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 vladolaru/claude-code-pluginsnpx agentmods add plugins/vladolaru/claude-code-plugins/pirategoat-toolsgit clone --depth 1 https://github.com/vladolaru/claude-code-pluginsWrote 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/vladolaru/claude-code-plugins/pirategoat-tools)<a href="https://agentmods.dev/plugins/vladolaru/claude-code-plugins/pirategoat-tools"><img src="https://agentmods.dev/badge/plugins/vladolaru/claude-code-plugins/pirategoat-tools.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
pirategoat-tools 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "pirategoat-tools",
"source": "./plugins/pirategoat-tools",
"description": "Code review orchestration (28 domain reviewers + pipeline/cross-validation agents), WordPress/WooCommerce development patterns, Figma-to-code workflow, accessibility guidance, testing patterns, and browser automation.",
"version": "1.117.0",
"author": {
"name": "Vlad Olaru"
},
"repository": "https://github.com/vladolaru/claude-code-plugins",
"license": "MIT",
"keywords": [
"wordpress",
"project-management",
"code-review",
"browser-automation",
"linear",
"architecture",
"design-patterns",
"accessibility",
"a11y",
"wcag",
"figma",
"design-system",
"design-to-code",
"copy-sync"
],
"category": "development-tools",
"strict": true,
"skills": [
"./skills/wordpress-backend-dev",
"./skills/browser-interaction",
"./skills/dig-into-linear-issue",
"./skills/woocommerce-browser-interaction",
"./skills/testing-patterns",
"./skills/php-testing-patterns",
"./skills/js-testing-patterns",
"./skills/e2e-testing-patterns",
"./skills/go-testing-patterns",
"./skills/rust-testing-patterns",
"./skills/python-testing-patterns",
"./skills/software-architecture",
"./skills/accessible-frontend-dev",
"./skills/using-figma",
"./skills/figma-copy-sync",
"./skills/analyzing-cc-sessions",
"./skills/analyzing-codex-sessions",
"./skills/creating-md-slides",
"./skills/current-datetime",
"./skills/decision-critic",
"./skills/marp-slide-quality",
"./skills/create-github-pr"
],
"commands": [
"./commands/full-code-review.md",
"./commands/code-review.md",
"./commands/pr-update.md",
"./commands/pr-review.md",
"./commands/copy-as.md",
"./commands/switch-to.md",
"./commands/iterative-review.md"
],
"agents": [
"./agents/technical-writer.md",
"./agents/code-reviewer.md",
"./agents/security-reviewer.md",
"What it installs
The manifest is a name and a version. 22 skills travel with it, and installing the plugin installs all of them — 1,165 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill analyzing-codex-sessions A 82 tokens
- Skill dig-into-linear-issue A 42 tokens
- Skill figma-copy-sync A 65 tokens
- Skill accessible-frontend-dev A 49 tokens
- Skill analyzing-cc-sessions A 71 tokens
- Skill using-figma A 70 tokens
- Skill browser-interaction A 35 tokens
- Skill woocommerce-browser-interaction A 59 tokens
- Skill wordpress-backend-dev A 66 tokens
- Skill create-github-pr A 40 tokens
- Skill python-testing-patterns A 52 tokens
- Skill rust-testing-patterns A 52 tokens
- Skill creating-md-slides A 54 tokens
- Skill current-datetime A 107 tokens
- Skill go-testing-patterns A 40 tokens
- Skill marp-slide-quality A 63 tokens
- Skill decision-critic A 6 tokens
- Skill software-architecture A 51 tokens
- Skill testing-patterns A 42 tokens
- Skill e2e-testing-patterns A 43 tokens
- Skill js-testing-patterns A 37 tokens
- Skill php-testing-patterns A 39 tokens
What ships with it
1 file beside marketplace.json#pirategoat-tools 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.
- today Changed 4b5108fcae56
- yesterday First seen · 98 lines scan A b40e37780c09
pirategoat-tools is a plugin published in the GitHub repository vladolaru/claude-code-plugins (8 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
sap-sac-test-automation
SAP Analytics Cloud (SAC) automated testing skill for designing capability-gated browser discovery and deterministic Playwright test suites for SAC stories, dashboards, reports, planning workflows, comments, permissions, visual regression, and reusable QA automation. This skill should be used when building SAC…
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction.
accessibility-test-scanner
A11y compliance testing with WCAG 2.1/2.2 validation, screen reader compatibility, and automated accessibility audits.
flow-tester
Discovers a web app's user flows, drives a real Chromium browser through them with a live local dashboard, flags functional/content/visual/console bugs, and runs a read-only security audit on local source. Identify-only, never fixes.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.