doc-review

A documentation-checking procedure for ToolHive, a software project. It checks whether explanations, examples, links, formatting, and claims match how the project actually works.

In plain words
What is it for?
Use it to review project guides and reference pages, verify linked files, and record findings as a to-do list for someone else to fix.
Why use it?
It catches incorrect or outdated documentation before readers rely on it.

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/stacklok/toolhive/doc-review
Any agent
npx skills add stacklok/toolhive --skill doc-review
Clone the repo
git clone --depth 1 https://github.com/stacklok/toolhive

Made for: Claude Code, Codex.

Per session 8 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 180 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 $0.00008 $0.00180
Opus 5 $0.00004 $0.00090
Sonnet 5 $0.00002 $0.00036
Haiku 4.5 $0.00001 $0.00018

Measured 2d ago against content hash 870affe59ffc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-review 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/doc-review/SKILL.md · 25 lines

What it actually says

Documentation Review

Instructions

  1. Read the documentation you are instructed to review
  2. Make sure that all claims about how toolhive works are accurate
  3. Make sure that all examples are based in how toolhive really works, check for formatting, typos and overall accuracy
  4. Make sure that all links point to existing files and the content of the links matches what it should

Fact-checking claims in the documentation

See CHECKING.md on instructions on how to check claims in the docs.

You have some examples on how to fact-check in EXAMPLES.md

Your report

  • Do not suggest inline changes
  • Present findings and put each into a todo list. The user will then go through them and review manually
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 · 25 lines · 8 tokens per session scan A 870affe59ffc

Subscribe to this mod's changes

doc-review is a skill published in the GitHub repository stacklok/toolhive (2,065 stars, last pushed today), licensed Apache-2.0. It adds 8 tokens to every session and 180 once invoked, about $0.0000 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.