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/Nanako0129/pilotfishWrote 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/nanako0129/pilotfish/plugin)<a href="https://agentmods.dev/plugins/nanako0129/pilotfish/plugin"><img src="https://agentmods.dev/badge/plugins/nanako0129/pilotfish/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/nanako0129/pilotfish/plugin"><img src="https://agentmods.dev/badge/plugins/nanako0129/pilotfish/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pilotfish 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 6d 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "pilotfish",
"displayName": "pilotfish",
"version": "1.5.0",
"description": "macOS and Linux Claude Code Plugin with hook-based ambient policy activation and namespaced role agents.",
"author": {
"name": "Nanako0129",
"url": "https://github.com/Nanako0129"
},
"repository": "https://github.com/Nanako0129/pilotfish",
"license": "MIT",
"keywords": [
"orchestration",
"ambient-activation",
"subagents",
"delegation"
]
}
What it installs
The manifest is a name and a version. 7 agents, 1 hook travel with it, and installing the plugin installs all of them — 426 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.
- 6d ago Changed · -1 lines 1944efe31ed5
- 7d ago Changed 658192e18120
- 20d ago Changed 574c3e7cb1f5
- 1mo ago First seen · 21 lines scan A 63e06017d369
pilotfish is a plugin published in the GitHub repository Nanako0129/pilotfish (708 stars, last pushed 6d 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 2026-08-30.
Other plugins, from other repositories
relay
Delegate work packets from a lead Claude Code session to executor sessions in their own iTerm tabs, with session reuse instead of always spawning fresh.
agent-taskgraph
Build native Claude Code Agent Teams with goals, roles, task graphs, collaboration protocols, and lifecycles.
ac
Main-agent planning trio (/ac:plan, /ac:execute, /ac:wisdom) with autonomous execution mode plus setup, init, commit commands and skill, agent, command, rule, CLAUDE.md creator skills. Two hooks back the workflow: SessionStart for twin-skill and resume, PreCompact for state preservation.
claude-hive
Cross-window multi-agent coordination for Claude Code — worktree isolation, GitHub PR workflows, and automated conflict detection.
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.