PuPu: Skill for Claude Code

.claude/skills/release-refine-ticket/SKILL.md

release-refine-ticket is a skill for Claude Code from haoxiang-xu/PuPu. It costs 60 tokens per session (1,025 once invoked), scanned A, original, Apache-2.0.

A workflow for turning a PuPu release sub-issue into a detailed implementation brief that a developer can follow without prior project knowledge. It uses repository and dependency investigation to clarify the work.

In plain words
What is it for?
Use it when refining a release ticket, especially when the change crosses repositories, providers, data formats, storage, or other persistent project state.
Why use it?
It removes uncertainty from draft tickets by documenting the relevant code, affected areas, and cross-system boundaries before implementation. Refinement is optional and does not block the developer from working.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

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-refine-ticket/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-refine-ticket

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/haoxiang-xu/pupu/release-refine-ticket"><img src="https://agentmods.dev/badge/skills/haoxiang-xu/pupu/release-refine-ticket.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,025 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 15
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00060 $0.01025
Opus 5 $0.00030 $0.00513
Sonnet 5 $0.00012 $0.00205
Haiku 4.5 $0.00006 $0.00103

Measured 11d ago against content hash 413c1161ca45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

release-refine-ticket 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 11d 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-refine-ticket/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release: Refine Ticket

Upgrade a draft into a brief a zero-context developer can execute. A separate refinement handoff is optional, not a prerequisite for assignment or implementation: [DRAFT] marks initial intent, not a delivery gate. Release work must be a direct child of an open Size=Release parent in PUPU Project; do not use a sprint document.

Method: apply the create-issue skill methodology to the existing issue: read .claude/skills/create-issue/SKILL.md and follow its investigation workflow and body structure. GitNexus query, context, and impact are required. If the task crosses a repository, process, provider, serialization, persistence, or durable-state boundary, also follow .claude/rules/cross-boundary-contract-gate.md. For an existing direct Release child, use that method only for investigation and body structure. Its confirmation-before-issue-creation steps govern creating a new issue; they do not apply to a scope-preserving body edit by the active implementing agent. Plumbing: .claude/skills/release-open-sprint/board-api.md.

Authority

An agent may directly edit the body of a direct Release child only while it is actively responsible for implementing that ticket. This standing authorization follows the implementation task, not the GitHub assignee; review, research, or audit participation alone does not grant it.

The implementing agent may preserve the project owner's What & Why and outcome-level scope while adding architecture context, relevant files, implementation path, verification, risks, dependencies, BC/SEQ/AC evidence, and delivery links. It may make the existing outline acceptance testable and remove the [DRAFT] marker when the body is sufficient for the work.

This is body-only authority. It does not permit changing the intended user result, non-goals, required capability, title, labels, Size, Project Status, Iteration, assignee, parent/child relationship, Release membership, or closure. If evidence calls for any of those changes, report evidence and options to the project owner and retain the current scope until they decide.

Read the full file on GitHub · 85 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. 11d ago First seen · 85 lines · 60 tokens per session scan A 413c1161ca45

Subscribe to this mod's changes

release-refine-ticket is a skill published in the GitHub repository haoxiang-xu/PuPu (36 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 1,025 once invoked, about $0.0003 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.