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 agentmods add skills/jerrylalala/compound-engineering/ce-prnpx skills add Jerrylalala/compound-engineering --skill ce-prgit clone --depth 1 https://github.com/Jerrylalala/compound-engineeringWrote 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/jerrylalala/compound-engineering/ce-pr)<a href="https://agentmods.dev/skills/jerrylalala/compound-engineering/ce-pr"><img src="https://agentmods.dev/badge/skills/jerrylalala/compound-engineering/ce-pr.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.01263 |
| Opus 5 | $0.00009 | $0.00632 |
| Sonnet 5 | $0.00003 | $0.00253 |
| Haiku 4.5 | $0.00002 | $0.00126 |
Grade A, and why
ce:pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Creation & Merge Command
创建 Pull Request 并可选合并到主分支。可在 /ce:work 或 /ce:review 完成后自动触发,也可独立使用。
参数解析
开始时解析用户参数:
--draft:创建 draft PR--no-merge:创建或定位 PR 后直接结束,不进入合并询问
移除已识别参数后,其余内容可作为 PR 标题/描述的额外上下文。
Phase 1: Pre-flight Checks
Step 1: 检测当前分支
current_branch=$(git branch --show-current)
如果 current_branch 为空(detached HEAD): → 提示用户:"当前处于 detached HEAD 状态,请先切换到功能分支。" → 终止流程
Step 2: 检测主分支
git symbolic-ref refs/remotes/origin/HEAD
如果输出形如 refs/remotes/origin/main,去掉 refs/remotes/origin/ 前缀作为 default_branch。
如果命令失败或输出为空,执行:
git rev-parse --verify origin/main
如果命令成功,使用 main 作为 default_branch;如果失败,使用 master。
Step 3: 分支安全检查
如果 current_branch == default_branch:
→ 提示:"当前在主分支 ($default_branch) 上,无法创建 PR。请先切换到功能分支。"
→ 终止流程
Step 4: 检查未提交的更改
git status --porcelain
如果有未提交的更改: → 使用 AskUserQuestion tool 询问:
Question: "检测到未提交的更改。如何处理?"
Options:
- 自动提交所有更改 - 使用自动生成的 commit message 提交
- 仅创建 PR(忽略未提交更改) - 只将已提交的内容纳入 PR
- 取消 - 先手动处理更改再创建 PR
Based on selection:
- 自动提交 → 读取
git status --porcelain,按相关变更列出具体文件,使用git add <file...>暂存确认后的文件,再执行git commit -m "feat: [auto-generated message]" - 忽略 → 继续流程
- 取消 → 终止流程
Step 5: 检查是否已有 PR
existing_pr=$(gh pr list --head "$current_branch" --json number,url --jq '.[0]')
如果已有 PR:
→ 如果 --no-merge 参数存在,显示已有 PR URL 后结束流程。
→ 否则使用 AskUserQuestion tool 询问:
Question: "当前分支已有 PR: $existing_pr_url。如何处理?"
Options:
- 查看已有 PR - 在浏览器中打开
- 跳到合并步骤 - 直接询问是否合并已有 PR
- 取消 - 终止流程
Based on selection:
- 查看 →
gh pr view --web - 合并 → 跳转到 Phase 3
- 取消 → 终止流程
Phase 2: Create PR
Step 1: 检查远端分支
git ls-remote --exit-code origin "$current_branch"
如果命令失败,执行:
git push -u origin "$current_branch"
如果命令成功,执行:
git push
Step 2: 生成 PR 标题
pr_title=$(echo "$current_branch" | sed 's|/|: |; s|-| |g')
commit_title=$(git log "$default_branch".."$current_branch" --format="%s" --reverse | head -1)
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.
- 5d ago First seen · 164 lines · 17 tokens per session scan A b49a769b3c48
ce:pr is a skill published in the GitHub repository Jerrylalala/compound-engineering (5 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 1,263 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
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release
Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.
changelog
Create changelog files for important commits in a PR.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
refresh-arm-sdk-release
WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…