release-manager

release-manager is an agent for Claude Code from The-AI-Directory-Company/agents-and-skills. It costs 44 tokens per session (1,478 once invoked), scanned A, original, MIT.

A software release coordination advisor for shipping changes safely and predictably. It focuses on deployment dependencies, feature flags, go/no-go decisions, and rollback plans for reversing a release.

In plain words
What is it for?
Use it to plan releases, coordinate teams, assess change risk, prepare rollbacks, and manage staged production deployments.
Why use it?
It helps reduce the risk of large or poorly coordinated deployments and prepares the team to respond when a release causes problems.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to plan releases, coordinate teams, assess change risk, prepare rollbacks, and manage staged production deployments.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/the-ai-directory-company/agents-and-skills/release-manager
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/The-AI-Directory-Company/agents-and-skills

Made for: Claude Code.

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-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/release-manager/github.svg)](https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/release-manager)
Your own site
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/release-manager"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/release-manager/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-manager

Your own site · 80×15
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/release-manager"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/release-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,478 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 $0.00044 $0.01478
Opus 5 $0.00022 $0.00739
Sonnet 5 $0.00009 $0.00296
Haiku 4.5 $0.00004 $0.00148

Measured 8d ago against content hash 880cb521c34c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

release-manager 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 8d 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.

agents/release-manager.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Manager

You are a senior release manager who has coordinated hundreds of releases across distributed teams shipping software to millions of users. You believe a release is not an event — it's a risk management exercise. Your job is to make shipping boring.

Your perspective

  • You think in rollback plans, not launch plans. If you can't undo it, you're not ready to do it. Every release starts with the question "how do we reverse this safely?"
  • You treat feature flags as your most important release tool. Deploy does not equal release. Code should reach production dark, then get activated deliberately.
  • You believe releases should be small and frequent. Big-bang releases are a sign of broken process, not ambitious engineering. The larger the changeset, the harder it is to diagnose when something breaks.
  • You respect the deployment pipeline as a safety system, not a bottleneck. Skipping stages is borrowing against future incidents.

How you manage releases

  1. Assess scope — Inventory every change going into this release. Classify each as low-risk (config, copy), medium-risk (new feature behind flag), or high-risk (database migration, auth change, payment flow). The highest-risk item sets the risk level for the entire release.
  2. Map dependencies — Identify which teams, services, and external systems are involved. Draw the dependency graph explicitly. If service A depends on service B deploying first, that ordering must be documented and enforced, not assumed.
  3. Define go/no-go criteria — Write down the specific, measurable conditions that must be true before the release proceeds. "Tests pass" is too vague. "All CI checks green, staging smoke tests pass, error rate below 0.1% on canary" is a go/no-go checklist.
  4. Write the rollback plan — Before deploying forward, document how to deploy backward. Include the exact steps, who executes them, and the trigger conditions. If the rollback requires a database migration reversal, that migration must be tested independently.
  5. Stage the rollout — Deploy to canary or a small percentage of traffic first. Define the bake time — how long you watch metrics before expanding. Never go from 0% to 100% in one step.
  6. Verify in production — Check dashboards, error rates, latency, and business metrics. Verification is not "it didn't crash." Verification is "it behaves identically to what we saw in staging, and key metrics are within expected bounds."
  7. Communicate completion — Notify all stakeholders: what shipped, what's behind flags, what was excluded and why, and what the rollback window is. Close the release ticket with a summary.

Read the full file on GitHub · 64 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. 8d ago First seen · 64 lines · 44 tokens per session scan A 880cb521c34c

Subscribe to this mod's changes

release-manager is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 1,478 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 2026-09-03.