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/andisab/swe-marketplaceWrote 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/andisab/swe-marketplace/dev)<a href="https://agentmods.dev/plugins/andisab/swe-marketplace/dev"><img src="https://agentmods.dev/badge/plugins/andisab/swe-marketplace/dev/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/andisab/swe-marketplace/dev"><img src="https://agentmods.dev/badge/plugins/andisab/swe-marketplace/dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dev 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": "dev",
"description": "Language-specific development experts covering 13 programming languages including Python, TypeScript, JavaScript, Go, Rust, C++, and more. Includes refactoring specialist.",
"version": "1.0.0",
"author": {
"name": "Andis A. Blukis",
"email": "[email protected]",
"url": "https://github.com/andisab"
},
"homepage": "https://github.com/andisab/swe-marketplace",
"repository": "https://github.com/andisab/swe-marketplace",
"license": "MIT",
"keywords": [
"programming-languages",
"development",
"python",
"typescript",
"javascript",
"go",
"rust",
"cpp",
"refactoring"
],
"agents": [
"./agents/dev-cpp-expert.md",
"./agents/dev-fastapi-architect.md",
"./agents/dev-go-expert.md",
"./agents/dev-javascript-expert.md",
"./agents/dev-kotlin-expert.md",
"./agents/dev-lua-expert.md",
"./agents/dev-nodejs-expert.md",
"./agents/dev-perl-expert.md",
"./agents/dev-php-expert.md",
"./agents/dev-python-expert.md",
"./agents/dev-refactor-agent.md",
"./agents/dev-rust-expert.md",
"./agents/dev-typescript-expert.md"
]
}
What it installs
The manifest is a name and a version. 13 agents travel with it, and installing the plugin installs all of them — 1,846 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Agent nodejs-expert A 391 tokens
- Agent python-expert A 446 tokens
- Agent typescript-expert A 408 tokens
- Agent fastapi-architect A 43 tokens
- Agent go-expert A 18 tokens
- Agent cpp-expert A 18 tokens
- Agent kotlin-expert A 28 tokens
- Agent perl-expert A 40 tokens
- Agent javascript-expert A 47 tokens
- Agent lua-expert A 40 tokens
- Agent refactor-agent A 300 tokens
- Agent php-expert A 21 tokens
- Agent rust-expert B 46 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.
- 1mo ago First seen · 40 lines scan A 68c153f77f4a
dev is a plugin published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed today), 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…
commander
Guided AI PM for Claude Code, running on The Fable Method — 12 enforceable gates so any model produces Fable-shaped results. 84 plugin skills (click-first /ccc- workflows, incl. /ccc-codex for the Codex CLI), 22 specialist sub-agents (architect, reviewer, debugger, designer, security-auditor…), 30 lifecycle hooks × 51.
unity-dev
Unity C# development workflow with architecture design, coding guidelines, testing patterns, and specialized review agents.
drogon
Drogon C++ backend rules & skills: correct async code, avoiding callback / event-loop pitfalls. Works with Claude Code, ZCode, Codex, Cursor, VS Code (Copilot), Gemini CLI and any AGENTS.md-compatible agent.
keep-alive
Prevents your machine from sleeping during Claude Code sessions (mirrors GitHub Copilot CLI /keep-alive).
matilha
You lead. Agents hunt. A cognitive + methodological harness for building complex AI-assisted projects — 11 phase-gated core skills, composition layer with plugin-namespace detection, SessionStart hook for cross-workspace activation, and 7 companion packs shipping 128 skills across UX, growth, agent architecture…