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/TeamManagementPlugin/claude-pluginWrote 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/teammanagementplugin/claude-plugin/plugin)<a href="https://agentmods.dev/plugins/teammanagementplugin/claude-plugin/plugin"><img src="https://agentmods.dev/badge/plugins/teammanagementplugin/claude-plugin/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/teammanagementplugin/claude-plugin/plugin"><img src="https://agentmods.dev/badge/plugins/teammanagementplugin/claude-plugin/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
team-management 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": "team-management",
"displayName": "team.management",
"version": "0.4.5",
"description": "Your AI on rails. On your terms. An open-source protocol engine that puts every process on rails — enforced as it happens, so your AI can't fake the work.",
"author": { "name": "Team Management" },
"homepage": "https://team.management",
"repository": "https://github.com/TeamManagementPlugin/claude-plugin",
"keywords": ["claude-code", "mcp", "daic", "protocol-engine", "task-management", "code-review", "ai-agents"],
"license": "MIT"
}
What it installs
The manifest is a name and a version. 9 commands, 17 agents, 6 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 1,045 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command config A 12 tokens
- Command wiki-lint A 14 tokens
- Command wiki-ingest A 10 tokens
- Command clean-check A 27 tokens
- Command custom-protocol-create A 12 tokens
- Command custom-protocol-update-after-reinstall A 11 tokens
- Command changelog A 25 tokens
- Command wiki-tune A 7 tokens
- Command init B 19 tokens
- Agent agy-cli A 97 tokens
- Agent code-review A 77 tokens
- Agent code-cleanliness A 78 tokens
- Agent codex-cli A 89 tokens
- Agent red-team A 99 tokens
- Agent service-documentation A 65 tokens
- Agent spec-compliance-reviewer A 0 tokens
- Agent testing-specialist A 82 tokens
- Agent logging A 26 tokens
- Agent context-gathering A 59 tokens
- Agent context-refinement A 32 tokens
- Agent scope-strategist A 33 tokens
- Agent critic A 29 tokens
- Agent risk-security-analyst A 38 tokens
- Agent code-architect A 40 tokens
- Agent code-explorer A 33 tokens
- Agent user-perspective A 31 tokens
- Hook PreToolUse A not measured
- Hook UserPromptSubmit A not measured
- Hook SessionStart A not measured
- Hook PostToolUse A not measured
- Hook PreCompact A not measured
- Hook UserPromptExpansion A not measured
- MCP server tm A not measured
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 Changed ecd0d13d2532
- 1mo ago First seen · 12 lines scan A 4ebe0768e747
team-management is a plugin published in the GitHub repository TeamManagementPlugin/claude-plugin (6 stars, last pushed 2d 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
hmd
Nothing ships unproven. Heimdall is an autonomous multi-agent orchestrator for Claude Code that turns one prompt into a finished project — and keeps moving the bar on what counts as done: every plan wires an external, falsifiable oracle so the implementation can never grade its own homework, and the merge stays…
version-sentinel
Hard-blocks dependency additions, bumps, and downgrades until a fresh, source-cited version check is recorded. Supports npm, pip, Poetry/uv, Cargo, and NuGet.
talk-to-anyone
Turn any public figure into your personal coach, living or historical. /coach researches the person across the web, pulls real transcripts when they have video anywhere on YouTube, builds a persona, and talks to you as them until you switch or end.
magi
Multi-model engineering workflow with MAGI weighted voting and cross-CLI orchestration.
claude-webcache
Cross-session WebFetch cache for Claude Code. WebFetches disappear after 15 minutes — claude-webcache makes them persist.
compounded
Turns your agent into a trainable employee. Learns rules from your corrections (with your approval), and skills earn autonomy through demonstrated reliability — proposed → verified → trusted → autonomous. No daemon. No cloud.