release-please-setup

release-please-setup is a skill for Claude Code, Codex from joaquimscosta/arkhe-claude-plugins. It costs 154 tokens per session (1,133 once invoked), scanned A, original, MIT.

A setup tool that adds release-please to a repository. Release-please is a service and workflow that prepares version changes and release notes from repository history, including projects with several packages.

In plain words
What is it for?
Use it to scan packages, create release-please configuration and manifests, connect the release workflow, and optionally add deployment or publishing templates.
Why use it?
It removes the manual work of creating release configuration and GitHub Actions wiring. It can start a new setup or migrate repositories that already use their own version tags.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to scan packages, create release-please configuration and manifests, connect the release workflow, and optionally add deployment or publishing templates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joaquimscosta/arkhe-claude-plugins/release-please-setup
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.

Any agent
npx skills add joaquimscosta/arkhe-claude-plugins --skill release-please-setup
Clone the repo
git clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-plugins

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-please-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/release-please-setup/github.svg)](https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/release-please-setup)
Your own site
<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/release-please-setup"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/release-please-setup/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-please-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/release-please-setup"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/release-please-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,133 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 $0.00154 $0.01133
Opus 5.5 $0.00062 $0.00453
Sonnet 5.5 $0.00031 $0.00227
Haiku 4.5 $0.00015 $0.00113

Measured yesterday against content hash d7a5fc73a400, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release-please-setup 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 yesterday.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/discover_packages.py, scripts/generate_config.py, scripts/release_please_setup.py, …), 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.

plugins/git/skills/release-please-setup/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release-Please Setup

Scaffold or migrate a repository onto release-please. The skill generates release-please-config.json and .release-please-manifest.json from a monorepo package scan, then guides you through wiring the release-please.yml workflow and optionally an opt-in deploy/publish template from the six provided in templates/.

Two modes

Mode When to use
Greenfield (default) New repo with no prior tags. All packages start at 0.0.0 (or --initial <ver>).
--migrate Existing repo with hand-maintained <component>-v* tags. Manifest is seeded from detected file versions; existing deploy workflows keep working unchanged.

Quick start

# SCRIPTS = absolute path to this skill's scripts/ directory
# Always dry-run first — no files are written
python3 SCRIPTS/release_please_setup.py --root . --dry-run            # greenfield
python3 SCRIPTS/release_please_setup.py --root . --migrate --dry-run  # migrate
python3 SCRIPTS/release_please_setup.py --root . --migrate            # write files

CLI flags: --root (repo root), --globs (comma-separated package globs; default packages/*,backend/*,frontend/*), --migrate (migration mode), --single (force single-package config), --initial (starting version; default 0.0.0), --dry-run (print output, no writes), --out-dir (write location; default --root).

Then:

  1. Copy templates/release-please.yml into .github/workflows/.
  2. Set the REPO_TOKEN secret — see CONTRACT.md. ⚠️ GITHUB_TOKEN-created tags do not trigger other workflows; a PAT is required for deploy templates to fire.
  3. Pick a deploy template (optional).

Deploy template menu

Template Use for
deploy-fly.yml Fly.io app deploy
publish-npm-oidc.yml npm Trusted Publishing (OIDC, no token)
release-asset.yml Build artifact → GitHub Release (e.g. .vsix, .zip)
deploy-docker-matrix.yml Docker image → Amazon ECR / any registry
deploy-frontend-host.yml Gated frontend deploy (Amplify, Vercel, Netlify)
deploy-generic.yml Any build + deploy command
None Release-please only — add deploy later

Read the full file on GitHub · 74 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. yesterday First seen · 74 lines · 154 tokens per session scan A d7a5fc73a400

Subscribe to this mod's changes

release-please-setup is a skill published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed yesterday), licensed MIT. It adds 154 tokens to every session and 1,133 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-16.