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/strzhao/autopilotWrote 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/strzhao/autopilot/npm-toolkit)<a href="https://agentmods.dev/plugins/strzhao/autopilot/npm-toolkit"><img src="https://agentmods.dev/badge/plugins/strzhao/autopilot/npm-toolkit/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/strzhao/autopilot/npm-toolkit"><img src="https://agentmods.dev/badge/plugins/strzhao/autopilot/npm-toolkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
npm-toolkit 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": "npm-toolkit",
"version": "2.0.0",
"description": "npm 发布与 GitHub Actions CI/CD 配置工具包。包含 OIDC trusted publishing 自动发布、安全最佳实践、发布自动化工具选型和 GitHub Actions 工作流配置",
"author": {
"name": "stringzhao",
"email": "[email protected]"
},
"license": "MIT",
"keywords": ["npm", "publish", "github-actions", "ci", "cd", "oidc", "trusted-publishing", "security", "changesets", "semantic-release", "release-please", "monorepo", "provenance", "2fa"]
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 227 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.
- 1mo ago First seen · 12 lines scan A fee31dedf81c
npm-toolkit is a plugin published in the GitHub repository strzhao/autopilot (32 stars, last pushed 5d 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
nyann
Project governance for Claude Code. Bootstrap and maintain git workflow, hooks, commits, releases, CI, docs, and repo health.
ship
Complete PR workflow from commit to production with validation.
release-please-monorepo
Set up automated semantic versioning, changelogs, and per-package publishing in a pnpm/Turbo monorepo using googleapis/release-please-action v4.
claude-plugin-repo-ci-release
Wire up CI validation and automatic release-cutting for a Claude Code plugin or marketplace repo (one with a .claude-plugin/marketplace.json and plugins/). Adds two GitHub Actions — a structure validator on every PR/push, and a release-on-version-bump job that cuts a GitHub Release whenever VERSION changes — plus the.
release
Xcode release automation for Claude Code: SemVer bumps and tags, changelogs, decisions tracking and TestFlight notes for iOS/macOS apps.
pr-trains
Batch operators for GitHub queues: review-train reviews every open PR, fix-train applies requested changes, fix-ci-train turns red CI green, merge-train fixes and merges in dependency order, issue-train triages and builds one PR per actionable issue — all with parallel sub-agents and one grouped confirmation.