agentmods.dev

Pixuli: Skill for Cursor

.cursor/skills/ref-issue-pr/SKILL.md

ref-issue-pr is a skill for Cursor from trueLoving/Pixuli. It costs 47 tokens per session (509 once invoked), scanned A, original, MIT.

A workflow for turning REF-labeled refactoring issues into pull requests and keeping the project plan updated. It covers issue research, implementation, tests, PR details, post-merge tracking, and creating new refactor tasks.

In plain words
What is it for?
Use it for GitHub Issues marked with REF- identifiers, milestones M1–M6, or changes that must be tracked in PLANS.md, a project planning file.
Why use it?
It keeps issue requirements, code changes, tests, pull requests, and the refactoring plan aligned.

Skill for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

This is trueLoving/Pixuli's own configuration. It tells Cursor how to work on Pixuli 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 Pixuli configures →

not rated 64repo changed 2d ago A scan SkillSpector: pass 47 tokens original MIT
View source ↗ trueLoving/Pixuli pixuli-web.vercel.app
Reuse

Borrowing it

Nothing to install: this file belongs to trueLoving/Pixuli. 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/trueLoving/Pixuli/develop/.cursor/skills/ref-issue-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/trueLoving/Pixuli

Made for: Cursor.

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 ref-issue-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/trueloving/pixuli/ref-issue-pr/github.svg)](https://agentmods.dev/skills/trueloving/pixuli/ref-issue-pr)
Your own site
<a href="https://agentmods.dev/skills/trueloving/pixuli/ref-issue-pr"><img src="https://agentmods.dev/badge/skills/trueloving/pixuli/ref-issue-pr/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 ref-issue-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/trueloving/pixuli/ref-issue-pr"><img src="https://agentmods.dev/badge/skills/trueloving/pixuli/ref-issue-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 509 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 $0.00047 $0.00509
Opus 5.5 $0.00019 $0.00204
Sonnet 5.5 $0.00009 $0.00102
Haiku 4.5 $0.00005 $0.00051

Measured 2d ago against content hash b1e8433b5fee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ref-issue-pr 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 2d 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.

.cursor/skills/ref-issue-pr/SKILL.md · 58 lines

What it actually says

REF Issue → PR

Before coding

  1. Read issue body on GitHub (gh issue view <n>) for 计划编号 (REF-xxx)
  2. Open matching row in PLANS.md — check Depends on, Labels, 建议顺序
  3. Read linked docs under docs/ (not .local/ unless available)

Implementation

  • Smallest correct diff; match monorepo conventions (AGENTS.md)
  • Run pnpm test; add tests for provider/core changes
  • Do not commit unless user asks

PR

## Summary

- …

## Test plan

- [ ] pnpm test
- [ ] pnpm run ci
- [ ] …

Fixes #<issue> # only if PR fully closes the issue Related: REF-<id>
  • Title: [M4] REF-414 … or fix(m3): … (REF-313)
  • Link milestone label if applicable (m4, refactor, etc.)

After merge

  1. Align with GitHub: issue should be CLOSED if Fixes #n merged
  2. Update PLANS.md：对应行 状态 → ✅，或从「进行中」表移除
  3. 更新 Plans 文首 最近同步 日期；必要时跑 gh issue list --state open 核对 OPEN 条数
  4. User-facing docs → docs/guide.md / docs/product.md；Agent/Skill → AGENTS.md / .cursor/（仅架构边界变更时）

Add a new task

  1. gh issue create（标题含 [M4|M5|M6]，label / milestone 齐全）
  2. 把 #number、标题、REF-id 写入 PLANS.md 对应里程碑表
  3. 需要排期时写入「当前焦点」表
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. 2d ago Changed b1e8433b5fee
  2. 2mo ago First seen · 58 lines · 47 tokens per session scan A 8604e12096ff

Subscribe to this mod's changes

ref-issue-pr is a skill published in the GitHub repository trueLoving/Pixuli (64 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 509 once invoked, about $0.0002 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 2026-08-30.

Git and workflowPlanning
Related

ref-issue-pr compared with skills from other repositories

ref-issue-pr next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ref-issue-prtrueLoving/PixuliSkill64yesterdayMITA47Cursor
merge-batchdiegosouzapw/OmniRouteSkill83k5d agoMITA46Claude Code
prowler-commitprowler-cloud/prowlerSkill15kyesterdayApache-2.0A44Claude Code, Codex
gh-auth-isolationgithub/gh-awSkill5.6ktodayMITA20Claude Code, Codex
github-skillzeenie-ai/OpenCompanySkill1.1kyesterdayMITA51Claude Code
comet-githubrpamis/cometSkill3.3ktodayMITA72Claude Code, Codex
re0-mergeLilMGenius/paperthinSkill1.4k4d agoMITA70Claude Code