release-manager

release-manager is a skill for Claude Code, Codex from flurdy/agent-skills. It costs 93 tokens per session (9,988 once invoked), scanned A, original, MIT.

An interactive release dashboard for deciding which services are ready to deploy, meaning send new code to a running environment. It checks release gates, handles failed CI, follows deployment order, watches rollouts, and asks before pushing.

In plain words
What is it for?
Use it to review ready services, respond to failed continuous-integration checks, deploy in the required order, monitor rollouts, and coordinate configuration-related restarts.
Why use it?
It gathers release information and guides decisions in one place while keeping deployments under explicit human control.

Skill for Claude CodeCodex

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 skills/flurdy/agent-skills/release-manager
Any agent
npx skills add flurdy/agent-skills --skill release-manager
Clone the repo
git clone --depth 1 https://github.com/flurdy/agent-skills

Made for: Claude Code, Codex.

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/skills/flurdy/agent-skills/release-manager.svg)](https://agentmods.dev/skills/flurdy/agent-skills/release-manager)
Your own site
<a href="https://agentmods.dev/skills/flurdy/agent-skills/release-manager"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/release-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,988 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 5.1 $0.00093 $0.09988
Opus 5 $0.00046 $0.04994
Sonnet 5 $0.00019 $0.01998
Haiku 4.5 $0.00009 $0.00999

Measured 5d ago against content hash 94e24eaf1b16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (tests/test_release_ci.py, tests/test_release_order.py, tests/test-skill-contract.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/release-manager/SKILL.md · 556 lines

How it starts

The opening of the file, as written. The whole thing — 556 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Manager

The interactive gatekeeper. One invocation = one tick: gather release state, evaluate gates, take care of CI failures, and prompt you for a decision on anything that's ready to ship. Designed to run on a loop in a dedicated tab via /watch-release.

It is advisory and explicit: nothing gets pushed unless you choose push at the prompt (honors the project rule "never auto-push, always ask"). The one thing it does autonomously is file a bead when CI is red — deduplicated, so it never double-files.

When to Use

  • Driven by /watch-release (adaptive cadence — step 8b's next-tick: line paces the loop) in a kitty tab during parallel work.
  • Ad-hoc, when you want to be walked through what's ready to push/release right now.

For a passive look with no prompts, use /release-status. For a deep gate on a single service, use /ready-to-release <service>.

Usage

/release-manager              # one tick across all services
/release-manager dispatch     # one tick scoped to a service

Setup

This skill ships two project-facing authorities:

  • release-order resolves the effective deploy-order graph for /release-manager, /release-status, and /ready-to-release.
  • release-ci resolves read-only CI evidence for the exact upstream revision of each requested service. It has built-in adapters for CircleCI, GitHub Actions, Google Cloud Build, and none.

On first run, ensure both project commands resolve to the installed skill:

ln -sfn "$SKILLS_DIR/release-manager/scripts/release-order" ./scripts/release-order
ln -sfn "$SKILLS_DIR/release-manager/scripts/release-ci" ./scripts/release-ci
chmod +x ./scripts/release-order ./scripts/release-ci

Where $SKILLS_DIR resolves to the installed shared skill root. Both authorities find a multi-repo root from RELEASE_PROJECT_ROOT, .mgit.conf, a release manifest, or a Git root.

release-order selects the pact provider when live pact edges or a generated pact block exist, uses order.manual for a plain manifest-declared graph, and returns an empty graph when neither source exists. An accepted generated block remains effective until you explicitly reconcile provider drift. Manual edges and suppressions use the same flow-list map shape.

Read the full file on GitHub · 556 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 556 lines · 93 tokens per session scan A 94e24eaf1b16

Subscribe to this mod's changes

release-manager is a skill published in the GitHub repository flurdy/agent-skills (8 stars, last pushed 7d ago), licensed MIT. It adds 93 tokens to every session and 9,988 once invoked, about $0.0005 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 skills, from other repositories

ship

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. (gstack).

garrytan/gstack · 35 tokens

github-release-management

Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.

ruvnet/RuView · 27 tokens

agent-github-modes

Agent skill for github-modes - invoke with $agent-github-modes.

ruvnet/ruflo · 21 tokens

tutti-app-release

Set up, review, run, or debug external repositories that publish a Tutti workspace app through the reusable Tutti App Release GitHub Actions workflow. Use for caller workflows, tutti.app.json manifests, @tutti-os/app-release-tools, S3/CloudFront release hosting, latest.json, versions.json, catalog.json, catalog-only…

tutti-os/tutti · 80 tokens

harness-release

Generic release automation for projects using Keep a Changelog + GitHub. Single confirmation gate then end-to-end automation: bump detection, CHANGELOG promotion, PR/main merge, tag, GitHub Release. Trigger: release, version bump, publish. Do NOT load for: implementation, review, planning, setup.

Chachamaru127/claude-code-harness · 66 tokens

publish

Publish the Octop Python package: cut a release branch from develop, bump version, update CHANGELOG, open a PR to main; after merge, Actions tag on main (PyPI / Docker Hub + GHCR) and sync main into develop. Use when the user asks to publish, release, bump version, cut a release, or run /publish.

TencentCloud/Octop · 74 tokens