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/agagniere/spekyWrote 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/agagniere/speky/speky)<a href="https://agentmods.dev/plugins/agagniere/speky/speky"><img src="https://agentmods.dev/badge/plugins/agagniere/speky/speky/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/agagniere/speky/speky"><img src="https://agentmods.dev/badge/plugins/agagniere/speky/speky.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
speky 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": "speky",
"description": "Skills to best use Speky, the requirements and test specification manager.",
"author": {
"name": "Antoine Gagniere",
"email": "[email protected]",
"url": "https://github.com/agagniere"
},
"homepage": "https://agagniere.github.io/speky",
"repository": "https://github.com/agagniere/speky",
"license": "MIT",
"keywords": [
"specification",
"requirements"
],
"skills": [
"./claude_plugin/skills/init",
"./claude_plugin/skills/speky-workflow",
"./claude_plugin/skills/write-test-plans"
],
"agents": [
"./claude_plugin/agents/code-test-reviewer.md",
"./claude_plugin/agents/requirement-reviewer.md",
"./claude_plugin/agents/test-plan-author.md",
"./claude_plugin/agents/test-plan-reviewer.md"
],
"mcpServers": {
"speky": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"speky-mcp",
"specs/spec.yaml"
],
"env": {
"UV_CACHE_DIR": "${CLAUDE_PLUGIN_DATA}/uvcache",
"UV_PROJECT": "${CLAUDE_PLUGIN_ROOT}"
}
},
"speky-selfspec": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"speky-mcp",
"specs/speky.yaml",
"specs/mcp/mcp.toml"
],
"env": {
"UV_CACHE_DIR": "${CLAUDE_PLUGIN_DATA}/uvcache",
"UV_WORKING_DIR": "${CLAUDE_PLUGIN_ROOT}"
}
}
}
}
What it installs
The manifest is a name and a version. 3 skills, 4 agents travel with it, and installing the plugin installs all of them — 385 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 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 · 57 lines scan A b333e1a7b9af
speky is a plugin published in the GitHub repository agagniere/speky (2 stars, last pushed 5mo 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
crap-analyzer
Analyze recently-changed code for Change Risk Anti-Patterns. Computes CRAP per changed function across TypeScript, JavaScript, Python, Java, Kotlin, Go, Ruby, C#, Rust, and PHP. Auto-discovers how the repo generates coverage and proposes refactors + test stubs.
fuse-react
Expert React 19 with hooks, TanStack Router, TanStack Form, Zustand, Testing Library, shadcn/ui, and SOLID principles.
dev-loop
Multi-agent orchestration grounded in an LLM wiki. /dev-loop:orchestrate splits one goal into a dependency graph of parallel Claude Code sessions, each in its own worktree, and supervises them natively on Orca (a tracked Task + Dispatch per phase, pushed workerdone / question / escalation events instead of polling, st.
looptimal
Turns an objective into a delivered, VERIFIED OUTCOME: frames a hash-pinned sealed acceptance suite, designs the right loop (the loop-design wizard, formerly LoopPrint), war-games it forward, executes with dynamic domain-expert sub-agents (maker != checker), and gates completion on a separate verifier re-running the…
polygraph
A polygraph for your state machine. The agent does the hard part for you: it instruments your code, builds any test doubles needed to run it, and captures real execution traces — then has an LLM derive a transition-function spec from the source (default: a SAM v2 strict-profile module with named…
superpowers-orchestrator
Agentic development framework for Claude Code — disciplined workflow routing, TDD enforcement, safety hooks, systematic debugging, and code review.