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.
curl -O https://raw.githubusercontent.com/junghan0611/entwurf/main/.claude/skills/entwurf-release/SKILL.mdgit clone --depth 1 https://github.com/junghan0611/entwurfWrote 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.
[](https://agentmods.dev/skills/junghan0611/entwurf/entwurf-release)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00105 | $0.12053 |
| Opus 5.5 | $0.00042 | $0.04821 |
| Sonnet 5.5 | $0.00021 | $0.02411 |
| Haiku 4.5 | $0.00011 | $0.01205 |
Grade C, and why
entwurf-release scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
xargs -r -a "$RESIDUE" rm -rf -- # read the list above FIRST; it is the whole delete set How it starts
The opening of the file, as written. The whole thing — 1,071 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.
landpushes an already reviewed pre-version HEAD and waits for the required exact-SHA CI jobs. It never edits, versions, tags, or publishes.prepareedits release records, runs deterministic and LIVE gates, and creates the release-prep commit. It never pushes, tags, or publishes.makepushes the prepared HEAD, waits for exact-SHA CI, creates and accepts one preserved candidate, then tags, stamps, and creates the GitHub release. It never runsnpm publish.publishpublishes 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.
A narrower operator restriction may add a requirement or block a mode, never remove a
VERIFY.md release-acceptance axis. If the current lane forbids local FULL or required LIVE
execution, feature-branch push/CI may proceed when authorized, but prepare/make remains blocked
until the named cut can run its required floors. Do not reinterpret that restriction as a
floor waiver, nor a delegated tag/release decision as proof those floors already passed.
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.
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.
- 5d ago Changed · +43 lines b9e3607696e6
- 6d ago Changed · +6 lines 8128db5d7f6a
- 7d ago Changed · +11 lines d70b10645490
- 9d ago Changed · +91 lines 27f9b7932671
- 12d ago Changed · -22 lines a583b8744ce2
- 19d ago Changed · +8 lines 81980ce3fe79
- 1mo ago Changed · +75 lines 2565afaf6e50
- 1mo ago Changed · +1 lines 990bc4455150
- 1mo ago Changed · +5 lines 38a2666927c1
- 1mo ago First seen · 853 lines · 105 tokens per session scan C 4274765163f4
entwurf-release is a skill published in the GitHub repository junghan0611/entwurf (31 stars, last pushed 2d ago), licensed MIT. It adds 105 tokens to every session and 12,053 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
update-v8-version
Update Codex's pinned v8 / rustyv8 versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update rustyv8 artifacts, prepare or validate a V8 release candidate, check v8-canary, or diagnose why a V8 version update no longer builds.
pi-package-sandbox-test
Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.
rp
Always read this skill when the user mentions "rp" or "repoprompt", or before accessing a repository outside the current RepoPrompt workspace. Covers workspace discovery, binding, root verification, and workspace hygiene.
pi-release-workflow
Use when preparing or validating Pi monorepo releases, including Changesets, pnpm lockfile updates, package previews, release-age policy, and installability checks.
pi-review-gated-delivery
Use when coordinating review-gated delivery of discrete GitHub issues between one implementation peer and a review-only lead, with user-owned Changesets and approval-gated commits.
managing-archestra-releases
Runs rolling beta releases, stable patches, and complete stable-line cutovers. Use when backporting fixes, cutting or retiring release branches, configuring release protections, testing artifacts, recovering failed runs, or approving releases.