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-executegit 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-execute)<a href="https://agentmods.dev/skills/abysscn/oh-my-dag/omd-execute"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-execute/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-execute"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-execute.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 | $0.00067 | $0.01107 |
| Opus 5 | $0.00034 | $0.00553 |
| Sonnet 5 | $0.00013 | $0.00221 |
| Haiku 4.5 | $0.00007 | $0.00111 |
Grade A, and why
omd-execute 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 8d 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-execute — SDD → DAG → 验收闭环
经 omd MCP 的 run / dag_status / dag_result 三段式工具(可能带 mcp__omd__ 前缀;未加载先 ToolSearch "run")。把契约交引擎执行,再主动按 checklist 验收——不是跑完就算完。
流程
- 取契约:找
docs/plan/下最新 SDD(YYYY-MM-DD-<slug>.md,由/omd-contract落盘);用户直接给了任务文本也行,但大活先/omd-contract。 - 执行:
run传 task = SDD 全文(或任务文本)。conductor 分解成带类型节点的 DAG(agent 叶子改文件、command 叶子跑验证),并发扇出。拿runId后dag_status轮询、dag_result取产物——可能几分钟,耐心轮询,别重复发起。 - 验收(必须主动做,不等 owner 催):先跑下面的交叉验证 checklist,再按成本四选一。
交叉验证 checklist(每次至少跑一遍——「验收」的可执行化)
验收不是「看 DAG 报了 ✅ 就信」。逐条对:
- 契约 vs 真身:SDD 标「后端已有」的端点/函数,抽查代码里真存在——防契约照抄了参照物但没接线。
- 演示/测试数据 vs 既有闸:造数前先问「会被哪个校验误伤」——唯一约束、状态机触发器、append-only、权限/双人闸。
- 写入形 vs 读取形互相印证:两边用同一个错误形状会一起躲过 oracle → 新读面加一条断言存储形字段的回归测试。
- 改契约三处同步:schema + 接口/端点清单 + 验收测试,漏一处 typecheck 不一定抓得到。
- 幂等重放:重跑 seed/迁移,计数必须归零或跳过;「新建 N」在重放里重现 = 幂等标签撒谎,查库对行数。
- 「复用既有」必须验对象:验收表写「✅ 复用 X」时,去 X 的真身逐元素核对确实包含这些行。销号 ✅ ≠ 元素真生效——按验收项逐条指认,不是整屏扫一眼。
- 垂直可验证性:每个 DAG 叶应是端到端可独立验证的用户功能片,不是技术层横切(「只建表」这种叶子跑完也没法单独验)。SDD 若按技术层组织 → conductor 继承横切 DAG、末端才炸 → 重画,让 task 文本按用户功能垂直切(承 /omd-path 垂直切分闸)。
四选一验收
| 结果 | 动作 |
|---|---|
| 接受 | checklist 全过 + SDD 的 GWT 验收点/不变量逐条 pass → 向 owner 报「做了什么 + 为什么」 |
| 重画 | 契约级失败(方向/分解错)→ 带失败要点重 run,task 末尾附 ===== REDRAW FEEDBACK =====\n<要点>,conductor 针对性重分解 |
| 迭代 | 部分收敛、差在收尾 → 交 /omd-iterate 定点收敛 |
| 直接修 | 小缺口 → 自己动手改 + 验证,比再派 DAG 便宜 |
验收后让 owner review 实际 diff。
与既有 skill 的边界
/omd-execute= 把已定的 SDD/plan 交 DAG 执行 + 四选一验收。- 不用于:pathfinder 已散尽区域的增量交付(权力闸)→
/omd-deliver;plan 前把方案审议透 →/omd-grill;fixpoint 反复迭代 →/omd-iterate(它是本 skill 的循环包装);结论落成 SDD →/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.
- 8d ago First seen · 43 lines · 67 tokens per session scan A 5ca3aa1df9d3
omd-execute is a skill published in the GitHub repository AbyssCN/oh-my-dag (39 stars, last pushed 4d ago), licensed MIT. It adds 67 tokens to every session and 1,107 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 2026-08-30.
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.
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…
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…