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/paullukic/coographWrote 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/paullukic/coograph/plugin)<a href="https://agentmods.dev/plugins/paullukic/coograph/plugin"><img src="https://agentmods.dev/badge/plugins/paullukic/coograph/plugin/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/paullukic/coograph/plugin"><img src="https://agentmods.dev/badge/plugins/paullukic/coograph/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
coograph 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 9d 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": "coograph",
"version": "1.8.5",
"description": "Graph-first AI coding workflow: Plan, Propose, Apply, Review, Archive with OpenSpec gates, evidence-based agents, and guardrail hooks.",
"author": {
"name": "Paul Lukic",
"url": "https://github.com/paullukic"
},
"homepage": "https://coograph.com",
"repository": "https://github.com/paullukic/coograph",
"license": "MIT",
"keywords": [
"workflow",
"openspec",
"code-review",
"code-graph",
"agents"
]
}
What it installs
The manifest is a name and a version. 5 skills travel with it, and installing the plugin installs all of them — 187 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 9d ago Changed f752af3f77b5
- 20d ago Changed 1292291143a4
- 24d ago Changed f473bce7921b
- 25d ago Changed ebf5989ec0e5
- 26d ago Changed dda9566c5eaf
- 1mo ago First seen · 20 lines scan A b3e20cce86a6
coograph is a plugin published in the GitHub repository paullukic/coograph (17 stars, last pushed 9d 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 2026-09-16.
Other plugins, from other repositories
roam-code
Local codebase intelligence + change-safety gates for coding agents. REQUIRES Python 3.10+ and pip install roam-code first — this plugin launches the roam binary from your PATH, and its MCP server cannot start without it. Pre-indexes your repo's symbols, call graph, deps, and git history into SQLite (28 languages.
comprehensive-review
Multi-perspective code analysis covering architecture, security, and best practices.
jury
Jury v0.1.0 — standalone cross-family cascade-then-jury reviewer (Gemini + GPT small-fish → cross-family tiebreaker). The free 'jury beats judge' base; codi and super-developer depend on it optionally for cross-family verification. No API keys (OAuth local CLIs).
genesis-spec-kit
AI coding with intent — the end of vibe coding. A spec-driven pipeline for Claude Code that loops a five-lens audit to zero findings before code ships. It won't save you time or tokens; it saves you from slop. File-backed, no external services. Legacy (V2-era) edition.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.