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/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/pi)<a href="https://agentmods.dev/plugins/fortiumpartners/ensemble/pi"><img src="https://agentmods.dev/badge/plugins/fortiumpartners/ensemble/pi/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/fortiumpartners/ensemble/pi"><img src="https://agentmods.dev/badge/plugins/fortiumpartners/ensemble/pi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ensemble-pi 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": "ensemble-pi",
"version": "1.0.0",
"description": "Pi runtime support — translates ensemble artifacts for Pi coding agent",
"author": {
"name": "Fortium Partners",
"email": "[email protected]"
},
"skills": "./skills"
}
What it installs
The manifest is a name and a version. 7 skills, 6 agents travel with it, and installing the plugin installs all of them — 852 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill ensemble-full-create-trd A 84 tokens
- Skill ensemble-full-create-trd-foreman A 94 tokens
- Skill ensemble-full-implement-trd A 65 tokens
- Skill ensemble-full-refine-trd A 45 tokens
- Skill ensemble-full-implement-trd-beads A 304 tokens
- Skill ensemble-full-create-prd A 77 tokens
- Skill ensemble-full-refine-prd A 72 tokens
- Agent deep-debugger A 24 tokens
- Agent product-management-orchestrator A 28 tokens
- Agent test-runner A 16 tokens
- Agent code-reviewer A 17 tokens
- Agent qa-orchestrator A 12 tokens
- Agent test-reader-agent A 14 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 · 11 lines scan A 1d21dcb3940b
ensemble-pi is a plugin published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed 2d 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
vlt
Agent skills for the vlt CLI and vlt.io registries.
tierward marketplace
Tierward governance skills for Claude Code: commit enforcement, audits, code quality.
cli-code-skills
Production-ready Claude Code skills — audit code quality, forge design docs, generate documentation, automate infrastructure.
guild
Spec-first workflows and specialized agent roles for Claude Code. Design docs before code, structured deliberation, automatic previous-session recap on startup.
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.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.