PuPu: Skill for Claude Code

.claude/skills/release-open-sprint/SKILL.md

release-open-sprint is a skill for Claude Code from haoxiang-xu/PuPu. It costs 87 tokens per session (824 once invoked), scanned A, original, Apache-2.0.

A workflow for opening a new PuPu software release as a parent GitHub issue, with its release work tracked in smaller child issues. It treats the GitHub Project as the official record of the release scope.

In plain words
What is it for?
Use it to review recent growth and download information, choose the next version, create the release parent issue, and set its project size and planning status.
Why use it?
It keeps all work for one version grouped in one place and avoids relying on separate sprint documents. It also uses project data to inform release planning before the release is opened.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is haoxiang-xu/PuPu's own configuration. It tells Claude Code how to work on PuPu 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 PuPu configures →

Reuse

Borrowing it

Nothing to install: this file belongs to haoxiang-xu/PuPu. 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/haoxiang-xu/PuPu/main/.claude/skills/release-open-sprint/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/haoxiang-xu/PuPu

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-open-sprint

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/haoxiang-xu/pupu/release-open-sprint"><img src="https://agentmods.dev/badge/skills/haoxiang-xu/pupu/release-open-sprint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 824 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00087 $0.00824
Opus 5 $0.00044 $0.00412
Sonnet 5 $0.00017 $0.00165
Haiku 4.5 $0.00009 $0.00082

Measured 12d ago against content hash f73b98670693, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

release-open-sprint 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 12d 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.

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-open-sprint/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release: Open

GitHub Project is the only operational record. A version is one open parent issue whose Project Size is Release; its direct sub-issues are the whole release scope. Iterations is optional scheduling, never version membership. Do not create or maintain a sprint document.

Plumbing: read board-api.md in this directory first. Without project scope, do not mutate the Project.

Acts

Every scope call belongs to the project owner: present one item, wait for the decision, then execute and record it on the affected GitHub issue.

Act 0 — data first. Run growth-analyst in light mode, reusing .claude/archive/growth snapshots younger than seven days. Report the previous release's download trend, stars/uniques delta, search movement, notable new issues/discussions, and the topic-optimizer verdict. One screen, business language.

Act 1 — open the Release parent. Propose the previous version +0.0.1, or use the project owner's version. Find open Size=Release parents first; zero or several matches requires an explicit project owner choice. For a new release, create Release vX.Y.Z with label release, add it to PUPU Project, set Size=Release and Status=Planning. The project owner dictates the version intent and release conditions; write their words in the parent body without inventing a keynote. Set Iterations only if the project owner explicitly chooses a time cadence.

Act 2 — carryover. List the previous Release parent's open direct sub-issues and unparented backlog items. For each, the project owner chooses: attach to this Release, keep backlog, close, or move to a named future Release. Before removing or reparenting, comment the decision, reason, and destination on the old parent; after attaching, note it on the new parent. Never infer membership from an Iterations value, title, or label. Before attaching any legacy item, confirm its work-type label with the project owner; a new user-facing capability must carry new feature, and an unclassified item stays out of the Release.

Read the full file on GitHub · 67 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. 12d ago First seen · 67 lines · 87 tokens per session scan A f73b98670693

Subscribe to this mod's changes

release-open-sprint is a skill published in the GitHub repository haoxiang-xu/PuPu (36 stars, last pushed yesterday), licensed Apache-2.0. It adds 87 tokens to every session and 824 once invoked, about $0.0004 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 2026-08-30.