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 compound-promotion-laddergit 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/compound-promotion-ladder)<a href="https://agentmods.dev/skills/jerrylalala/compound-engineering/compound-promotion-ladder"><img src="https://agentmods.dev/badge/skills/jerrylalala/compound-engineering/compound-promotion-ladder/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/jerrylalala/compound-engineering/compound-promotion-ladder"><img src="https://agentmods.dev/badge/skills/jerrylalala/compound-engineering/compound-promotion-ladder.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 | $0.00067 | $0.01383 |
| Opus 5 | $0.00034 | $0.00691 |
| Sonnet 5 | $0.00013 | $0.00277 |
| Haiku 4.5 | $0.00007 | $0.00138 |
Grade A, and why
compound-promotion-ladder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compound Promotion Ladder — 经验分层沉淀
Codex 洞察（P4→P5）：本仓库强项不是"自动造 skill"，而是"把经验分层沉淀成可检索、可升级知识"。
升级阶梯
原始经验 → solution doc → critical pattern → existing skill 补充 → new skill
↑ ↑
ce:compound 写入 手动决策后创建
| 层级 | 位置 | 形态 | 触发方式 |
|---|---|---|---|
| solution | docs/solutions/ |
具体事件记录 + YAML frontmatter | ce:compound 自动写入 |
| critical pattern | docs/solutions/ + pattern: tag |
跨场景抽象规律 | 检测到 ≥2 次重复后提升 |
| skill supplement | 现有 skills/*/SKILL.md 新增章节 |
在已有 skill 内追加注意事项 | 检测到跨模块影响 |
| new skill | skills-custom/ 新目录 |
独立 SKILL.md | 非显然模式 + 影响范围广 |
P5a：ce:compound 后的自动检测
ce:compound 写入 solution doc 后，运行以下检测：
检测逻辑
# 1. 统计同类问题出现频次
# 检查 docs/solutions/ 中相同 tags 的文档数量
SIMILAR_COUNT=$(grep -rl "tags:.*$TAG" docs/solutions/ | wc -l)
# 2. 检查是否跨模块
AFFECTED_FILES=$(git log --all -- "$RELATED_FILE" --name-only | sort -u | wc -l)
# 3. 判断是否为非显然模式（无法通过直觉推导）
# 需要人工判断，但 AI 可以提示
升级触发条件
| 条件 | 行动 | 优先级 |
|---|---|---|
| 同类问题 ≥ 2 次（相同 tags） | 建议提升为 critical pattern |
中 |
| 影响 ≥ 3 个不同模块 | 建议补充到相关 skill | 高 |
| 非显然模式 + 频繁出现 | 建议创建新 skill | 高 |
| 单次事件，无重复 | 保留 solution doc，不提升 | 低 |
检测输出格式
ce:compound 完成后，如果检测到升级条件，输出：
🪜 Compound Promotion 检测结果：
同类问题出现 3 次（tags: windows-hooks, encoding）
影响模块：hooks/, scripts/, .claude/
建议：
1. 将 docs/solutions/2026-04-05-windows-hooks-crlf.md 提升为 critical pattern
→ 添加 type: critical-pattern 到 frontmatter
2. 在 skills/git-worktree/SKILL.md 的 Windows 注意事项节补充此模式
执行？(y/n/skip)
P5b：Recurrence Miner — 定期挖掘重复问题
手动调用时（或每月），从 docs/solutions/ 挖掘重复模式：
# 1. 按 tags 统计频次
grep -r "^tags:" docs/solutions/*.md | \
sed 's/.*tags: //' | tr ',' '\n' | \
sort | uniq -c | sort -rn | head -20
# 2. 找出同一 file_path 出现多次的问题
grep -r "^ - " docs/solutions/*.md | \
grep -E "file_path|affected_files" | \
awk '{print $NF}' | sort | uniq -c | sort -rn | head -10
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.
- 10d ago First seen · 161 lines · 67 tokens per session scan A a04f0c157bfe
compound-promotion-ladder is a skill published in the GitHub repository Jerrylalala/compound-engineering (5 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 1,383 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.