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.
npx skills add zamana-inc/vajra --skill vajra-doc-reviewgit clone --depth 1 https://github.com/zamana-inc/vajraWrote 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.
[](https://agentmods.dev/skills/zamana-inc/vajra/vajra-doc-review)<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.
<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>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 | $0.00030 | $0.00563 |
| Opus 5 | $0.00015 | $0.00282 |
| Sonnet 5 | $0.00006 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00056 |
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.
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.
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.
- 13d ago First seen · 68 lines · 30 tokens per session scan A 1e0bd74c8a1e
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
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…
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…