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 AbyssCN/oh-my-dag --skill omd-deepengit clone --depth 1 https://github.com/AbyssCN/oh-my-dagWrote 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/abysscn/oh-my-dag/omd-deepen)<a href="https://agentmods.dev/skills/abysscn/oh-my-dag/omd-deepen"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-deepen/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/abysscn/oh-my-dag/omd-deepen"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-deepen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.00863 |
| Opus 5 | $0.00046 | $0.00432 |
| Sonnet 5 | $0.00018 | $0.00173 |
| Haiku 4.5 | $0.00009 | $0.00086 |
Grade A, and why
omd-deepen 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 12d 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.
What it actually says
/omd-deepen — 架构加深扫描
经 omd MCP 的 dag_deepen(可能带 mcp__omd__ 前缀;未加载先 ToolSearch "dag_deepen")。不是让一个 agent 满仓乱逛,而是:确定性热点 pass(按近期 commit 的 git 触碰频率算,零 LLM)先挑出摩擦真正所在的模块 → 一热点一 leaf 并发扫,各自用删除测试猎浅模块 → 合成 leaf 归并跨热点的重复逻辑并按 leverage 排序。产物是一张 HTML 报告(每个候选一卡:文件/摩擦度/删除测试判定/before-after 接口草图/强度)。
用法(参数都可省)
commits:回看多少条 git 历史算热点(默认 200)。热点太旧、近 N commit 无代码触碰会报错 → 加大重试。hotspots:扫描的热点目录个数(默认 6)。想更广加大,想快减小。- 想只扫某方向 → 给一个 scope 路径,跳过全仓排序。
流程(异步三段式)
dag_deepen(commits?, hotspots?)→ 拿runId;dag_status(runId)轮询,别重复发起;dag_result(runId)取 HTML 报告落盘路径 → 交给 owner;要转述要点自己Read。
浅模块判据(报告在找什么)
- 接口比实现贵:调用方要记的规矩、要传的参数、要处理的返回态,比这模块干的活还多 → 浅,该加厚(把复杂度吞进去,让接口变窄)。
- 壳层:只做转发/改名/透传的中间层,删了调用方直连也不塌 → 删除测试不通过 = 删。
- 删除测试:假设这模块不存在,调用方要多写多少?几乎不多写 → 它没在挣它的位置。
- 跨热点重复:同一段逻辑在 N 处手抄 → 一个共享工具候选(这是单点扫描看不见的全局赢面,靠合成 leaf 捞)。
- 按 leverage 排序:机会大小 × 热点温度。冷模块的浅不用管——没在付的摩擦不重构(架构的 YAGNI),widen 用
commits不满仓巡。
转述纪律
候选是输入不是结论:dag_deepen 从不改文件、不开 PR。按 leverage 讲给 owner,不替他拍板改哪个;真要动某模块,先 /omd-grill 或 /omd-contract 把方案钉死再走 /omd-execute。
与既有 skill 的边界
/omd-deepen= git 热点架构加深(浅模块去壳加厚 / 收敛复杂度),只出候选不动手。- 不用于:审 diff 找 bug →
/omd-review;删镀金/过度工程 →/omd-slim;把候选钉成方案 →/omd-grill+/omd-contract。
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.
- 12d ago First seen · 38 lines · 91 tokens per session scan A dac60d3350e5
omd-deepen is a skill published in the GitHub repository AbyssCN/oh-my-dag (39 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 863 once invoked, about $0.0005 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.
Other skills, from other repositories
optimization
Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
neuron-debugger
Debug and monitor Neuron AI applications with Inspector APM, event observability, logging, and performance analysis. Use this skill whenever the user mentions debugging, monitoring, observability, performance analysis, tracing, Inspector, or needs to understand why an agent is behaving a certain way. Also trigger for…
code-search
Search a codebase efficiently with ripgrep regular expressions, file globs, and git history search. Use to locate symbols, usages, and definitions instead of reading whole files.
agent-identity
Verify an agent's live address and billing account before sharing a chat link, diagnosing a deploy mismatch, or deciding why two hosts share an identity.
data-fetching
Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, axios, React Query, SWR, error handling, caching strategies, offline support.