What is doc-accuracy?

A documentation audit that treats the program itself as the source of truth. It checks whether written explanations, code examples, public interfaces, and stated behaviour match the implementation.

Use it to check documentation against code, verify that examples compile, audit behavioural claims, and review documentation before a release.

Documentation can become outdated, contain examples that do not run, or make claims that conflict with the code. This finds those inconsistencies before they mislead users.

doc-accuracy — Skill for Claude Code by rjmurillo/ai-agents

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 rjmurillo/ai-agents --skill doc-accuracy

Clone the repo

git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: Claude Code.

Or install project-toolkit, the plugin that ships this one along with the rest of its 125 skills, 25 commands, 33 agents, 5 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rjmurillo/ai-agents/doc-accuracy/github.svg)](https://agentmods.dev/skills/rjmurillo/ai-agents/doc-accuracy)

Your own site

<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/doc-accuracy"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/doc-accuracy/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/doc-accuracy"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/doc-accuracy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,268 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.

Model	Per session	Once invoked
Fable 5.1	$0.00084	$0.02268
Opus 5.5	$0.00034	$0.00907
Sonnet 5.5	$0.00017	$0.00454
Haiku 4.5	$0.00008	$0.00227

Measured 8d ago against content hash 76803a34327a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

doc-accuracy 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 8d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/doc_accuracy.py, scripts/pr_snapshot.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-accuracy/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Accuracy Skill

Verify documentation claims against actual code behavior. Code is truth; docs are the subject under test.

Triggers

Trigger Phrase	Operation
`check documentation accuracy`	Full audit (Phases 1-6)
`verify code examples`	Compilability check (Phases 1-3)
`audit docs vs code`	Behavioral verification (Phases 1-4)
`check doc consistency`	Cross-document consistency (Phases 1-2, 5)
`run doc-accuracy`	Full audit (Phases 1-6)

When to Use

Use this skill when:

Documentation may contain non-compilable code examples
Behavioral claims in docs may contradict implementation
Quantitative claims (performance, limits) appear in multiple files with different values
Preparing for a release and need a documentation accuracy audit
API reference may be missing public members

Use direct code review instead when:

Investigating a single known documentation error
The inaccuracy is already identified and needs a fix

Replaces

Skill	Reason
`incoherence`	15.8% recall on critical issues; Haiku agents too shallow
`doc-coverage`	0% recall on actionable issues; checks presence, not correctness
`doc-sync`	No scripts, purely manual LLM workflow
`comment-analyzer`	Advisory only, single-file scope

Architecture

Asymmetric Verification

Code compiles and runs. Documentation describes what code does. When they disagree, the code is right. This skill reads code first, builds a verified model, then checks documentation claims against that model.

Phase Overview

Phase 1: Assessment        (script-only, <30s)  -> assessment.json
Phase 2: Claim Extraction  (script-only, <15s)  -> claims.json
Phase 3: Compilability     (script-only, <60s)  -> compilability-findings.json
Phase 4: Behavioral        (Sonnet agents, 3-7m) -> behavioral-findings.json
Phase 5: Cross-Document    (script + Sonnet, 1-2m) -> consistency-findings.json
Phase 6: Structure         (Sonnet agent, 1-2m)  -> structure-findings.json

Read the full file on GitHub · 274 lines

Files

What ships with it

3 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.

8d ago Changed · +5 lines 76803a34327a
10d ago Changed d5e11dd870a4
17d ago Changed 382201cd9147
22d ago Changed · +6 lines 57b05ef967a9
1mo ago First seen · 263 lines · 84 tokens per session scan A a01623b7716f

Subscribe to this mod's changes

doc-accuracy is a skill published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 2,268 once invoked, about $0.0003 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 2026-09-03.

CI and CD Claude Code Code review Writing and docs agentic-ai ai-agents developer-tools github-copilot

install-gemini-code-review-action

Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.

derailed-dash/dazbo-agent-skills · 73 tokens

doc-accuracy