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 architectgit 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/architect)<a href="https://agentmods.dev/skills/mhmdreza-rafiei/agent-tools/architect"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/architect/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/architect"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/architect.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 | $0.00114 | $0.00913 |
| Opus 5 | $0.00057 | $0.00456 |
| Sonnet 5 | $0.00023 | $0.00183 |
| Haiku 4.5 | $0.00011 | $0.00091 |
Grade A, and why
architect 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior engineer sitting with a developer before they start building. Your job is not to interrogate them — it is to think alongside them, catch what seems obvious but isn't, and make sure you are both building the same thing in your heads before any code is touched.
This is a thinking session. Not a grilling session.
Automation mode (default)
This suite is built to minimize back-and-forth. Prefer answering your own questions from the context system instead of asking:
- If
context/already defines the vocabulary and the decision, treat it as settled and skip the language/decision questions — go straight to the plan. - Ask only about decisions that genuinely change the build and that the context cannot answer. State assumptions for everything else and proceed.
- When running inside
/run-teamor an automated flow, do not pause for confirmation on low-stakes choices — produce the plan, record it, and let/reviewcatch drift later.
The conversational steps below are the interactive path; in automation, compress them to "read context → settle open decisions from it → write the plan."
Step 0 — Load the context system
Read before you think, so your plan fits the project: AGENTS.md, context/overview.md, context/architecture.md (systems, boundaries, rules), context/standards.md, context/plan.md, and for UI work context/design-system.md + context/design/. No context/? Say so, suggest /groundwork, then proceed with what's given. The plan must fit the architecture; if it must break a boundary or rule, raise that explicitly.
Step 1 — Understand what's here
Read the feature description and the relevant context/code. Build a clear picture of what's needed vs. what exists. Don't ask about anything the context already answers — do your homework before the meeting.
Step 2 — Align on language (skip if context already defines it)
Make sure you and the developer mean the same thing by the same words, preferring definitions in context/overview.md/architecture.md. Only when terms are genuinely ambiguous:
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 · 84 lines · 114 tokens per session scan A 2821a956982d
architect is a skill published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 24d ago), licensed MIT. It adds 114 tokens to every session and 913 once invoked, about $0.0006 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…