ce-compound-lite

ce-compound-lite is a skill for Claude Code, Codex from astordu/qoderharness. It costs 121 tokens per session (881 once invoked), scanned A, original, MIT.

A workflow for turning completed coding work into a reusable solution note. It captures the problem, context, final approach, verification, and reuse guidance in a Markdown file under docs/solutions/.

In plain words
What is it for?
Documenting debugging results, implementation patterns, important trade-offs, and lessons learned after a task is complete.
Why use it?
It preserves non-obvious fixes and decisions so future agents can find and reuse them instead of investigating from scratch.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions AGENTS.md.

Install

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.

agentmods
npx agentmods add skills/astordu/qoderharness/ce-compound-lite
Any agent
npx skills add astordu/qoderharness --skill ce-compound-lite
Clone the repo
git clone --depth 1 https://github.com/astordu/qoderharness

Made for: Claude Code, Codex.

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 ce-compound-lite

README.md
[![agentmods](https://agentmods.dev/badge/skills/astordu/qoderharness/ce-compound-lite.svg)](https://agentmods.dev/skills/astordu/qoderharness/ce-compound-lite)
Your own site
<a href="https://agentmods.dev/skills/astordu/qoderharness/ce-compound-lite"><img src="https://agentmods.dev/badge/skills/astordu/qoderharness/ce-compound-lite.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 881 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00121 $0.00881
Opus 5 $0.00060 $0.00441
Sonnet 5 $0.00024 $0.00176
Haiku 4.5 $0.00012 $0.00088

Measured 6d ago against content hash 82b09af97c90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ce-compound-lite 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 6d 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.

.qoder/skills/ce-compound-lite/SKILL.md · 119 lines

What it actually says

CE Compound Lite

在任务完成后使用此技能,将已完成的工作蒸馏为可复用的方案文档。

目标

创建一份持久、可搜索的方案笔记,供未来的 agent 复用。

仅在 docs/solutions/ 下写入一个最终文件。Subagent 不得写文件。

何时使用

  • 任务揭示了非显而易见的修复、工作流或决策
  • 任务涉及调试、调查或权衡取舍
  • 用户要求"复利工程"、"沉淀"、"lessons learned"或"write this up"

如果任务很琐碎且没有产生可复用的洞察,跳过此技能。

输入

收集最少必要的上下文:

  • 最近的用户请求
  • 变更的文件或产生的产物
  • 关键命令、错误或约束
  • docs/solutions/ 下可能与新内容重叠的已有文档

轨道

选择一个主轨道:

  • bug:诊断并修复了一个异常行为
  • knowledge:建立了一个可复用的实现模式、决策或工作流

工作流

  1. 从当前对话和工作区收集任务上下文。
  2. 一定要通过 Agent 工具启动最多三个 subagent(位于 .qoder/agents/):
    • context-analyzer:分析上下文
    • solution-extractor:提取可复用方案
    • related-docs-finder:发现相关已有文档
  3. 检查 docs/solutions/ 中是否已有可能重叠的文档。
  4. 决定是创建新笔记还是更新已有笔记。
  5. docs/solutions/ 下写入恰好一个 Markdown 文件。

Subagent 规则

如果启动 subagent:

  • 给每个 subagent 一个狭窄的只读任务
  • 让它们以纯文本返回发现
  • 不允许 subagent 编辑文件
  • 编排器拥有所有最终编辑权

输出格式

使用此结构:

---
title: 简短标题
slug: short-kebab-name
track: bug|knowledge
updated_at: YYYY-MM-DD
keywords:
  - keyword
  - keyword
---

# 简短标题

## 问题

发生了什么或需要弄清楚什么。

## 上下文

约束、症状、根因或相关环境细节。

## 方案

最终采用的方法。有用时引用具体文件、命令或检查。

## 复用

未来 agent 遇到类似情况时应首先做什么。

## 参考

- 相对路径或命令

质量标准

  • 偏好一个具体笔记而非宽泛摘要
  • 移除填充内容,只保留下次有用的信息
  • 包含足够的细节使笔记可执行
  • 保持文件名稳定且可搜索

文件命名

使用 docs/solutions/<slug>.md

推荐简短描述性的 slug,例如:

  • fix-dev-server-port-conflict.md
  • document-postgres-migration-workflow.md

可发现性

未来 agent 在重新解决类似问题前应搜索 docs/solutions/

如果 AGENTS.md 未提及此目录,更新它。

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. 6d ago First seen · 119 lines · 121 tokens per session scan A 82b09af97c90

Subscribe to this mod's changes

ce-compound-lite is a skill published in the GitHub repository astordu/qoderharness (23 stars, last pushed 2d ago), licensed MIT. It adds 121 tokens to every session and 881 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens