vajra-doc-review

vajra-doc-review is a skill for Claude Code, Codex from zamana-inc/vajra. It costs 30 tokens per session (563 once invoked), scanned A, original, MIT.

A documentation fact-checking and editing guide that compares written documentation with the software source code.

In plain words
What is it for?
Review a documentation draft, verify its technical claims against the code, correct errors, and shorten it to a publishable version.
Why use it?
It helps catch incorrect file paths, function details, and behavior descriptions before documentation is published.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Review a documentation draft, verify its technical claims against the code, correct errors, and shorten it to a publishable version.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zamana-inc/vajra/vajra-doc-review
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 zamana-inc/vajra --skill vajra-doc-review
Clone the repo
git clone --depth 1 https://github.com/zamana-inc/vajra

Made for: Claude Code, Codex.

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 vajra-doc-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-doc-review/github.svg)](https://agentmods.dev/skills/zamana-inc/vajra/vajra-doc-review)
Your own site
<a href="https://agentmods.dev/skills/zamana-inc/vajra/vajra-doc-review"><img src="https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-doc-review/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 vajra-doc-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/zamana-inc/vajra/vajra-doc-review"><img src="https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-doc-review.svg" alt="Reviewed on agentmods" width="80" 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 563 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.
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 $0.00563
Opus 5 $0.00015 $0.00282
Sonnet 5 $0.00006 $0.00113
Haiku 4.5 $0.00003 $0.00056

Measured 13d ago against content hash 1e0bd74c8a1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vajra-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 13d 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.

orchestrator/skills/vajra-doc-review/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vajra Doc Review

You are reviewing a documentation draft. Your output is not a review document — it is the draft itself, edited in place to its final state. When you are done, the docs are ready to publish.

Context

Documentation should be practical and accurate. Do not expand scope. Do not turn a focused guide into an encyclopedia.

Mindset

Documentation review is fact-checking against the codebase. The writer read the code and described it. Your job is to verify every claim by reading the same code — and fixing what is wrong.

The most valuable thing you do is catch factual errors. Wrong file paths, incorrect function signatures, outdated behavior descriptions — these are worse than no documentation because they actively mislead.

The second most valuable thing is cutting. If a section is verbose, make it concise. If a section covers something outside the issue's scope, remove it. Engineers skim — shorter docs get read.

Process

1. Read the draft and the issue

Understand what the docs are supposed to cover. Is the scope right? Is anything missing? Is anything unnecessary?

2. Verify every factual claim

The draft mentions files, functions, behaviors, commands. Check them:

  • Does the file exist at that path?
  • Does the function have the described signature and behavior?
  • Does the command actually work?
  • Do the examples match reality?

This is the step that matters most.

3. Fix and tighten

  • Fix factual errors inline
  • Cut verbose explanations down to essentials
  • Remove speculative language ("should", "is designed to", "will eventually")
  • Replace vague references with concrete file paths and function names
  • Ensure examples are real, not hypothetical

4. Check structure

  • Can an engineer scan this in 2 minutes and find what they need?
  • Are headings clear and descriptive?
  • Is the most important information first?
  • Are code blocks used for commands and file paths?

Quality Bar

Good review: catches factual errors, makes the docs shorter and sharper, leaves a document that accurately describes the code as it exists today.

Read the full file on GitHub · 68 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. 13d ago First seen · 68 lines · 30 tokens per session scan A 1e0bd74c8a1e

Subscribe to this mod's changes

vajra-doc-review is a skill published in the GitHub repository zamana-inc/vajra (55 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 563 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens