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 mhmdreza-rafiei/agent-tools --skill validategit clone --depth 1 https://github.com/mhmdreza-rafiei/agent-toolsWrote 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/mhmdreza-rafiei/agent-tools/validate)<a href="https://agentmods.dev/skills/mhmdreza-rafiei/agent-tools/validate"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/validate/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/mhmdreza-rafiei/agent-tools/validate"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/validate.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 | $0.00134 | $0.01305 |
| Opus 5 | $0.00067 | $0.00652 |
| Sonnet 5 | $0.00027 | $0.00261 |
| Haiku 4.5 | $0.00013 | $0.00130 |
Grade A, and why
validate 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 8d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/validate
/review asks an inward question: did we follow our own rules? /validate asks a harder, outward one: are our rules, approach, and quality bar even right for what this is trying to be?
A project can pass /review — perfectly consistent with its own context — and still be the wrong thing, built to the wrong bar. /validate looks outward (how the best comparable projects are built) and reasons from first principles, then reports the gap between where the project is and where it should be for its intended level.
/review vs /validate
/review— inward / conformance. Does the build matchplan.md,architecture.md,standards.md? Run after every feature./validate— outward / calibration. Are those standards and the approach actually good and high enough for this category of project? Run after/groundwork, after setup, at milestones, or when quality is in doubt.
Automation mode (default)
Research and reason on your own, then produce the report. Ask the developer only for the one thing you cannot infer — the target tier, when overview.md does not make it obvious.
Step 0 — Load reality
Read the context (overview.md, architecture.md, standards.md, design-system.md, plan.md, and any extra files the project added) and the actual current code/state. You are judging both the project and the context that describes it.
Step 1 — Establish the target (what is this, at what tier?)
Everything is judged against this, so get it right.
- Category — what kind of thing is it, precisely? ("a premium ImGui overlay menu", "a production REST API", "a marketing site", "a parsing library").
- Tier — throwaway prototype / solid production / best-in-class (premium).
Pull both from overview.md (success criteria, target users). If the tier is unclear and it changes the bar, ask once: "What's the bar here — quick prototype, solid production, or best-in-class?" A premium target and a prototype target are judged completely differently — do not default the bar low.
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.
- 8d ago First seen · 85 lines · 134 tokens per session scan A 7dce155bbac8
validate is a skill published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 24d ago), licensed MIT. It adds 134 tokens to every session and 1,305 once invoked, about $0.0007 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 2026-09-03.
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…