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/kimsanguine/hplanWrote 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/kimsanguine/hplan/operate)<a href="https://agentmods.dev/plugins/kimsanguine/hplan/operate"><img src="https://agentmods.dev/badge/plugins/kimsanguine/hplan/operate/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/kimsanguine/hplan/operate"><img src="https://agentmods.dev/badge/plugins/kimsanguine/hplan/operate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
operate 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": "operate",
"version": "1.1.0",
"description": "Operate and continuously improve AI agents — portfolio tiering, scorecards, weekly rollups, cross-team routing, KPI/North Star/OKR design (metrics-design), reliability measurement, cost monitoring, cohort analysis, incident response, stakeholder reporting (ops-review: exec-summary 임원 보고, weekly-update 팀 주간, partner-brief 외부 파트너, stakeholder update), and PM knowledge capture (pm-engine). Use when running agents in production: measuring health, communicating status to stakeholders, learning from outcomes, and feeding insights back into the next build cycle.",
"author": {
"name": "AI PM Skills Contributors",
"url": "https://github.com/kimsanguine"
},
"repository": "https://github.com/kimsanguine/hplan",
"license": "MIT",
"keywords": [
"agent",
"portfolio",
"operations",
"scorecard",
"tiering",
"multi-agent",
"rollup",
"routing",
"kpi",
"reliability",
"burn-rate",
"incident",
"pm-engine",
"knowledge",
"pm",
"agent-ecosystem",
"stakeholder",
"exec-summary",
"weekly-update",
"partner-brief",
"status-report"
],
"skills": "./skills/",
"commands": "./commands/"
}What it installs
The manifest is a name and a version. 6 skills travel with it, and installing the plugin installs all of them — 494 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.
- 1mo ago First seen · 36 lines scan A 285d48d060fe
operate is a plugin published in the GitHub repository kimsanguine/hplan (3 stars, last pushed 2mo 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
sd0x-dev-flow
Harness engineering for Claude Code — reminder-layer review hooks, behaviour-layer gates, and fail-closed safety where it counts.
gan-zhong-xue
A learning add-on that turns AI-made code changes into guided, explainable understanding. It uses a question-and-answer process so developers can restate the reasoning and apply it elsewhere.
yield-xyz-agentkit-builder
Build applications that integrate the Yield.xyz API — generate integration code for DeFi yield across 80+ networks.
skill-engine
Teach Claude your codebase, then keep it taught. On opt-in, clones registered git sources to a local cache (/.cache/skill-engine/) and installs per-skill context files under your project's .claude/skills/. Reads only paths you register.
ed3d-extending-claude
Knowledge skills for extending Claude Code: creating plugins, commands, agents, skills, hooks, MCP servers, and marketplace management.
ed3d-00-getting-started
Getting started guide and onboarding for ed3d-plugins.