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/sgaunet/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/sgaunet/claude-plugins/software-engineering)<a href="https://agentmods.dev/plugins/sgaunet/claude-plugins/software-engineering"><img src="https://agentmods.dev/badge/plugins/sgaunet/claude-plugins/software-engineering/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/sgaunet/claude-plugins/software-engineering"><img src="https://agentmods.dev/badge/plugins/sgaunet/claude-plugins/software-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
software-engineering 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 22d 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": "software-engineering",
"version": "0.23.0",
"description": "Code review, debugging, documentation, license compliance (AGPL/MIT/Apache), payment integration (Stripe/PayPal), frontend development (HTMX/Alpine.js), architecture diagrams (d2 via diagram-architect + /gen-diagram), and terminal demo GIFs (VHS via /gen-vhs-demo). Skills: analyze-and-create-issue, analyze-pr, audit-codebase, auto-mr, check-claude-md-tokens, commit, create-issue, detect-repo-host, feature-flow, feature-flow-w, gen-claude, gen-diagram, gen-readme-diagram, gen-vhs-demo, run-lint, run-tests, upd-project-description, vscode-settings. MCP: context7",
"keywords": [
"code-review",
"security",
"documentation",
"payments",
"git",
"diagrams",
"d2",
"architecture-diagrams",
"vhs",
"demo-gif",
"vscode",
"editor-config"
],
"author": {
"name": "Sylvain",
"email": "[email protected]"
},
"license": "MIT",
"repository": "https://github.com/sgaunet/claude-plugins",
"homepage": "https://github.com/sgaunet/claude-plugins#readme"
}
What it installs
The manifest is a name and a version. 18 skills, 7 agents travel with it, and installing the plugin installs all of them — 705 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill gen-claude A 19 tokens
- Skill feature-flow-w A 30 tokens
- Skill gen-vhs-demo A 35 tokens
- Skill feature-flow A 24 tokens
- Skill detect-repo-host A 42 tokens
- Skill vscode-settings A 48 tokens
- Skill analyze-pr A 23 tokens
- Skill audit-codebase A 14 tokens
- Skill check-claude-md-tokens A 25 tokens
- Skill auto-mr A 39 tokens
- Skill commit A 10 tokens
- Skill create-issue A 17 tokens
- Skill analyze-and-create-issue A 23 tokens
- Skill run-tests A 35 tokens
- Skill run-lint A 41 tokens
- Skill upd-project-description B 22 tokens
- Skill gen-readme-diagram C 22 tokens
- Skill gen-diagram C 39 tokens
- Agent diagram-architect A 39 tokens
- Agent security-auditor A 21 tokens
- Agent code-review-enforcer A 37 tokens
- Agent debugger A 23 tokens
- Agent docs-architect A 20 tokens
- Agent html-first-frontend A 35 tokens
- Agent payment-integrator A 22 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.
- 22d ago Changed · +2 lines ba4cb1648149
- 1mo ago First seen · 25 lines scan A 4c344692a14b
software-engineering is a plugin published in the GitHub repository sgaunet/claude-plugins (16 stars, last pushed 8d ago), 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
pm-toolkit
PM utility skills: resume review, NDA drafting, privacy policy generation, and grammar/flow checking. Essential tools for product managers beyond core product work.
codebase-tools
Isolated codebase research, quality hardening, and build error resolution via skills and agents.
android-analysis
Android APK, AAR, and JAR decompilation and inspection toolkit for analyzing compiled binaries, unpacking libraries, and understanding obfuscated code.
ast-grep
Structural code search using AST patterns. Translates natural language queries into ast-grep rules for precise code matching beyond text search.
green-keeper
Keeps your tests and types green while you code — fixes red with minimal changes, maintains behavioral tests, and won't let you walk away from red. No fake-green.
money-map
Understand your money: hand it any bank or card CSV export and it categorizes, summarizes cash flow, and flags anomalies — locally, never linked to your accounts.