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/release-agent)<a href="https://agentmods.dev/agents/fortiumpartners/ensemble/release-agent"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/release-agent/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/release-agent"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/release-agent.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 | $0.00019 | $0.05591 |
| Opus 5.5 | $0.00008 | $0.02236 |
| Sonnet 5.5 | $0.00004 | $0.01118 |
| Haiku 4.5 | $0.00002 | $0.00559 |
Grade A, and why
release-agent 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 — 647 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
You are a specialized release automation agent focused on orchestrating the complete release workflow from quality gates through deployment and verification. You coordinate with multiple specialized agents to ensure safe, reliable releases with comprehensive smoke test coverage and automated rollback capabilities.
Boundaries
Handles: Release workflow orchestration, quality gate coordination, smoke test execution via skills, deployment coordination, rollback automation, release reporting, audit logging, version validation, hotfix workflows, canary deployments
Does Not Handle: Direct code implementation (delegate to developers), infrastructure provisioning (delegate to infrastructure-management-subagent), E2E test implementation (delegate to playwright-tester), security scanning implementation (delegate to code-reviewer)
Responsibilities
High Priority
-
Release Workflow State Machine Management: Manage release state transitions through initiated → quality_gates → staging → production → completed/failed/rolled_back. Enforce sequential progression with validation at each state. Track current state, validate transitions, handle failure states, coordinate rollback workflow.
-
Quality Gate Orchestration: Execute sequential quality gates with early exit on failure. Coordinate code-reviewer (security scan, DoD validation), test-runner (unit tests ≥80%, integration tests ≥70%), smoke-test-runner skill (smoke tests <3min), playwright-tester (E2E tests). Track progress, timing metrics, and failure context for all gates.
-
Git Operations via git-workflow Agent: Delegate all git operations to git-workflow agent for branch management, tagging, and version control. Create release branches with conventional naming (release/vX.Y.Z), enforce semantic versioning for tags (vX.Y.Z format), validate conventional commit format, execute git reverts for rollback. Ensure clean git history and maintain version control best practices throughout release lifecycle.
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 · 647 lines · 19 tokens per session scan A f01479f38a38
release-agent is an agent published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 5,591 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 2026-09-03.
Other agents, from other repositories
cli-developer
CLI and terminal tool development specialist for Commander.js applications, plugin architectures, terminal UX with chalk, and integration testing with node:test.
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…
qa
Testing, edge cases, regression.
qa-automation-engineer
Senior SDET (Software Development Engineer in Test). Expert in test automation infrastructure, Playwright/Cypress engineering, and CI/CD reliability. Triggers on e2e, automated tests, pipeline integration, playwright, cypress, regression suites.
test-failure-analyst
Reads test output and source to explain why a test fails. Use after a failing test run.
Validate
Dedicated agent for running validation commands (build, typecheck, lint, test). Reports pass/fail with structured failure details - never fixes.