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-research-deepgit 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-research-deep)<a href="https://agentmods.dev/skills/abysscn/oh-my-dag/omd-research-deep"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-research-deep/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-research-deep"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-research-deep.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 | $0.00117 | $0.00957 |
| Opus 5 | $0.00059 | $0.00478 |
| Sonnet 5 | $0.00023 | $0.00191 |
| Haiku 4.5 | $0.00012 | $0.00096 |
Grade A, and why
omd-research-deep 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 11d 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-research-deep — 终极档深度调研
调 omd MCP dag_research(可能带 mcp__omd__ 前缀;未加载先 ToolSearch "dag_research"),
开 super: true + rounds: 3。管线全在引擎内跑完才返回,引擎计数,不问模型"够了吗":
- 种子作者化(
super开的就是这个)— 模型把问题拆 3-4 个互补角度 query (机制 / 实践 / 反面 / 生态),各自独立检索并入语料。 - council 分解 — conductor 按全部语料 author 领域专家 lens → L×V fanout →
per-lens 判优 → 综合 → judge panel → graft。(
council默认就是开的,不用传。) - 多轮缺口补挖(
rounds,上限 4)— 轮间做 [模型缺口分析 + 确定性 probe: 引用集 − 已抓集 的缺料补抓],无新增即提前停;二轮起 challenger lens 只挖缺口不重答原题。
用法
dag_research(question: "<研究问题>", super: true, rounds: 3)
- 异步返回(spawn detached 子进程):立即回
runId,用dag_status轮询到完成再取报告(真源src/mcp/tools/research.ts的 detached 分支)。 summary进对话;全文在reportPath(lens 冠军 + 逐轮缺口留痕 + 全部语料附录零丢失)。 关键决策必须Read那个文件,别只看 summary。- 转述纪律:结论 + 来源 URL + 哪轮缺口补出了什么;「语料未覆盖」的部分如实说。
- 成本形状:种子×检索 + council + ≤N 轮,比默认档
dag_research贵数倍 ——真要挖透的领域才用。
前置与降级
- 必须有 search provider:
TAVILY_API_KEY/ANYSEARCH_API_KEY/SEARXNG_URL任一。 没有 → 工具响亮拒绝(不会静默降级成"看起来像调研的一段话")。这是有意的: 没有 web 就没有调研。 - 锚点文件 / 显式种子 query 不在 MCP 面上:
--anchor(把已有设计笔记原样送进 groundTruth 之首)和--queries(给死种子、不作者化)只有源码档的bun run scripts/dag-research.ts有。要这两个 → 直接跑脚本(需 omd 源码/包目录), 或把锚点要点写进question正文。
与既有能力的边界
dag_research默认档(不开super)= 单问题综合,便宜得多 —— 大多数调研用它就够。omd_web= 只抓不综合 ·omd_distill= 吃已有料蒸洞察 ·dag-map= codegraph 代码理解。- 轻量单点查证走客户端自带的 web 检索,别为一个事实起这条管线。
- 领域法定源 RAG(会计/法条类)不在此管线。
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.
- 11d ago First seen · 47 lines · 117 tokens per session scan A f8e292788ada
omd-research-deep is a skill published in the GitHub repository AbyssCN/oh-my-dag (39 stars, last pushed 2d ago), licensed MIT. It adds 117 tokens to every session and 957 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.
Other skills, from other repositories
skill-test
Verifies that the skill system is working correctly.
interview-and-create-plan
Before starting a Ralph RLM loop, interview the user to sharpen the goal, stress-test the design, and write an authored PLAN.md (goal, definition of done, milestones, open questions, invariants) that the loop can follow. Use when a user wants to plan, scope, or stress-test work before delegating it to the supervisor /…
setup-opencode-ralph-rlm
Set up Ralph RLM in an existing OpenCode project by installing the package, running the opencode-ralph-rlm setup command, checking generated .opencode config, and verifying the provider/worker loop wiring. Use when a user asks to install, configure, initialize, troubleshoot setup for, or add opencode-ralph-rlm / Ralph…
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.
openalex-database
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly…
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…