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.
/plugin marketplace add FlorianBruniaux/claude-code-pluginsnpx agentmods add plugins/florianbruniaux/claude-code-plugins/marketplacegit clone --depth 1 https://github.com/FlorianBruniaux/claude-code-pluginsGrade A, and why
florian-claude-tools 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "florian-claude-tools",
"owner": { "name": "Florian Bruniaux" },
"metadata": {
"description": "Production-ready Claude Code plugins from the Ultimate Guide",
"version": "2.1.0"
},
"plugins": [
{
"name": "session-summary",
"source": "./plugins/session-summary",
"description": "Session analytics dashboard — 15 configurable sections displayed at session end (models, cost, cache, tools, files, git diff, RTK savings...)",
"author": { "name": "Florian Bruniaux" },
"keywords": ["hooks", "analytics", "session", "cost-tracking", "dashboard"],
"category": "productivity",
"license": "MIT"
},
{
"name": "security-suite",
"source": "./plugins/security-suite",
"description": "Security auditing pipeline — OWASP checks, vulnerability scanning, threat detection, cyber-defense multi-agent pipeline, and 13 protective hooks",
"author": { "name": "Florian Bruniaux" },
"keywords": ["security", "owasp", "audit", "threat", "vulnerability", "hooks"],
"category": "security",
"license": "MIT"
},
{
"name": "devops-pipeline",
"source": "./plugins/devops-pipeline",
"description": "CI/CD automation — git worktrees, deploy pipeline, canary monitoring, auto-format/test hooks, and GitHub Actions templates",
"author": { "name": "Florian Bruniaux" },
"keywords": ["ci", "cd", "git", "deployment", "hooks", "github-actions"],
"category": "devops",
"license": "MIT"
},
{
"name": "release-automation",
"source": "./plugins/release-automation",
"description": "Release workflow — generate changelogs, release notes (3 formats), and social content (LinkedIn/Twitter/Slack/Newsletter) from git commits",
"author": { "name": "Florian Bruniaux" },
"keywords": ["release", "changelog", "release-notes", "social", "versioning"],
"category": "productivity",
"license": "MIT"
},
{
"name": "cWhat 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.
- 2d ago First seen · 83 lines scan A a5e7de7d06ca
florian-claude-tools is a plugin published in the GitHub repository FlorianBruniaux/claude-code-plugins (40 stars, last pushed 2mo 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
badi
Workflow management for Claude Code, Cursor, Gemini, Windsurf, AGENTS.md — 30 AI agents, 86 commands, 14 hooks, 63 opt-in skill categories. Built for Anthropic Claude Opus 4.7 and Sonnet 4.6.
badi-marketplace
Plugin marketplace listing 1 plugin: badi.
core
Workframe core plugin: 4 baseline agents (PM / Dev / QA / Prompt-Eng), 36 skills (13 domain + 8 system/maintenance + 8 docs/publishing + 7 modules-system), an 11-stage hook pipeline, 4 auto-loaded rules, and the modules/ documentation system that keeps requirements and code in sync.
harness-claude
A lean, full-SDLC Claude Code harness — Plan → Implement → Verify → Maintain — with subagent orchestration, memory persistence, and an evolution path toward eval loops, retrieval, and multi-agent systems.
agents-atlas
Plugin marketplace listing 1 plugin: agents-atlas.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.