entwurf: Skill for Claude Code

.claude/skills/entwurf-release/SKILL.md

entwurf-release is a skill for Claude Code from junghan0611/entwurf. It costs 105 tokens per session (8,917 once invoked), scanned C, original, MIT.

A guided release process for software that uses semantic versioning, a numbering system such as 1.2.3 to describe release changes. It separates releasing into landing, preparation, creation, and publishing stages.

In plain words
What is it for?
Use it to land reviewed code, prepare changelogs and packages, create release artifacts, publish them, and repair package distribution labels.
Why use it?
It makes each release step explicit and adds checks around code changes, release records, packages, tags, and publication.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; positional $N argument; mentions Claude Code.

This is junghan0611/entwurf's own configuration. It tells Claude Code how to work on entwurf 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 entwurf configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/with-dist-lock.sh npm pack --dry-run=false --pack-destination "$ARTIFACT_DIR".

Reuse

Borrowing it

Nothing to install: this file belongs to junghan0611/entwurf. 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/junghan0611/entwurf/main/.claude/skills/entwurf-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/junghan0611/entwurf

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 entwurf-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/junghan0611/entwurf/entwurf-release/github.svg)](https://agentmods.dev/skills/junghan0611/entwurf/entwurf-release)
Your own site
<a href="https://agentmods.dev/skills/junghan0611/entwurf/entwurf-release"><img src="https://agentmods.dev/badge/skills/junghan0611/entwurf/entwurf-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 entwurf-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/junghan0611/entwurf/entwurf-release"><img src="https://agentmods.dev/badge/skills/junghan0611/entwurf/entwurf-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,917 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00105 $0.08917
Opus 5 $0.00053 $0.04458
Sonnet 5 $0.00021 $0.01783
Haiku 4.5 $0.00011 $0.00892

Measured today against content hash 38a2666927c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

entwurf-release scanned grade C with 1 finding 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/verify-exact-ci.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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

xargs -r -a "$RESIDUE" rm -rf -- # read the list above FIRST; it is the whole delete set
.claude/skills/entwurf-release/SKILL.md · 858 lines

How it starts

The opening of the file, as written. The whole thing — 858 lines — stays where its author put it; the contents beside it link to each section on GitHub.

entwurf-release

Repository: ~/repos/gh/entwurf.

This skill is the shared release-operation SSOT that replaces the former .pi/prompts/prepare-release.md and .pi/prompts/make-release.md files. Claude Code discovers it natively under .claude/skills/; pi discovers the same file through .pi/settings.json and its "skills": ["../.claude/skills"] entry.

Invocation

# Claude Code - stable example
/entwurf-release land 0.12.8
/entwurf-release prepare 0.12.8
/entwurf-release make 0.12.8
/entwurf-release publish 0.12.8 /absolute/path/to/candidate.tgz latest

# pi - prerelease/repair example
/skill:entwurf-release land 0.12.8-repair.1
/skill:entwurf-release prepare 0.12.8-repair.1
/skill:entwurf-release make 0.12.8-repair.1
/skill:entwurf-release publish 0.12.8-repair.1 /absolute/path/to/candidate.tgz repair

Natural-language requests map to the same four modes.

  • land pushes an already reviewed pre-version HEAD and waits for the required exact-SHA CI jobs. It never edits, versions, tags, or publishes.
  • prepare edits release records, runs deterministic and LIVE gates, and creates the release-prep commit. It never pushes, tags, or publishes.
  • make pushes the prepared HEAD, waits for exact-SHA CI, creates and accepts one preserved candidate, then tags, stamps, and creates the GitHub release. It never runs npm publish.
  • publish publishes only the already accepted preserved candidate under an explicitly supplied dist-tag and proves the registry-installed result.

The invocation authorizes only the named mode. prepare is not land authorization. make is not publish authorization. If the mode, version, or a mode-specific required argument is missing, ask for it and stop.

Shared version contract

Accept a normal SemVer release or prerelease. Reject a leading v.

VERSION="<user argument>"
case "$VERSION" in
  "") echo "ABORT: version required (for example 0.12.8 or 0.12.8-repair.0)"; exit 1 ;;
  v*) echo "ABORT: drop the leading 'v'"; exit 1 ;;
esac
if [[ ! "$VERSION" =~ ^[0-9]+\.[0-9]+\.[0-9]+(-[0-9A-Za-z-]+(\.[0-9A-Za-z-]+)*)?$ ]]; then
  echo "ABORT: version must be SemVer, optionally with a prerelease suffix"
  exit 1
fi

Read the full file on GitHub · 858 lines

Files

What ships with it

1 file 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. today Changed · +5 lines 38a2666927c1
  2. yesterday Changed · +79 lines 4274765163f4
  3. 2d ago Changed · +45 lines 2bb4500de837
  4. 3d ago Changed · +4 lines 573756803c90
  5. 5d ago Changed · +5 lines cd1bb51af5ef
  6. 10d ago First seen · 720 lines · 105 tokens per session scan C b957e30964b3

Subscribe to this mod's changes

entwurf-release is a skill published in the GitHub repository junghan0611/entwurf (27 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 8,917 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

dsh-plugin-publisher

A release tool for DSH plugins, where DSH is the DeepSeek Harness used to load these add-ons. It validates an existing plugin package, publishes it through npm, Git, or a tarball, and checks that the harness can load it.

lovstudio/skills · 82 tokens

lov-skill-optimizer

Audit and optimize one or more existing Agent Skills from a canonical source path, then bump semver, update README/SKILL.md/skill.yaml/CHANGELOG.md, and verify installed copies and catalog synchronization. Checks frontmatter, trigger quality, CLI hygiene, naming, portability, version drift, dirty worktrees, shared…

lovstudio/skills · 127 tokens

lov-skill-publisher

Publish or submit a validated Skill. Default to the LovStudio official website, run lov-skill-pricing automatically, and use other channels only when explicitly named.

lovstudio/skills · 38 tokens

github-release-notes-writer

Draft or update user-focused GitHub Release Notes from verified tags, commits, pull requests, existing releases, and supplied changelog baselines. Use when preparing prerelease or stable release notes, turning GitHub's generated What's Changed list into a curated narrative, documenting upgrades or breaking changes, or…

flc1125/skills · 84 tokens

github-release-pr-writer

Draft or update GitHub release pull request descriptions from verified tags, commits, merged pull requests, and the release diff. Use when a PR prepares a version, aligns release metadata, promotes a prerelease, or needs a reviewer-focused release summary, exact change inventory, breaking-change section, or migration…

flc1125/skills · 80 tokens

otel-changelog-pr-verifier

Verify whether CHANGELOG entries in an OpenTelemetry Go repository point to the correct pull requests and whether each (#NNNN) matches the described change. Use when checking a release PR, validating a CHANGELOG section, or screening only mismatched changelog-to-PR references.

flc1125/skills · 62 tokens