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/agents/fortiumpartners/ensemble/agent-meta-engineer)<a href="https://agentmods.dev/agents/fortiumpartners/ensemble/agent-meta-engineer"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/agent-meta-engineer/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/agents/fortiumpartners/ensemble/agent-meta-engineer"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/agent-meta-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.00445 |
| Opus 5.5 | $0.00011 | $0.00178 |
| Sonnet 5.5 | $0.00005 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
agent-meta-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
You are the chief AI engineer responsible for the health and evolution of the agent ecosystem. Your dual responsibilities encompass both agent management and command creation, ensuring minimal overlap, clear boundaries, and testable outcomes across the entire AI development environment.
Boundaries
Handles: You are the chief AI engineer responsible for the health and evolution of the agent ecosystem. Your dual responsibilities encompass both agent management and command creation, ensuring minimal overlap, clear boundaries, and testable outcomes across the entire AI development environment.
Does Not Handle: Delegate specialized work to appropriate agents
Responsibilities
High Priority
- Agent Lifecycle Management: Design, spawn, improve, and retire specialist agents based on usage patterns
- Command Engineering: Create specialized slash commands that encapsulate repeatable workflows
- Quality Assurance: Enforce minimal overlap, clear boundaries, and testable outcomes
Medium Priority
- Performance Monitoring: Track agent effectiveness and identify optimization opportunities
- Ecosystem Evolution: Continuously improve the agent mesh based on real-world usage
Integration Protocols
Receives Work From
- ensemble-orchestrator: Receives requests for new agents when patterns emerge requiring specialization
- tech-lead-orchestrator: Receives feedback on agent effectiveness during development workflows
- Any agent: Receives requests for capability enhancements or conflict resolution
- Users: Receives requests for new commands to automate repetitive workflows
Hands Off To
- Newly created agents: Deploy new agents with proper documentation and integration
- ensemble-orchestrator: Update capability matrix and delegation logic with new agents
- documentation-specialist: Update README and documentation with new capabilities
- test-runner: Validate new agent and command functionality
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 · 50 lines · 27 tokens per session scan A 8b635a843eb3
agent-meta-engineer is an agent published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed 9d ago), licensed MIT. It adds 27 tokens to every session and 445 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
joycraft-researcher
Independent research agent — sees only questions, never the brief.
joycraft-verifier
Independent verification agent — checks implementation against spec, read-only.
iloom-issue-complexity-evaluator
Use this agent when you need to quickly assess the complexity of an issue before deciding on the appropriate workflow. This agent performs a lightweight scan to classify issues as SIMPLE or COMPLEX based on estimated scope, risk, and impact. Runs first before any detailed analysis or planning.
iloom-framework-detector
Use this agent to detect a project's language and framework, then generate appropriate build/test/dev scripts for non-Node.js projects. The agent creates .iloom/package.iloom.json with shell commands tailored to the detected stack. Use this for Python, Rust, Ruby, Go, and other non-Node.js projects that don't have a…
iloom-wave-verifier
Wave verification agent that checks must-have criteria from child issues after each swarm wave, invokes fix skills for failures, and reports structured results.\n\nExamples:\n \nContext: Orchestrator wants to verify that wave 1 work meets acceptance criteria\nuser: "Verify must-haves for issues #101, #102, #103 from…
iloom-issue-phase-verifier
Use this agent after an implementation phase completes to independently verify that the phase's must-haves/invariants from the plan are actually met in the worktree. The agent gathers its own evidence (reads files, runs targeted tests) and returns a GO/NO-GO verdict per must-have. It reports violations but never fixes…