vajra-document

vajra-document is a skill for Claude Code, Codex from zamana-inc/vajra. It costs 21 tokens per session (713 once invoked), scanned A, original, MIT.

A documentation skill for writing practical developer guides based on the actual codebase. It treats the code, tests, and configuration as the source of truth rather than relying on guesses.

In plain words
What is it for?
Use it when creating or updating a README, developer guide, onboarding material, or API reference. It helps determine the documentation scope, audience, format, and relevant source files to inspect.
Why use it?
It helps prevent documentation from describing intended or assumed behavior instead of what the software really does, while keeping the result concise for engineers.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it when creating or updating a README, developer guide, onboarding material, or API reference. It helps determine the documentation scope, audience, format, and relevant source files to inspect.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zamana-inc/vajra/vajra-document
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-document
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-document

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/zamana-inc/vajra/vajra-document"><img src="https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-document.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 713 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.00713
Opus 5 $0.00010 $0.00357
Sonnet 5 $0.00004 $0.00143
Haiku 4.5 $0.00002 $0.00071

Measured 12d ago against content hash 28f8342caf36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vajra-document 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 12d 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-document/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vajra Document

You are writing developer documentation. Your job is to read the code, understand the system, and produce docs that help engineers onboard and work effectively.

Context

Documentation should be practical and concise — not exhaustive. Write what an engineer actually needs to know. Skip ceremony.

Mindset

Documentation is a map of the territory. The territory is the code. If you have not read the code, you cannot draw the map.

The most common documentation failure is writing about what you think the code does instead of what it actually does. Every claim in your docs must be verifiable by opening the file you reference. If you are unsure how something works, read it — do not guess.

The second most common failure is writing too much. Engineers skim documentation. Dense paragraphs get skipped. Short sections with concrete examples get read.

Process

1. Understand the scope

Read the issue. What area needs documentation? What audience — new developer, maintainer, API consumer? What is the right format — README, guide, AGENTS.md, API reference?

2. Read the code

Read the relevant source files, tests, and configs thoroughly. Understand:

  • What the system does and why it exists
  • How the key components interact
  • What the entry points are
  • What the non-obvious behaviors and gotchas are

Tests are often the best documentation of actual behavior. Read them.

3. Write grounded documentation

Every statement must trace back to code you read. Prefer:

  • Concrete file paths and function names over vague descriptions
  • Real examples from the codebase over hypothetical ones
  • Short sections with clear headings over walls of text
  • "This does X" over "This is designed to do X"

4. Structure for scanning

Engineers do not read docs linearly. Structure for quick lookup:

  • Start with a one-paragraph overview
  • Use clear headings that answer "what is this section about?"
  • Put the most important information first in each section
  • Use code blocks for commands, file paths, and examples

Read the full file on GitHub · 94 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. 12d ago First seen · 94 lines · 21 tokens per session scan A 28f8342caf36

Subscribe to this mod's changes

vajra-document is a skill published in the GitHub repository zamana-inc/vajra (55 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 713 once invoked, about $0.0001 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