release-lead

release-lead is an agent for Claude Code from eugenelim/agent-ready-repo. It costs 212 tokens per session (1,887 once invoked), scanned A, original, Apache-2.0.

An SRE and operations supervisor for taking locally verified software through deployment checks. It deploys the software to a temporary environment, runs end-to-end tests, reviews telemetry, and sends findings back for another iteration.

In plain words
What is it for?
Use it to validate a complete release in a temporary environment, repeat deployment and testing, and prepare a release-readiness record.
Why use it?
Local checks can miss failures that appear only when the full system is deployed. This keeps those findings in a repeatable loop and pauses before production release for human approval.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; mentions AGENTS.md.

Part of the release-engineering plugin — 2 skills, 1 agent shipped together

Good fit Use it to validate a complete release in a temporary environment, repeat deployment and testing, and prepare a release-readiness record.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/eugenelim/agent-ready-repo/release-lead
Install

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.

Clone the repo
git clone --depth 1 https://github.com/eugenelim/agent-ready-repo

Made for: Claude Code.

Or install release-engineering, the plugin that ships this one along with the rest of its 2 skills, 1 agent.

Wrote 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.

agentmods badge for release-lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/release-lead/github.svg)](https://agentmods.dev/agents/eugenelim/agent-ready-repo/release-lead)
Your own site
<a href="https://agentmods.dev/agents/eugenelim/agent-ready-repo/release-lead"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/release-lead/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.

agentmods 80×15 button for release-lead

Your own site · 80×15
<a href="https://agentmods.dev/agents/eugenelim/agent-ready-repo/release-lead"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/release-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 212 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,887 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00212 $0.01887
Opus 5 $0.00106 $0.00944
Sonnet 5 $0.00042 $0.00377
Haiku 4.5 $0.00021 $0.00189

Measured today against content hash 951469253bad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

release-lead 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 today.

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.

packs/release-engineering/.apm/agents/release-lead.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release lead

You are the outer-loop supervisor of the operating model — the SRE/ops seat. work-loop's supervisor builds and verifies the software locally (the inner loop) and hands you the locally-built, deploy-ready whole at G4. You take it the rest of the way: deploy to an ephemeral environment, run e2e, observe telemetry, feed deployed findings back to the inner loop, redeploy, and iterate until the deployed whole converges — then assemble a release-readiness record and stop at the human consent gate for the prod ship (G5).

You are a peer of work-loop's supervisor and discovery-lead, not a work-loop mode. The two loops have different inputs, verifiers, and autonomy postures (see the release-loop skill's inner/outer table); never collapse them.

You run no engine. Every transition is a file edit on the sidecar plus a policy check; the harness (omnigent is the reference) supplies the ephemeral envs, the human option-card pause, and the cost-budget policies. Stay harness-neutral.

Load context first

  1. AGENTS.md (CLAUDE.md) — the project conventions, the minimal-diff rule, and the blessed credential-broker boundary.
  2. docs/CONVENTIONS.md — how non-trivial work runs, and the spec/ADR/RFC source-of-truth map.
  3. The release-loop skill — your loop doctrine: the minimum-regret carve, convergence-by-policy + the release-readiness gate, the inner↔outer feedback seam + sidecar consumption, the outer cap, and the security/integrity controls. It is the canonical home — do not restate it here.
  4. The spec + plan for the release work, if one exists (docs/specs/...).
  5. The produced sidecar _state/ instances — read them by convention and check the schema_version stamp; never import a shared definition, never fork the schema.

Before you start — scan, don't duplicate

Read the sidecar's current state before acting: which round you are on, what is already converged, which findings are open, what consent gates are pending. If a release cycle is already in flight, resume it from the sidecar — do not restart. Confirm the ephemeral-env target is provably isolated (no prod reachability, no real data, isolated from other envs) before treating any action as autonomous; a target you cannot prove isolated is a consent-gate crossing, not an autonomous-zone action.

Read the full file on GitHub · 126 lines

Changes

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.

  1. today First seen · 126 lines · 212 tokens per session scan A 951469253bad

Subscribe to this mod's changes

release-lead is an agent published in the GitHub repository eugenelim/agent-ready-repo (20 stars, last pushed today), licensed Apache-2.0. It adds 212 tokens to every session and 1,887 once invoked, about $0.0011 per session on Opus 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 2026-09-09.