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/shinpr/claude-code-discoverWrote 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/shinpr/claude-code-discover/claude-code-discover)<a href="https://agentmods.dev/plugins/shinpr/claude-code-discover/claude-code-discover"><img src="https://agentmods.dev/badge/plugins/shinpr/claude-code-discover/claude-code-discover/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/shinpr/claude-code-discover/claude-code-discover"><img src="https://agentmods.dev/badge/plugins/shinpr/claude-code-discover/claude-code-discover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
discover 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": "discover",
"version": "0.4.1",
"description": "Discover product opportunities, validate hypotheses, and create evidence-backed PRDs in your repository",
"author": {
"name": "shinpr",
"url": "https://github.com/shinpr"
},
"homepage": "https://github.com/shinpr/claude-code-discover",
"repository": "https://github.com/shinpr/claude-code-discover.git",
"license": "MIT",
"keywords": [
"product-discovery",
"hypothesis-driven",
"prd",
"validation",
"product-management"
],
"agents": [
"./agents/prd-reviewer.md",
"./agents/codebase-analyzer.md",
"./agents/hypothesis-verifier.md",
"./agents/knowledge-distiller.md",
"./agents/prototype-generator.md"
]
}
What it installs
The manifest is a name and a version. 15 skills, 5 agents travel with it, and installing the plugin installs all of them — 739 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill product-principles A 49 tokens
- Skill recipe-define A 27 tokens
- Skill recipe-validate A 26 tokens
- Skill hypothesis-discipline A 45 tokens
- Skill blueprint-standards A 43 tokens
- Skill recipe-blueprint A 31 tokens
- Skill recipe-discover A 17 tokens
- Skill recipe-reflect A 27 tokens
- Skill design-perspective A 49 tokens
- Skill prototype-guide A 49 tokens
- Skill recipe-persona A 19 tokens
- Skill recipe-refine-visuals A 31 tokens
- Skill recipe-vision A 17 tokens
- Skill business-context A 45 tokens
- Skill prd-standards A 52 tokens
- Agent prd-reviewer A 38 tokens
- Agent prototype-generator A 49 tokens
- Agent hypothesis-verifier A 42 tokens
- Agent knowledge-distiller A 41 tokens
- Agent codebase-analyzer A 42 tokens
What ships with it
1 file beside plugin.json 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 · 27 lines scan A 48105e85b1f8
discover is a plugin published in the GitHub repository shinpr/claude-code-discover (12 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 2026-08-31.
Other plugins, from other repositories
prfaq-dev
Amazon Working Backwards PR/FAQ process — generate professional LaTeX documents for product discovery and decision-making.
han-communication
Foundational communication plugin for the Han suite. Owns the canonical readability standard, the writing-voice profile, and the explanation standard for talking to a reader who will not implement the work, plus the readability-guidance skill that surfaces the first two into a calling skill's own context for in-voice…
handbook-agent-spec-kit
Spec-driven development workflow system with structured phases: Requirements → Design → Tasks → Implementation.
go-ultimate
Opinionated Go development skill — architecture, conventions, production readiness, repo/CI hygiene, review, and MCP/agent patterns.
deadeye
Fits model, effort, and context to each task via a deterministic policy kernel behind Claude Code hooks. He doesn't waste shots.
ar
ar — autoresearch: a skill-only autonomous experiment loop. Propose → measure → keep winners → repeat, against any numeric objective, with noise-floor gating so nothing is banked on noise. Five skills: /ar:start opens a run (dedicated branch + baseline noise floor), /ar:resume advances it, /ar:status prints read-only…