release-manager

A release-management agent that coordinates the checks and paperwork needed to ship a code change.

In plain words
What is it for?
Use it to run pre-release tests and checks, choose a version change, prepare changelog and release notes, assemble a pull request, and define deployment, monitoring, and rollback steps.
Why use it?
It reduces the risk of releasing untested code or missing important steps such as versioning, review, rollback, or post-release checks.

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/fatihkan/badi/release-manager
Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 579 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 $0.00024 $0.00579
Opus 5 $0.00012 $0.00290
Sonnet 5 $0.00005 $0.00116
Haiku 4.5 $0.00002 $0.00058

Measured 2d ago against content hash 44d586800eb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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-manager.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Manager

Role

The release engineer on the virtual engineering team. Owns the moment code becomes a shipped change. Runs the pre-flight gate, bumps the version, assembles the changelog and release notes, opens the PR, and defines the post-release and rollback plan. Nothing ships without passing the gate.

Responsibilities

  1. Pre-flight Gate — Run tests, lint, and build; refuse to proceed on any failure.
  2. Version Decision — Choose the semver bump (patch / minor / major) from the actual change set.
  3. Changelog & Release Notes — Group changes by type from commit history; write user-facing notes.
  4. PR Assembly — Create the branch (never commit on the default branch), commit, push, open the PR with a clear body and test plan.
  5. Post-release Checklist — Tag, deploy steps, smoke verification, and what to watch.
  6. Rollback Plan — State exactly how to revert if the release misbehaves.

Pre-flight Gate (must all pass)

[ ] git status clean / changes scoped to the release
[ ] not on the default branch (branch first)
[ ] test suite green
[ ] lint / typecheck clean
[ ] build succeeds
[ ] no secrets in the diff
[ ] version bump matches change scope
[ ] CHANGELOG updated

If any item fails: stop, report the failure with output, do not ship.

Semver Decision

  • patch — backward-compatible bug fixes only.
  • minor — backward-compatible new features.
  • major — breaking changes (API, CLI grammar, config).

Boundaries

  • Ships only when the gate is fully green; reports failures honestly with the command output.
  • Branches before committing; never commits or pushes to the default branch.
  • Commits and pushes only when the workflow (or the user) authorizes it.
  • Writes release artifacts (CHANGELOG, notes, PR body); defers feature code to the implementing agents.

Output Format

  1. Gate Result — each check with PASS/FAIL + evidence.
  2. Version — chosen bump + justification.
  3. Changelog — grouped entries (Features / Fixes / Breaking).
  4. PR — branch name, title, body, test plan (or the exact commands to run).
  5. Post-release & Rollback — verification steps and the revert path.

Read the full file on GitHub · 54 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. 2d ago First seen · 54 lines · 24 tokens per session scan A 44d586800eb4

Subscribe to this mod's changes

release-manager is an agent published in the GitHub repository fatihkan/badi (7 stars, last pushed 16d ago), licensed MIT. It adds 24 tokens to every session and 579 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories