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/KevinZai/commanderWrote 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/kevinzai/commander/marketplace)<a href="https://agentmods.dev/plugins/kevinzai/commander/marketplace"><img src="https://agentmods.dev/badge/plugins/kevinzai/commander/marketplace/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/kevinzai/commander/marketplace"><img src="https://agentmods.dev/badge/plugins/kevinzai/commander/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
commander-hub marketplace 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": "commander-hub",
"owner": {
"name": "Kevin Zicherman",
"url": "https://kevinz.ai"
},
"plugins": [
{
"name": "commander",
"displayName": "Commander",
"source": "./commander/cowork-plugin",
"description": "CC Commander — Guided AI PM for Claude Code, running on **The Fable Method** (12 enforceable gates so any model produces Fable-shaped results). Brain/hands architecture with **22 specialist sub-agent personas** (architect · reviewer · builder · security-auditor · debugger · designer · qa-engineer · devops · data-analyst · content-strategist · product-manager · performance-engineer · researcher · technical-writer · fleet-worker · typescript-reviewer · python-reviewer). **83 plugin skills** incl **17 click-first `/ccc-*` workflows** + `/ccc-save-session` + `/ccc-resume-session` + `/ccc-e2e` + `/ccc-memory` + `/ccc-tasks` + `/ccc-recall` + `/ccc-fleet-viz` + `/ccc-changelog` + `/ccc-doctor` + `/ccc-upgrade` + `/ccc-deploy` + `/ccc-rollback` + `/ccc-onboard`. **23 lifecycle hooks × 44 handlers** (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, Notification, PreCompact, SubagentStop). **2 credential-free bundled MCP servers** (context7 + sequential-thinking) + 16 opt-in via /ccc-connect. Native Plan pane integration (EnterPlanMode + ExitPlanMode), spawn_task sidebar chips, mark_chapter session nav. 467+ skills across 11 CCC domains. Works in Claude Code Desktop, Cowork Desktop, CLI, Cursor, Windsurf, Cline, Continue, Codex. **Free for now.**",
"version": "7.4.2",
"category": "development",
"license": "MIT",
"author": {
"name": "Kevin Zicherman",
"url": "https://kevinz.ai"
}
}
],
"version": "7.4.2"
}
The plugins it lists here
This marketplace lists 1 plugin kept in the same repository. Each has its own page, its own measurements and its own install command.
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 · 24 lines scan A f7ee35893537
commander-hub marketplace is a plugin published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), 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
debt-ops
Every shortcut your coding agent takes, saved to your repo as it happens. Fix them when you're ready.
coco
Autonomous spec-driven development for Claude Code. Describe a feature, get merged, tested, reviewed code.
databases
Database experts for SQL, NoSQL, graph databases, and vector databases. Includes Postgres, MongoDB, Neo4j, Cassandra, MariaDB, and vector DB specialists.
paperclip-plugin
Autonomous AI company advisor for the Paperclip platform — create, design, and manage AI-powered companies with proper agent hierarchies, runtime configurations, and infrastructure following the Agent Companies spec (agentcompanies/v1).
masterplan
Brainstorm, plan, execute, resume, import, lint, and retrospect long-running Claude Code work with durable run bundles and strict context control.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.