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-knowledge-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-knowledge-review)<a href="https://agentmods.dev/skills/zamana-inc/vajra/vajra-knowledge-review"><img src="https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-knowledge-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-knowledge-review"><img src="https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-knowledge-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 | $0.00031 | $0.01168 |
| Opus 5 | $0.00015 | $0.00584 |
| Sonnet 5 | $0.00006 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
vajra-knowledge-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 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vajra Knowledge Review
You are reviewing a category knowledge draft. Your output is the edited draft itself, ready for human supervision in experiments/knowledge/agent-drafts/.
This is not a separate review memo. Edit the draft in place so it is materially better, more schema-aware, and more faithful to the repo's source material.
Non-Negotiable Read Requirements
Before reviewing anything, you must read every file in experiments/knowledge/instructions completely and carefully.
Do not skim, sample, or stop early. That behavior is incorrect for this task. It is not possible to succeed without fully reading and understanding the instruction documents and historical logs in that directory.
What the instruction files are
The files in experiments/knowledge/instructions are cleaned conversation logs between the project owner and an AI collaborator. They are not structured style guides. They are transcripts of real writing sessions where the owner demonstrated the quality bar, corrected mistakes, pushed back on generic output, and showed what good knowledge writing actually looks like for this repo.
Read them as the definitive reference for what the owner accepts and rejects. Pay attention to:
- what the owner corrected and why
- what patterns the owner praised or accepted
- what specific mistakes triggered pushback
- the level of specificity and schema-grounding the owner demanded
Your review should catch the same mistakes the owner catches in these logs. If the logs show the owner rejecting a particular pattern, and the draft uses that pattern, that is a review failure.
Schema and extraction instructions
Then read the target category's schema and extraction instructions:
experiments/schemas/examples/<category>.jsoncexperiments/schemas/examples/<category>.md
Closest existing knowledge docs
Then inspect the existing knowledge docs in experiments/knowledge/, identify the 2–3 closest examples to learn from, and read those examples fully. Choose examples based on product structure, buyer tradeoffs, and schema shape, not superficial keyword similarity. For example, if reviewing a throw pillows draft, cushions and decorative pillowcases are structurally closer than bedsheets — even though all are "textiles."
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.
- 12d ago First seen · 132 lines · 31 tokens per session scan A c2a74c63ab0f
vajra-knowledge-review is a skill published in the GitHub repository zamana-inc/vajra (55 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,168 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…