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/review-docs"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/review-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,698 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00030 $0.03698
Opus 5 $0.00015 $0.01849
Sonnet 5 $0.00006 $0.00740
Haiku 4.5 $0.00003 $0.00370

Measured yesterday against content hash 386391379a3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

review-docs scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- [ ] Verify external HTTPS links with curl (timeout 10s). Some sites return non-200 for automated requests — GitHub rate-limits, `docs.openshift.com` blocks curl. Treat 403/429 as "needs manual check" not automatic fail
plugins/agentic-docs/skills/review-docs/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Review & Verification

Reviews agentic documentation using two-tier verification: local codebase checks first, then cross-repo verification via Chai Bot for claims that can't be resolved locally. Chai Bot access may be provided directly by its hosted workspace or through an external MCP connection. Verify locally when possible, escalate to Chai Bot when necessary.

Prerequisites

Recommended (for cross-repo verification): Chai Bot access through its hosted workspace or an external MCP connection. External access requires a configured bearer token and Red Hat VPN connection. Without either access path, cross-repo claims (enhancements, platform terminology, convention compliance, non-vendored API types) are flagged as "unverified" but local verification still runs fully.

External MCP setup instructions: See plugin README for Chai Bot configuration steps.

Chai Bot Access

Before any Chai Bot-assisted operation, select exactly one access path:

  1. Hosted — If explicit host context identifies execution inside Chai Bot's hosted workspace and provides a callable knowledge/search capability, use that capability. Do not configure or call a second Chai Bot MCP server.
  2. External — Otherwise, use an available Chai Bot ask_persona MCP capability. Hosts may normalize the server name differently; select it by capability, not by an exact tool identifier.
  3. Unavailable — If neither path is available, report which Chai Bot-assisted work could not be performed. Do not infer or fabricate results.

Resolve the access path once per run and reuse it. Explicit hosted context without a callable knowledge capability is unavailable, not permission to invent results. Do not infer hosted execution merely from a missing MCP tool, repository name, or working directory. Never modify MCP configuration from a managed hosted workspace.

When to Use

  • After /component-docs or /update-platform-docs
  • Before documentation PRs
  • When docs may contain outdated/incorrect information

Read the full file on GitHub · 237 lines

Files

What ships with it

1 file 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. yesterday Changed · -28 lines 386391379a3b
  2. 7d ago First seen · 265 lines · 30 tokens per session scan A f44d0716cf90

Subscribe to this mod's changes

review-docs is a skill published in the GitHub repository openshift-eng/ai-helpers (116 stars, last pushed 2d ago), licensed Apache-2.0. It adds 30 tokens to every session and 3,698 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.