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/laurigates/claude-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/laurigates/claude-plugins/agent-patterns-plugin)<a href="https://agentmods.dev/plugins/laurigates/claude-plugins/agent-patterns-plugin"><img src="https://agentmods.dev/badge/plugins/laurigates/claude-plugins/agent-patterns-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/laurigates/claude-plugins/agent-patterns-plugin"><img src="https://agentmods.dev/badge/plugins/laurigates/claude-plugins/agent-patterns-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-patterns-plugin 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 3d 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": "agent-patterns-plugin",
"version": "2.50.3",
"description": "Agent configuration utilities - project assimilation, config auditing, teammate definitions, MCP management, and hooks configuration",
"author": {
"name": "Lauri Gates"
},
"license": "MIT",
"hooks": "./hooks.json",
"keywords": [
"agents",
"configuration",
"assimilation",
"audit",
"mcp",
"mcp-code-execution",
"mcp-server-authoring",
"fastmcp",
"hooks",
"custom-agents",
"teammate-definitions",
"agent-teams",
"teams",
"multi-agent",
"plugin-settings",
"adversarial-review",
"red-team",
"multi-model",
"pal",
"code-review",
"execution-grounded-review"
]
}
What it installs
The manifest is a name and a version. 24 skills travel with it, and installing the plugin installs all of them — 1,048 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill parallel-agent-dispatch A 37 tokens
- Skill execution-grounded-review A 30 tokens
- Skill cold-read-gate A 42 tokens
- Skill multi-model-delegation A 41 tokens
- Skill adversarial-review A 37 tokens
- Skill agent-cli-worktree-safety A 53 tokens
- Skill custom-agent-definitions A 37 tokens
- Skill mcp-server-authoring A 50 tokens
- Skill probe-input-integrity A 47 tokens
- Skill exclusive-lock-dispatch A 44 tokens
- Skill harness-tool-errors A 48 tokens
- Skill meta-audit A 38 tokens
- Skill tool-result-traps A 68 tokens
- Skill verify-before-plan A 44 tokens
- Skill mcp-code-execution A 43 tokens
- Skill meta-context-diet A 49 tokens
- Skill agent-teams A 40 tokens
- Skill meta-local-notes A 46 tokens
- Skill wave-based-dispatch A 39 tokens
- Skill expose-tunable-knob A 56 tokens
- Skill meta-assimilate A 42 tokens
- Skill mcp-management B 40 tokens
- Skill plugin-settings C 36 tokens
- Skill meta-promote D 41 tokens
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.
- 3d ago Changed 4f8b25a42d79
- 6d ago Changed f573230d7712
- 9d ago Changed aadac870b1df
- 11d ago Changed 94ad60183c00
- 15d ago Changed 8c9f4bbcb34f
- 18d ago Changed 811a39e61fa8
- 20d ago Changed aa3fb994d481
- 22d ago Changed · +4 lines 3873ca620862
- 27d ago Changed ab1cc775ce36
- 29d ago First seen · 31 lines scan A f6188d6fb692
agent-patterns-plugin is a plugin published in the GitHub repository laurigates/claude-plugins (60 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 2026-08-30.
Other plugins, from other repositories
dev-tooling
Three MCP servers for PHP and JavaScript operations. PHP (php-tooling): PHPStan, ECS, Rector, PHPUnit, PHPUnit coverage gap analysis, Symfony Console. Administration (js-admin-tooling): ESLint, Stylelint, Prettier, Jest, TypeScript, Vite builds. Storefront (js-storefront-tooling): ESLint, Stylelint, Jest, Webpack…
instruction-placement
Routes agent instructions to the surface that loads them at the right time. audit finds conventions narrower than the always-loaded CLAUDE.md or AGENTS.md, or stranded in docs Claude never loads, and proposes a destination with a validated paths glob; safety content is never demoted. realign applies each move and…
a11y-audit
Full accessibility audit with WCAG compliance checking.
code-review-assistant
Automated code review with severity levels and actionable feedback.
design-compare
Compare Figma designs against implementation screenshots with interactive HTML reports.
ryk
ryk safety hooks and skills for Claude Code.