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/josix/agent-flowWrote 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/josix/agent-flow/agent-flow)<a href="https://agentmods.dev/plugins/josix/agent-flow/agent-flow"><img src="https://agentmods.dev/badge/plugins/josix/agent-flow/agent-flow/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/josix/agent-flow/agent-flow"><img src="https://agentmods.dev/badge/plugins/josix/agent-flow/agent-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-flow 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 17d 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": "agent-flow",
"version": "1.11.0",
"description": "Transform Claude Code into a multi-agent orchestrated system with verification gates",
"author": {
"name": "Wilson \"Josix\" Wang"
},
"license": "MIT",
"repository": "https://github.com/josix/agent-flow",
"keywords": [
"multi-agent",
"orchestration",
"verification",
"quality-gates"
],
"mcpServers": {
"graphify": {
"type": "stdio",
"command": "${CLAUDE_PLUGIN_ROOT}/scripts/start-graphify-mcp.sh"
},
"agentsview": {
"type": "stdio",
"command": "${CLAUDE_PLUGIN_ROOT}/scripts/start-agentsview-mcp.sh"
}
}
}
What it installs
The manifest is a name and a version. 11 skills, 5 commands, 6 agents, 7 hooks travel with it, and installing the plugin installs all of them — 763 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill skill-agent-mapping A 34 tokens
- Skill exploration-strategy A 34 tokens
- Skill personal-kb-usage A 39 tokens
- Skill prompt-refinement A 36 tokens
- Skill team-decision A 39 tokens
- Skill verification-gates A 38 tokens
- Skill agent-behavior-constraints A 41 tokens
- Skill agentsview-usage A 55 tokens
- Skill graphify-usage A 36 tokens
- Skill task-classification A 37 tokens
- Skill explainer-design-system A 140 tokens
- Command explain A 44 tokens
- Command analyze A 0 tokens
- Command orchestrate B 0 tokens
- Command team-orchestrate A 0 tokens
- Command deep-dive B 13 tokens
- Agent Speedwagon A 56 tokens
- Agent Lawliet A 25 tokens
- Agent Riko A 24 tokens
- Agent Senku A 23 tokens
- Agent Loid A 23 tokens
- Agent Alphonse A 26 tokens
- Hook SessionStart A not measured
- Hook PostToolUse A not measured
- Hook Stop A not measured
- Hook PreToolUse A not measured
- Hook SessionEnd A not measured
- Hook SubagentStop A not measured
- Hook UserPromptSubmit 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.
- 17d ago Changed · +10 lines ed53cd961692
- 1mo ago First seen · 17 lines scan A 2940ea0a2bc4
agent-flow is a plugin published in the GitHub repository josix/agent-flow (7 stars, last pushed 16d 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
loki-seal
Stop hook that refuses 'done' while the repo's real tests are red or were deleted, skipped, xfailed or weakened. Runs locally, no model calls, prints a 5-line receipt.
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.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins marketplace
Plugin marketplace listing 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.