decompose: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from sciyoshi/decompose. It costs 75 tokens per session (1,722 once invoked), scanned A, original, Apache-2.0.

A release workflow for the decompose Rust project. It updates the package version, creates a GitHub release, and relies on the release tag to start publishing and binary-upload automation.

In plain words
What is it for?
Use it to cut a specified stable or pre-release version, generate notes from commits, tag it, and publish the project through its existing automation.
Why use it?
It checks that the working tree, branch, remote history, and CI are ready before creating a release.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is sciyoshi/decompose's own configuration. It tells Claude Code how to work on decompose itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything decompose configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sciyoshi/decompose. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sciyoshi/decompose/main/.claude/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sciyoshi/decompose

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/sciyoshi/decompose/release/github.svg)](https://agentmods.dev/skills/sciyoshi/decompose/release)
Your own site
<a href="https://agentmods.dev/skills/sciyoshi/decompose/release"><img src="https://agentmods.dev/badge/skills/sciyoshi/decompose/release/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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sciyoshi/decompose/release"><img src="https://agentmods.dev/badge/skills/sciyoshi/decompose/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,722 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 $0.00075 $0.01722
Opus 5.5 $0.00030 $0.00689
Sonnet 5.5 $0.00015 $0.00344
Haiku 4.5 $0.00007 $0.00172

Measured yesterday against content hash 8ca0342bba31, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release 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.

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/skills/release/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are helping the user cut a new release of decompose.

Version format

The crate uses SemVer. Cargo rejects PEP 440 syntax (0.1.0a1 is not valid). Use:

  • Stable: 0.1.0, 0.2.0, 1.0.0
  • Pre-release: 0.1.0-alpha.1, 0.1.0-beta.1, 0.1.0-rc.1

The git tag is always v + the version, e.g. v0.1.0-alpha.1.

Args

The user invokes this skill with the target version as the argument, e.g. /release 0.1.0-alpha.1. If no argument is given, ask the user which version to cut before doing anything else. Validate the version is SemVer.

Steps

Execute these in order. Stop and ask the user if anything is surprising.

1. Preflight

Run these checks in parallel. Abort if any fails.

git status --porcelain              # must be empty (clean tree)
git rev-parse --abbrev-ref HEAD     # must be "main"
git fetch origin main               # sync refs
git rev-list --count HEAD..origin/main  # must be 0 (up to date with remote)
git rev-list --count origin/main..HEAD  # must be 0 (no unpushed commits)

Check CI is green on the current HEAD:

gh run list --branch main --limit 1 --json conclusion,status,headSha

The most recent run on main must have conclusion == "success" and headSha matching current HEAD. If it's still running (status == "in_progress"), ask the user whether to wait or proceed. If it's failing, abort.

2. Determine version and previous tag

  • Current version: read the version = "..." line from Cargo.toml.
  • Target version: from the skill args (validated above).
  • Previous tag: git describe --tags --abbrev=0 2>/dev/null -- may be empty for the first release.

Confirm to the user: "Cutting release: current={current}, target={target}, previous tag={tag or none}. Proceed?" Do not take any irreversible action until they confirm.

3. Bump Cargo.toml

Use Edit to change the version = "..." line in Cargo.toml to the target version. Then run cargo build --locked to refresh Cargo.lock. (If --locked fails because the lockfile needs updating, run cargo build without --locked once, then re-run with --locked to verify.)

Read the full file on GitHub · 147 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 · 147 lines · 75 tokens per session scan A 8ca0342bba31

Subscribe to this mod's changes

release is a skill published in the GitHub repository sciyoshi/decompose (7 stars, last pushed 12d ago), licensed Apache-2.0. It adds 75 tokens to every session and 1,722 once invoked, about $0.0003 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 2026-11-07.

Related

release compared with skills from other repositories

release next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
releasesciyoshi/decomposeSkill712d agoApache-2.0A75Claude Code
release-announcementpaperclipai/paperclipSkill112ktodayMITA42Claude Code, Codex
releasethedotmack/claude-memSkill115ktodayApache-2.0A13Claude Code
release-notesphuryn/pm-skillsSkill28k9d agoMITA57Claude Code
multi-agent-release-managerchromium/chromiumSkill25ktodayBSD-3-ClauseA27Claude Code, Codex
pack-submitaeonfun/aeonSkill7892d agoMITA27Claude Code, Codex
updater_guidesiddsachar/row-botSkill1.7kyesterdayApache-2.0A22Claude Code, Codex