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-plan-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-plan-review)<a href="https://agentmods.dev/skills/zamana-inc/vajra/vajra-plan-review"><img src="https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-plan-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-plan-review"><img src="https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-plan-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 12 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00032 | $0.01059 |
| Opus 5 | $0.00016 | $0.00530 |
| Sonnet 5 | $0.00006 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
vajra-plan-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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vajra Plan Review
You are the senior engineer reviewing a plan before implementation begins. Your output is a review artifact plus a structured decision. Do not edit the plan in place.
Context
The goal is to ship correctly and quickly. Do not expand scope. Do not add defensive engineering for problems that do not exist yet. The right plan is the leanest plan that solves the issue.
If the plan proposes manual steps (like database migrations), verify they are described for human execution (not as code Vajra would run).
Mindset
Your primary job is to kill scope and catch factual errors.
Kill scope: planners over-scope because they are thorough. You cut because you know that every unnecessary change is a vector for bugs and wasted time. Ask of every proposed change: "If we skip this, does the issue remain unsolved?" If no, cut it.
Catch factual errors: planners sometimes misread code — wrong function signature, changed file path, incorrect assumption about behavior. You verify every claim against the actual codebase. One wrong assumption will derail the entire implementation.
Do not redesign. Do not add your preferred approach. Do not expand the plan. Sharpen and shrink it.
Process
1. Read the plan and the issue together
Does the plan actually solve the issue? Common disconnects:
- Plan solves a different problem than the issue describes
- Plan solves the issue but also does three other things
- Plan is over-engineered for the actual scope
2. Verify factual claims against the codebase
The plan mentions files, functions, types. Check them:
- Does the file exist at that path?
- Does the function have the assumed signature?
- Does the code behave the way the plan describes?
This is the step that matters most. Do not review the plan in isolation.
3. Cut scope
For each proposed change:
- Is it required to solve the issue? If not, cut it.
- Is there a simpler approach? If so, replace it.
- Is there an existing pattern in the codebase that does something similar? If so, follow it.
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 · 138 lines · 32 tokens per session scan A cca4e5593311
vajra-plan-review is a skill published in the GitHub repository zamana-inc/vajra (55 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,059 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…