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-resumegit 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-resume)<a href="https://agentmods.dev/skills/abysscn/oh-my-dag/omd-resume"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-resume/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-resume"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-resume.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 | $0.00097 | $0.00849 |
| Opus 5 | $0.00048 | $0.00425 |
| Sonnet 5 | $0.00019 | $0.00170 |
| Haiku 4.5 | $0.00010 | $0.00085 |
Grade A, and why
omd-resume 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-resume — 挑一个断掉的图接着跑
调 omd MCP server 的 dag_runs + dag_resume 工具(可能带前缀 mcp__omd__;未加载先 ToolSearch "dag_runs,dag_resume")。UX 三步:列 → 问 → 续。
1 · 列出可续跑的 run
调 dag_runs(不带 status 过滤——要同时抓到两类可续的:内存里 failed 的,和进程/server 死后磁盘里 unknown(restart) 的「合笔记本」型)。从返回里筛出可续的:status 是 failed 或 unknown/restart 的。
- 一个都没有 → 转告「没有断掉/失败的图可续」,结束。
- 有 → 每条列:goal(任务文字)· 什么时候(createdAt)· 短 runId。goal 是给 owner 认图的关键,必须列。
2 · 问 owner 续哪个(别自动挑)
用 AskUserQuestion 让 owner 选:
- 多个可续 → 每个一个选项,label = goal 前 ~40 字,description = 时间 + runId + 状态。加一个「都不续」。
- 恰好一个 → 仍确认一次(「续这个吗:?」),别默认就跑——续跑会真派车队烧钱。
续跑只接 failed / 未知(重启后)的 run,在飞或已 done 的 dag_resume 会拒——所以列表只放可续的,不给 owner 选到会被拒的。
3 · 续跑
owner 选定 → 调 dag_resume runId=<选中的>。引擎从 .omd/continuity/<runId>/_dag.json 重载 plan,按产物 hash 逐节点判「还算数吗」,只补跑不算数的(已绿的跳过)。返回 runId + status: running → 转告 owner,并说可 dag_status 轮询进度、dag_result 取产物。
边界与诚实
- 只有 plan-memory 改动之后建的 run 能一键续。老 run 只存了骨架 →
dag_resume会报「skeleton only」,转告 owner:那份得手供 plan 走dag_run_plan resume=<runId>(骨架能跳过已绿节点,但重放不出完整 plan)。 run(LLM 现规划)建的图续跑未必省事:重跑 conductor 可能吐出形态不同的图 → 图代数签名变 → 旧 checkpoint 全作废、整图重跑。最干净的续跑对象是dag_run_plan/ pathfinder slice 建的图(plan 确定性、可重放)。dag_resume 走的正是「重载存下来的那份 plan」,所以它对这两类最有效。- 产物守卫:某已绿节点的产出文件被删/改过 → hash 对不上 → 那个节点也会重跑(不信一个产物已经不在的「done」)。这是正确性,不是 bug。
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 · 35 lines · 97 tokens per session scan A 63b9dd3d1700
omd-resume is a skill published in the GitHub repository AbyssCN/oh-my-dag (39 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 849 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
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…