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/bug-ops/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/bug-ops/claude-plugins/dev-agents)<a href="https://agentmods.dev/plugins/bug-ops/claude-plugins/dev-agents"><img src="https://agentmods.dev/badge/plugins/bug-ops/claude-plugins/dev-agents/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/bug-ops/claude-plugins/dev-agents"><img src="https://agentmods.dev/badge/plugins/bug-ops/claude-plugins/dev-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dev-agents 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. 20 skills, 15 agents travel with it, and installing the plugin installs all of them — 2,623 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill team-develop A 85 tokens
- Skill arch-inspect A 99 tokens
- Skill rust-modern-apis A 60 tokens
- Skill sdd A 33 tokens
- Skill continuous-improvement A 99 tokens
- Skill team-debug A 94 tokens
- Skill live-testing A 64 tokens
- Skill obsidian-zettelkasten A 46 tokens
- Skill readme-generator A 50 tokens
- Skill release A 54 tokens
- Skill fast-yaml A 48 tokens
- Skill mdbook-tech-writer A 43 tokens
- Skill research-protocol A 46 tokens
- Skill triage-and-solve A 43 tokens
- Skill init-project A 61 tokens
- Skill stack A 75 tokens
- Skill agent-handoff A 37 tokens
- Skill solve-issue A 32 tokens
- Skill security-audit B 125 tokens
- Skill spec-from-stream B 109 tokens
- Agent critic A 125 tokens
- Agent testing-engineer A 131 tokens
- Agent architect A 69 tokens
- Agent code-reviewer A 60 tokens
- Agent developer A 57 tokens
- Agent tech-writer A 79 tokens
- Agent cicd-devops A 73 tokens
- Agent debugger A 78 tokens
- Agent live-tester A 71 tokens
- Agent performance-engineer A 71 tokens
- Agent researcher A 68 tokens
- Agent security-maintenance A 64 tokens
- Agent security-analyst A 125 tokens
- Agent arch-analyst A 92 tokens
- Agent sdd B 157 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.
- 7d ago First seen · 52 lines scan A 963aa3becc33
dev-agents is a plugin published in the GitHub repository bug-ops/claude-plugins (11 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 2026-10-09.
Other plugins, from other repositories
bevy-plugin
Bevy game engine development - ECS, rendering, game architecture.
development
All development skills for systemprompt.io: Rust backend (extensions, CLI binaries, MCP servers), web features, canonical per-language coding standards (Rust, JavaScript, CSS) with mechanical forbidden-construct tables, HTML/asset workflow, print factsheet design, distribution-channel validation, and UX/UI design…
rust-developer
Comprehensive Rust development assistance for building, testing, and deploying Rust applications with cargo, clippy, async patterns, and framework support.
rust
Rust development tools for Claude Code.
open-responses-agent-dev
Build autonomous agents in Rust, TypeScript, or Python using Open Responses API for seamless multi-provider support (OpenAI, Anthropic, HuggingFace, etc.).
nodejs-development
Node.js and TypeScript backend development with Express, NestJS patterns, performance optimization, and modern API development.