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.
git clone --depth 1 https://github.com/smicolon/ai-kitWrote 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/plugins/smicolon/ai-kit/clarify)<a href="https://agentmods.dev/plugins/smicolon/ai-kit/clarify"><img src="https://agentmods.dev/badge/plugins/smicolon/ai-kit/clarify/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/plugins/smicolon/ai-kit/clarify"><img src="https://agentmods.dev/badge/plugins/smicolon/ai-kit/clarify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
clarify 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 1mo 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.
What it actually says
{
"name": "clarify",
"version": "0.1.1",
"description": "Pre-implementation clarification: detect ambiguity in tasks and produce a structured execution context before code is written",
"source": "./packs/clarify",
"author": {
"name": "Smicolon",
"email": "[email protected]",
"url": "https://github.com/smicolon"
},
"homepage": "https://github.com/smicolon/ai-kit",
"repository": "https://github.com/smicolon/ai-kit",
"license": "MIT",
"category": "workflow",
"keywords": [
"clarify",
"pre-implementation",
"ambiguity",
"execution-context",
"flow-detection",
"tdd"
],
"agents": [
"./agents/clarifier.md"
],
"commands": [
"./commands/clarify.md"
],
"skills": [
"./skills/flow-detector",
"./skills/flow-selector",
"./skills/execution-context-builder"
]
}What it installs
The manifest is a name and a version. 3 skills travel with it, and installing the plugin installs all of them — 199 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside marketplace.json#clarify in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 34 lines scan A d1e1548f40b4
clarify is a plugin published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
job-apply
AI-powered job application assistant for Claude Code and Codex covering LinkedIn, Greenhouse, Ashby, Lever, Rippling, and Workday.
project-toolkit
Specialized agent definitions, reusable skills, and lifecycle hooks for GitHub Copilot CLI, generated from Claude canonical sources.
aio-saas-tools
Drive Jira, Confluence, Google Workspace (Drive/Gmail/Calendar/Sheets/Docs), Tanca HR, and X/Twitter from your terminal — one CLI per service, no context switching.
opencairn
Skills for Claude Code: park/pickup session chaining, morning/afternoon/goodnight day loops, weekly & quarterly reviews, a six-layer cross-model audit panel, and PKM utilities. Designed to pair with the OpenCairn NIPARAS vault, but the skills install standalone.
navigator
Finish What You Start - Sessions that last, AI that learns, Features that ship. Context engineering + Theory of Mind + Knowledge Graph + Loop Mode + Task Mode. Features Project Knowledge Graph (unified search, experiential memory), unified workflow orchestration, auto-update on session start, ToM-based verification…
claude-pilot
SPEC-First development workflow with TDD, Ralph Loop, and autonomous agent coordination for Claude Code.