Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Azzygoatcoder/agent-useful-skills --skill pr-skillgit clone --depth 1 https://github.com/Azzygoatcoder/agent-useful-skillsWrote 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/azzygoatcoder/agent-useful-skills/pr-skill)<a href="https://agentmods.dev/skills/azzygoatcoder/agent-useful-skills/pr-skill"><img src="https://agentmods.dev/badge/skills/azzygoatcoder/agent-useful-skills/pr-skill/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/azzygoatcoder/agent-useful-skills/pr-skill"><img src="https://agentmods.dev/badge/skills/azzygoatcoder/agent-useful-skills/pr-skill.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 | $0.00070 | $0.00750 |
| Opus 5 | $0.00035 | $0.00375 |
| Sonnet 5 | $0.00014 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
pr-skill 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 8d 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.
What it actually says
PR — 提 Pull Request 工作流
fork 工作流提 PR。用于「无上游 push 权限」或「有权限但想走评审」的场景。
何时用 / 何时不用（看 push 权限）
判据同 release-skill：git remote -v 看 origin 是「权威仓库」还是「你的 fork」。
| 角色 | 要不要用 pr-skill |
|---|---|
| Owner（origin 即你的主仓库） | ❌ 不需要——直接 push，不用 PR |
| Maintainer（团队 repo 写权限） | 可选——想走评审才用 |
| Contributor（只有 fork） | ✅ 必须——fork-PR 是唯一路径 |
Prerequisites
ghCLI 已登录- remotes：
origin= upstream（权威）、fork= 你的 fork - 工作区干净（先 commit）
- 默认分支用
git rev-parse --abbrev-ref HEAD判（master / main 皆可，别硬编码）
步骤
- 定分支名：问用户，或从 commit 主题推（如
fix/feishu-deadlock、feat/aihot-push） - 建分支 + 推到 fork：
git checkout -b <branch> git push fork <branch> -u - 重置默认分支到 origin（工作留在 feature 分支，本地默认分支保持干净）：
git checkout <default-branch> git reset --hard origin/<default-branch> - 取 fork owner：
git remote get-url fork拼--head - 建 PR：
gh pr create --title "<conventional-commit>" --base <default-branch> --head <fork-owner>:<branch> --body "..."- title 用 conventional commit（
fix:/feat:/refactor:/chore:/docs:） - body 1-2 段说明改了什么、为什么；多文件改动加 "What changed" 节
- title 用 conventional commit（
- 报 PR URL 给用户
Edge cases
- 工作区不干净：先 commit 或 stash
- 分支已在 fork 存在：force-push 或换名
- gh 未登录：
gh auth login - 多 remote：确认 origin/fork 配置正确再推
自进化日志
| 日期 | 学习来源 | 吸收的模式 |
|---|---|---|
| 2026-08-13 | 角色化梳理（owner/maintainer/contributor） | 加「何时用」判据：owner 直接 push 不需要 PR，只有 contributor（或走评审的 maintainer）才用；与 release-skill 共用「push 权限」判据；默认分支自动判；中文化 + 场景表 + 自进化日志对齐科研骨架规范 |
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.
- 8d ago First seen · 61 lines · 70 tokens per session scan A 8dd9f8a6df3d
pr-skill is a skill published in the GitHub repository Azzygoatcoder/agent-useful-skills (6 stars, last pushed 10d ago), licensed MIT. It adds 70 tokens to every session and 750 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 2026-08-31.
Other skills, from other repositories
dsh-git-commit
A Git commit guide for writing standardised commit messages and performing basic checks before committing code. Git commits are saved checkpoints in a project’s history.
dsh-changelog
A release-note writing guide for maintaining a CHANGELOG, a file that records what changed in each software version. It follows Keep a Changelog categories and semantic versioning rules.
dsh-plugin-publish
A publishing procedure for putting a DSH plugin on GitHub and adding it to the DSH community list. DSH is the plugin ecosystem described by the procedure, and GitHub is the code-hosting service where the plugin is published.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.