Borrowing it
Nothing to install: this file belongs to xrf9268-hue/aiops-platform. 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/xrf9268-hue/aiops-platform/main/.claude/skills/handle-pr/SKILL.mdgit clone --depth 1 https://github.com/xrf9268-hue/aiops-platformWrote 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/xrf9268-hue/aiops-platform/handle-pr)<a href="https://agentmods.dev/skills/xrf9268-hue/aiops-platform/handle-pr"><img src="https://agentmods.dev/badge/skills/xrf9268-hue/aiops-platform/handle-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.
<a href="https://agentmods.dev/skills/xrf9268-hue/aiops-platform/handle-pr"><img src="https://agentmods.dev/badge/skills/xrf9268-hue/aiops-platform/handle-pr.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 | $0.00025 | $0.01599 |
| Opus 5 | $0.00013 | $0.00800 |
| Sonnet 5 | $0.00005 | $0.00320 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
handle-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handle PR #$ARGUMENTS
本仓库是 OpenAI Symphony SPEC 的 Go 端口，SPEC 对齐是硬要求。本 skill 覆盖 已有 PR 的 SPEC 对齐审查轮。
审查 / 合并协议是共享的。 commit-first、pre-push 双 reviewer、
@codex review每 push 收敛、GraphQL review threads 判定、PR-body 活账本、合并/auto-merge 门槛与 hard stops、回归+变异测试纪律统一在docs/runbooks/pr-review-merge-protocol.md。本 skill 只写 PR 审查阶段差异，到 push/审查/合并步骤照那份协议执行。
Upstream 已就位
![ -d /tmp/symphony-upstream ] || git clone --depth 1 https://github.com/openai/symphony.git /tmp/symphony-upstream 2>&1 | tail -3
参考路径：/tmp/symphony-upstream/SPEC.md + /tmp/symphony-upstream/elixir/lib/symphony_elixir/*.ex。SPEC 文本歧义时直接 grep Elixir 源码找原算法行号，不要用 WebFetch 总结。
当前 main HEAD
!git fetch origin main 2>&1 | tail -1 && git log --oneline origin/main -1
PR 审查阶段差异
-
并行 owner 探测（开始时 + 每次 push 前）：按协议 §8 探测活跃 owner；判定为 owned 即进入 §8 的 increment-only 协作模式，信号清单、观察窗、接管判据、push 被拒处理、触发去重全部以
docs/runbooks/pr-review-merge-protocol.md§8 为唯一来源，不在此复述。模式自主选定并通报用户，不询问。 -
读 AGENTS.md 的 "SPEC alignment" 和 "Cross-cutting checklist when porting from the Elixir reference" 两节作为审查清单。每个 finding 至少归到一类：
- 算法级 SPEC 偏差（vs upstream
handle_*逐分支比对） - 跨模块一致性漏镜像（grep 同概念其他 consumer，列出 aiops-platform 扩展 routing / fan-out / capacity caps / eligibility filter 是否都镜像了）
- Go 运行时硬化（followup goroutine 是否
context.WithTimeout/defer recoverPanic/Timer.Stop()——Elixir BEAM 隐式给的保证 Go 必须显式补） - 测试是否安慰剂（assertion 真的读到新代码改的字段吗？）
- 错位机制（在 §1 scheduler/runner 边界的错误一侧）：worker/orchestrator 侧「消费 agent 产物」的 phase/gate/artifact/config，先 grep Elixir 有没有等价物——没有就是过度设计信号，判删除（非搬进 prompt、非只记 DEVIATIONS），归宿默认是 WORKFLOW prompt（worker post-turn phase 在 push 后只能 flag 不能 prevent，且抢跑 D9 reconcile-cancel / §16.5 self-stop——#557 即此；AGENTS.md 原则 6；#557/#561 拆的就是这类）
- 算法级 SPEC 偏差（vs upstream
-
修一轮、提交一轮、push 前双审一轮：按协议 §2–§3 对稳定 head SHA 派 Codex + Claude Code 双 reviewer，并先执行协议里的 subagent-first reviewer routing；具体 reviewer-routing 细节以
docs/runbooks/pr-review-merge-protocol.md为唯一来源。主交互会话里的 reviewer subagent 路径在工具契约允许默认派生时默认开启、不问授权（#900）；运行时契约挡住时按协议记录 fallback，操作者可在当前请求写CLI review only等短语 opt-out。HIGH/MEDIUM/Critical 先验证技术正确性，再决定修复 / 反证 / 延后；不要盲从，也不要把 finding 当噪音略过。若 finding 证明计划本身错了，同轮更新代码、测试、SPEC/deviation 文档和 PR body。每 push 后按协议 §4 跑@codex review收敛、§5 用 GraphQL 处理 review threads。
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 · 51 lines · 25 tokens per session scan A 0becc8032be8
handle-pr is a skill published in the GitHub repository xrf9268-hue/aiops-platform (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 25 tokens to every session and 1,599 once invoked, about $0.0001 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
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
write-pr
Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.