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 Jerrylalala/compound-engineering --skill ce-resumegit 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-resume)<a href="https://agentmods.dev/skills/jerrylalala/compound-engineering/ce-resume"><img src="https://agentmods.dev/badge/skills/jerrylalala/compound-engineering/ce-resume.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 5.1 | $0.00025 | $0.01100 |
| Opus 5 | $0.00013 | $0.00550 |
| Sonnet 5 | $0.00005 | $0.00220 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
ce:resume 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
回归项目入口
Note: The current year is 2026.
ce:resume 是间歇性开发者回到项目的起点。运行后你会在 30 秒内知道:
- 上次做了什么
- 有什么在等待
- 建议下一步是什么
然后直接跳入你选择的路径。
Interaction Method
使用平台的阻塞问答工具(Claude Code 中为 AskUserQuestion)。
Execution Flow
Phase 1: 数据收集(并行读取三个来源)
同时执行以下三个读取操作:
来源 A:git log
git log --oneline -10
- 提取最近 10 条提交
- 识别最后一个「功能性」commit(跳过纯 chore/docs/ci 类型)
- 若命令失败(非 git 仓库)→ 来源 A = 不可用,在摘要中注明「无法读取 git 历史」
来源 B:IDEAS.md
读取项目根目录 IDEAS.md:
- 统计未完成条目数量(
- [ ]出现次数) - 提取前 3 条未完成条目的标题(
**[标题]**部分) - 若文件不存在 → 来源 B = 不可用,在摘要中注明「IDEAS.md 不存在,建议运行 /ce:ideas 创建」
来源 C:Active Plans
扫描 docs/plans/*.md(若目录不存在则跳过):
- 读取每个文件的 frontmatter(
---之间的 YAML) - 筛选
status: active的文件 - 按
date字段降序排序,取最新 1-3 个 - 提取每个文件的
title(frontmatter 中)和date - 若目录不存在或无 active plan → 来源 C = 不可用,在摘要中注明「尚无进行中的计划」
Phase 2: 三段摘要输出
基于收集的数据,输出固定格式的三段摘要:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📋 项目状态摘要
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
## 上次做了什么
[来源 A 可用时:] 最近的功能性提交:[commit subject]
[附上最近 3-5 条 oneline log,让用户快速定向]
[来源 A 不可用时:] 无法读取 git 历史。
---
## 有什么在等待
[来源 B 可用时:]
💡 IDEAS.md:[N] 个未执行想法
• [条目 1 标题]
• [条目 2 标题]
• [条目 3 标题]
[若 N > 3,加:] ...等 [N-3] 个更多
[来源 B 不可用时:] IDEAS.md 不存在。
[来源 C 可用时:]
📐 进行中的计划:
• [plan title 1] ([date])
• [plan title 2] ([date])
[来源 C 不可用时:] 尚无进行中的计划。
---
## 建议下一步
[推断逻辑:]
- 若有 active plan → 「建议继续 [最新 plan title],离完成最近」
- 若无 active plan 但 IDEAS.md 有内容 → 「建议从 IDEAS.md 选一个方向,运行 /ce:ideas」
- 若两者都空 → 「项目看起来是全新状态,建议运行 /ce:ideate 或 /ce:ideas 从头探索」
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Phase 3: Handoff
使用 AskUserQuestion 询问用户选择:
「好的,你想从哪里开始?」
动态选项(根据数据可用性调整):
-
选项 1(仅当有 active plan 时显示):继续上次任务
→ Invoke skill compound-engineering:ce-work with args: [最新 active plan 路径] -
选项 2(仅当 IDEAS.md 有内容时显示):从 IDEAS.md 选一个方向
→ Invoke skill compound-engineering:ce-ideas with args: (无参数) -
选项 3:全新开始(从头探索新方向)
→ Invoke skill compound-engineering:ce-ideate with args: (无参数)
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 · 134 lines · 25 tokens per session scan A e92af953e9f1
ce:resume is a skill published in the GitHub repository Jerrylalala/compound-engineering (5 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 1,100 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…