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/leandrosilvaferreira/claude-plugins-registryWrote 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/leandrosilvaferreira/claude-plugins-registry/aia-harness)<a href="https://agentmods.dev/plugins/leandrosilvaferreira/claude-plugins-registry/aia-harness"><img src="https://agentmods.dev/badge/plugins/leandrosilvaferreira/claude-plugins-registry/aia-harness/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/leandrosilvaferreira/claude-plugins-registry/aia-harness"><img src="https://agentmods.dev/badge/plugins/leandrosilvaferreira/claude-plugins-registry/aia-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
aia-harness 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 7d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What it installs
The manifest is a name and a version. 73 skills, 26 commands, 50 agents travel with it, and installing the plugin installs all of them — 6,449 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill cpp-coding-standards A 48 tokens
- Skill laravel-security A 32 tokens
- Skill quarkus-patterns A 52 tokens
- Skill quarkus-tdd A 53 tokens
- Skill check-consistency-workflow A 116 tokens
- Skill dart-flutter-patterns A 55 tokens
- Skill django-patterns A 32 tokens
- Skill django-tdd A 32 tokens
- Skill golang-testing A 35 tokens
- Skill kotlin-patterns A 37 tokens
- Skill kotlin-testing A 38 tokens
- Skill laravel-tdd A 29 tokens
- Skill python-patterns A 33 tokens
- Skill python-testing A 24 tokens
- Skill api-design A 31 tokens
- Skill django-security A 30 tokens
- Skill fastapi-patterns A 42 tokens
- Skill git-workflow A 33 tokens
- Skill golang-patterns A 27 tokens
- Skill mobile-design A 75 tokens
- Skill quarkus-security A 36 tokens
- Skill cpp-testing A 34 tokens
- Skill dotnet-patterns A 36 tokens
- Skill error-handling A 36 tokens
- Skill intelligent-routing A 50 tokens
- Skill java-coding-standards A 50 tokens
- Skill laravel-patterns A 32 tokens
- Skill react-patterns A 49 tokens
- Skill revise-agent-routing-workflow A 105 tokens
- Skill revise-claude-md A 100 tokens
- Skill coordinator-mode A 70 tokens
- Skill csharp-testing A 29 tokens
- Skill tailwind-patterns A 49 tokens
- Skill vulnerability-scanner A 48 tokens
- Skill behavioral-modes A 60 tokens
- Skill clean-code A 44 tokens
- Skill context-compression A 80 tokens
- Skill deployment-procedures A 51 tokens
- Skill game-art A 17 tokens
- Skill game-audio A 18 tokens
- Skill app-builder A 55 tokens
- Skill game-development A 44 tokens
- Skill jpa-patterns A 33 tokens
- Skill nuxt4-patterns A 37 tokens
- Skill batch-operations A 71 tokens
- Skill documentation-templates A 40 tokens
- Skill i18n-localization A 46 tokens
- Skill multiplayer A 15 tokens
- Skill pc-games A 19 tokens
- Skill performance-profiling A 37 tokens
- Skill powershell-windows A 42 tokens
- Skill revise-agent-frontmatter A 94 tokens
- Skill testing-patterns A 33 tokens
- Skill web-games A 20 tokens
- Skill 2d-games A 20 tokens
- Skill 3d-games A 18 tokens
- Skill game-design A 18 tokens
- Skill mcp-catalog A 66 tokens
- Skill mobile-games A 18 tokens
- Skill safe-hooks A 77 tokens
- Skill vr-ar A 16 tokens
- Skill architecture A 52 tokens
- Skill database-design A 51 tokens
- Skill lint-and-validate A 71 tokens
- Skill templates A 27 tokens
- Skill web-design-guidelines A 63 tokens
- Skill bash-linux B 55 tokens
- Skill harness-engineering B 96 tokens
- Skill red-team-tactics B 47 tokens
- Skill server-management B 47 tokens
- Skill condense-harness-prompts C 96 tokens
- Skill condense-harness-prompts-workflow C 98 tokens
- Skill memory-system C 74 tokens
- Command doctor A 24 tokens
- Command add-github-pm A 9 tokens
- Command orchestrate A 24 tokens
- Command condense-harness-prompts A 37 tokens
- Command scan A 18 tokens
- Command add-plugins A 46 tokens
- Command check-deps A 17 tokens
- Command add-mcp A 19 tokens
- Command deploy A 13 tokens
- Command check-consistency A 45 tokens
- Command revise-agent-routing A 27 tokens
- Command test A 14 tokens
- Command brainstorm A 14 tokens
- Command coordinate A 19 tokens
- Command create A 17 tokens
- Command debug A 13 tokens
- Command plan A 18 tokens
- Command remember A 20 tokens
- Command verify A 17 tokens
- Command enhance A 13 tokens
- Command preview A 15 tokens
- Command init C 21 tokens
- Command patch C 33 tokens
- Command add-obsidian D 25 tokens
- Command help D 37 tokens
- Command add-tools D 47 tokens
- Agent frontend-specialist A 43 tokens
- Agent orchestrator A 48 tokens
- Agent code-reviewer A 37 tokens
- Agent flutter-reviewer A 46 tokens
- Agent java-reviewer A 46 tokens
- Agent mobile-developer A 44 tokens
- Agent project-planner A 43 tokens
- Agent vue-reviewer A 60 tokens
- Agent react-build-resolver A 56 tokens
- Agent react-reviewer A 53 tokens
- Agent backend-specialist A 41 tokens
- Agent dart-build-resolver A 58 tokens
- Agent database-architect A 40 tokens
- Agent debugger A 40 tokens
- Agent django-build-resolver A 50 tokens
- Agent devops-engineer A 37 tokens
- Agent django-reviewer A 51 tokens
- Agent kotlin-reviewer A 46 tokens
- Agent rust-build-resolver A 47 tokens
- Agent security-reviewer A 50 tokens
- Agent typescript-reviewer A 50 tokens
- Agent csharp-reviewer A 57 tokens
- Agent explorer-agent A 47 tokens
- Agent game-developer A 46 tokens
- Agent penetration-tester A 43 tokens
- Agent performance-optimizer A 45 tokens
- Agent php-reviewer A 53 tokens
- Agent product-owner A 34 tokens
- Agent rust-reviewer A 44 tokens
- Agent security-auditor A 46 tokens
- Agent code-archaeologist A 44 tokens
- Agent cpp-build-resolver A 48 tokens
- Agent cpp-reviewer A 61 tokens
- Agent go-build-resolver A 45 tokens
- Agent harness-consistency-auditor A 93 tokens
- Agent product-manager A 31 tokens
- Agent python-reviewer A 41 tokens
- Agent qa-automation-engineer A 46 tokens
- Agent test-engineer A 36 tokens
- Agent documentation-writer A 42 tokens
- Agent fastapi-reviewer A 59 tokens
- Agent go-reviewer A 39 tokens
- Agent nestjs-code-reviewer A 70 tokens
- Agent nestjs-security-reviewer A 65 tokens
- Agent seo-specialist A 43 tokens
- Agent harness-reviewer A 52 tokens
- Agent stack-analyst A 46 tokens
- Agent architecture-mapper A 45 tokens
- Agent java-build-resolver C 53 tokens
- Agent kotlin-build-resolver C 43 tokens
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.
- 7d ago Changed ce77e956d36d
- 10d ago First seen · 41 lines scan A 2ecb348e70b3
aia-harness is a plugin published in the GitHub repository leandrosilvaferreira/claude-plugins-registry (7 stars, last pushed 7d ago), with no licence file. 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
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.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
container
Teaches Claude container's command surface and how it maps to Docker, Lima, Colima, and Podman on macOS.
knowledge-work-plugins marketplace
Plugin marketplace listing 99 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.