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 FortiumPartners/ensemblenpx agentmods add plugins/fortiumpartners/ensemble/developmentgit clone --depth 1 https://github.com/FortiumPartners/ensembleWrote 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/fortiumpartners/ensemble/development)<a href="https://agentmods.dev/plugins/fortiumpartners/ensemble/development"><img src="https://agentmods.dev/badge/plugins/fortiumpartners/ensemble/development.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
ensemble-development 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 yesterday.
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": "ensemble-development",
"version": "6.0.4",
"description": "Development agents for frontend/backend implementation",
"author": {
"name": "Fortium Partners",
"email": "[email protected]",
"url": "https://github.com/FortiumPartners"
},
"repository": "https://github.com/FortiumPartners/ensemble",
"license": "MIT",
"keywords": [
"development",
"implementation",
"coding",
"ensemble"
],
"commands": "./commands",
"skills": "./skills",
"agents": [
"./agents/api-documentation-specialist.md",
"./agents/beads-scaffold-specialist.md",
"./agents/backend-developer.md",
"./agents/documentation-specialist.md",
"./agents/frontend-developer.md",
"./agents/tech-lead-orchestrator.md"
]
}
What it installs
The manifest is a name and a version. 11 skills, 7 agents travel with it, and installing the plugin installs all of them — 539 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill developing-with-laravel A 39 tokens
- Skill developing-with-php A 37 tokens
- Skill developing-with-python A 40 tokens
- Skill developing-with-react A 38 tokens
- Skill using-celery A 45 tokens
- Skill using-prisma A 43 tokens
- Skill developing-with-typescript A 41 tokens
- Skill styling-with-tailwind A 44 tokens
- Skill complete-beads A 0 tokens
- Skill staleness-gate A 0 tokens
- Skill developing-with-flutter B 37 tokens
- Agent tech-lead-orchestrator A 36 tokens
- Agent documentation-specialist A 14 tokens
- Agent frontend-developer A 30 tokens
- Agent mobile-developer A 32 tokens
- Agent api-documentation-specialist A 14 tokens
- Agent backend-developer A 18 tokens
- Agent beads-scaffold-specialist A 31 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.
- yesterday First seen · 29 lines scan A 51decff9c4ed
ensemble-development is a plugin published in the GitHub repository FortiumPartners/ensemble (11 stars, last pushed 1mo 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 2026-09-03.
Other plugins, from other repositories
claude-prompts
Model Context Protocol (MCP) server for versioned prompt templates, multi-step workflow chains, and quality gates. Symbolic syntax: >>prompt --> >>chain @framework :: 'gate'.
sodam-graph
소담 7형제의 위치·진행 단계·의존 관계를 지도로 만들어 다음 할 일을 판정합니다. 형제 저장소는 100% 읽기 전용.
cc-blueprint-toolkit
Blueprint-driven Claude Code autopilot. Smart preparation over endless iterations - AI analyzes patterns, creates solid implementation plans, delivers working code in 15 minutes.
ticket-workflow
EARS-based ticket workflow: create issues, plan implementation, review commits, create PRs.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.