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/chrislamdev/hermes-core-skills/open-source-adaptation-patternnpx skills add ChrisLamDev/hermes-core-skills --skill open-source-adaptation-patterngit clone --depth 1 https://github.com/ChrisLamDev/hermes-core-skillsWrote 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/chrislamdev/hermes-core-skills/open-source-adaptation-pattern)<a href="https://agentmods.dev/skills/chrislamdev/hermes-core-skills/open-source-adaptation-pattern"><img src="https://agentmods.dev/badge/skills/chrislamdev/hermes-core-skills/open-source-adaptation-pattern.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 | $0.00018 | $0.01618 |
| Opus 5 | $0.00009 | $0.00809 |
| Sonnet 5 | $0.00004 | $0.00324 |
| Haiku 4.5 | $0.00002 | $0.00162 |
Grade A, and why
open-source-adaptation-pattern 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
開源項目分析與落地模式
3 層判斷流程
第1層：可以直接用嗎？
檢查工具生態是否兼容。唔兼容就跳第2層。
第2層：設計理念可以參考嗎？
如果唔可以直接用，睇佢嘅核心理念係咪通用嘅。通用理念就可以借鑒。
第3層：落地執行
將理念轉化為自己生態嘅實現方式，唔好1:1抄襲。
多層次分析模式（2026-06-16 CUA 經驗補充）
大 project 通常由多個子組件組成，唔同組件可能有唔同嘅可用性層次。要逐個分析，唔好一刀切：
4 個層次
- 🔧 可直接裝 — binary/app，一條 command 搞掂（如 Cua Driver）
- 📦 可 pip/brew 裝但有限制 — Python package 或 library，但可能要額外 runtime（如 QEMU、雲端 API key）
- 📚 可學習設計 — 源碼公開，可以參考架構同 API 設計（如 MCP Server 模式、Background input 技術）
- ☁️ 要錢/要賬號 — 雲端服務，免費版有限制（如 Cua Sandbox 雲端版要 CUA_API_KEY）
執行方式
- 逐個子組件 run 一次呢個 4 層 filter
- 最後對師兄匯報時用 Emoji 標記（✅ 裝到 / ⚠️ 有條件 / 📚 學設計 / ☁️ 要錢）
- 重點係：搞清楚「裝咗之後具體做到咩」，唔好剩係話「裝到」
執行步驟
- 快速掃描：README、安裝方式、目錄結構、核心文件
- 對比分析：建立「佢點做 vs 我哋點做」對比表
- 制定落地計劃：P0（立即）+ P1（今週）+ P2（規劃）
- 實作：適應自己生態，建立完整性驗證
- 匯報：用白話+比喻向師兄解釋變化
實作指引（2026-06-05 ECC 經驗補充）
深度分析階段
除咗 README 表面，一定要睇：
- Shortform/Longform guide（ECC 有 the-shortform-guide.md + the-longform-guide.md，入面先有真嘅使用哲學）
- 目錄結構（ECC 嘅 .agents/、hooks/、skills/、.claude/ 結構反映咗佢點組織 agent workflow）
- Install script（ECC 嘅 install.sh 揭示咗佢依存 Node.js runtime，唔係純 config pack）
Adaptation 核心原則
- 唔好直接 clone workspace — ECC 251 skills 大部分同你嘅項目無關，clone 落嚟佔幾百 MB
- 抽象核心理念 — ECC 嘅「subagents + hooks + skills + memory persistence」係通用理念，每個 harness 實現方式唔同
- 適應自己生態 — Hermes Agent 冇 Claude Code 嘅 hooks framework，所以要用 boot.sh 模式 + .agents/.md 文件代替
對師兄匯報方式
- 先講結論：「用唔用到 / 參考到」
- 然後「之前 vs 現在」對比
- 最後「師兄只需要記住 XX 一句話就得」
驗證項目
- 所有新元件存在且可執行
- boot.sh已更新（如果 boot.sh 係落地一部分）
- STATE.md已記錄
- git commit已做
- 已用白話+比喻向師兄匯報
實戰測試方法論（2026-06-06 headroom 經驗補充）
當工具聲稱可以「慳錢/加速/壓縮」時，必須做實際 workload 測試先好決定留唔留：
headroom-ai 測試案例
聲稱：壓縮 tool output 60-95% token，唔影響質量 實際測試結果：
- user messages（對話內容）→ 0% 壓縮（protected，跳過）
- 短 tool output（JSON 回傳）→ 0% 壓縮（router判斷為
protected:recent_code） - 長 prose 文章（RSS 文章）→ -10% 壓縮（反而大了，router唔擅長純文字）
- 重複性 verbose tool output → 0-95%（95% 係因為 router 判斷「太短」直接極簡，唔係有意義壓縮） 結論：headroom 真係好，但設計場景係 CI logs / code search / build output，唔係我哋嘅 prose 文章或對話
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 · 105 lines · 18 tokens per session scan A f2bf04124547
open-source-adaptation-pattern is a skill published in the GitHub repository ChrisLamDev/hermes-core-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 1,618 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
specification-writing
Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
golden-rss
Use when testing the rss golden build.
overleaf-sync
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…
omh-code-review
This is a Hermes-native code-review workflow skill.