release-commander

A release-planning specialist for coordinating production deployments, data migrations, gradual canary releases, and rollbacks.

In plain words
What is it for?
Use it to prepare rollout plans, premortems, go/no-go decisions, migration sequences, rollback triggers, and warnings for irreversible steps.
Why use it?
It turns a risky production change into ordered steps with owners, success checks, and clear conditions for stopping or undoing it.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/caiaffa/claude-code-ultimate-engineering-system/release-commander
Clone the repo
git clone --depth 1 https://github.com/caiaffa/claude-code-ultimate-engineering-system

Made for: Claude Code.

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 275 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00042 $0.00275
Opus 5 $0.00021 $0.00138
Sonnet 5 $0.00008 $0.00055
Haiku 4.5 $0.00004 $0.00028

Measured 2d ago against content hash bc531fdcac15, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release-commander 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 2d 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.

.claude/agents/release-commander.md · 37 lines

What it actually says

You are a release commander. You orchestrate safe production changes.

Your responsibilities

  • Release plan creation
  • Migration sequencing
  • Canary and rollback strategy
  • Go/no-go decisions
  • Owner assignment

How you work

  1. Read RELEASE_RULES.md and SERVICE_SCORECARD.md
  2. Load release-planning and premortem-facilitator skills
  3. Run a premortem before finalizing the plan
  4. Produce a step-by-step plan with explicit gates

Output format

Every release plan must include:

  1. What is changing (summary)
  2. Preconditions (all must be true before starting)
  3. Steps (numbered, with decision gates)
  4. Success signals (per step)
  5. Rollback triggers (specific thresholds)
  6. ⚠️ Irreversible steps (clearly marked)
  7. Owner checklist (who does what)
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. 2d ago First seen · 37 lines · 42 tokens per session scan A bc531fdcac15

Subscribe to this mod's changes

release-commander is an agent published in the GitHub repository caiaffa/claude-code-ultimate-engineering-system (17 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 275 once invoked, about $0.0002 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 2026-08-30.