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.
/plugin marketplace add KevinZai/commandernpx agentmods add plugins/kevinzai/commander/cowork-plugingit 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/cowork-plugin)<a href="https://agentmods.dev/plugins/kevinzai/commander/cowork-plugin"><img src="https://agentmods.dev/badge/plugins/kevinzai/commander/cowork-plugin.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
commander 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 yesterday.
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",
"displayName": "Commander",
"version": "7.4.2",
"description": "Guided AI PM for Claude Code, running on The Fable Method — 12 enforceable gates so any model produces Fable-shaped results. 83 plugin skills (click-first /ccc-* workflows), 22 specialist sub-agents (architect, reviewer, debugger, designer, security-auditor…), 23 lifecycle hooks × 44 handlers, 2 bundled MCP servers + 16 opt-in. Works in Claude Code Desktop, CLI, Cursor, Windsurf, Cline, Codex. Core free forever — no signup, no card. MIT-licensed.",
"author": {
"name": "Kevin Zicherman",
"url": "https://kevinz.ai"
},
"homepage": "https://commanderplugin.com",
"repository": "https://github.com/KevinZai/commander",
"license": "MIT",
"defaultEnabled": true,
"keywords": [
"project-manager",
"skills",
"orchestration",
"linear",
"fleet",
"knowledge",
"night-mode",
"desktop",
"web-search",
"tavily",
"context7",
"mcp",
"mcp-server",
"hosted",
"beta",
"cursor",
"windsurf"
]
}
What it installs
The manifest is a name and a version. 22 agents, 22 hooks travel with it, and installing the plugin installs all of them — 756 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Agent csharp-reviewer A 35 tokens
- Agent java-reviewer A 33 tokens
- Agent kotlin-reviewer A 31 tokens
- Agent rust-reviewer A 34 tokens
- Agent go-reviewer A 31 tokens
- Agent typescript-reviewer A 38 tokens
- Agent architect A 31 tokens
- Agent builder A 37 tokens
- Agent data-analyst A 31 tokens
- Agent debugger A 35 tokens
- Agent performance-engineer A 32 tokens
- Agent product-manager A 39 tokens
- Agent qa-engineer A 34 tokens
- Agent researcher A 32 tokens
- Agent reviewer A 31 tokens
- Agent security-auditor A 35 tokens
- Agent technical-writer A 37 tokens
- Agent content-strategist A 37 tokens
- Agent designer A 36 tokens
- Agent python-reviewer B 37 tokens
- Agent devops-engineer C 38 tokens
- Agent fleet-worker C 32 tokens
- Hook PermissionRequest A not measured
- Hook SubagentStop A not measured
- Hook Stop A not measured
- Hook ConfigChange A not measured
- Hook Elicitation A not measured
- Hook InstructionsLoaded A not measured
- Hook Notification A not measured
- Hook PostCompact A not measured
- Hook PostToolBatch A not measured
- Hook PostToolUseFailure A not measured
- Hook StopFailure A not measured
- Hook SubagentStart A not measured
- Hook TaskCreated A not measured
- Hook UserPromptExpansion A not measured
- Hook PreCompact A not measured
- Hook ElicitationResult A not measured
- Hook PreToolUse A not measured
- Hook PostToolUse A not measured
- Hook UserPromptSubmit A not measured
- Hook Setup A not measured
- Hook SessionEnd A not measured
- Hook TaskCompleted A not measured
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.
- yesterday First seen · 34 lines scan A f2184247b542
commander 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 2026-09-03.
Other plugins, from other repositories
arrow-maintenance
Scaling layer for linked-intent-dev. Tracks spec-to-code coherence across large projects via docs/arrows/ index. Includes brownfield bootstrap for mapping existing codebases.
debt-ops
Every shortcut your coding agent takes, saved to your repo as it happens. Fix them when you're ready.
specmanager
Lifecycle kanban for Claude Code projects (PRD → architecture → plan → tasks → walkthroughs).
coco
Autonomous spec-driven development for Claude Code. Describe a feature, get merged, tested, reviewed code.
shipwithai-starter
Sets up a standardized Claude Code harness for your project: CLAUDE.md, permissions, hooks, MCP servers, agents, SSOT docs, and observability logging. One init interview, consistent harness across every team member.
catalyst-dev
Complete development workflow: research → plan → implement → validate → ship. Includes research agents, planning tools, handoff system, Linear integration, and PM commands.