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-delivergit 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-deliver)<a href="https://agentmods.dev/skills/abysscn/oh-my-dag/omd-deliver"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-deliver/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-deliver"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-deliver.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 | $0.00081 | $0.00775 |
| Opus 5 | $0.00041 | $0.00387 |
| Sonnet 5 | $0.00016 | $0.00155 |
| Haiku 4.5 | $0.00008 | $0.00077 |
Grade A, and why
omd-deliver 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-deliver — 显式交付闸
调 omd MCP map_deliver(可能带前缀 mcp__omd__;未加载先 ToolSearch "map_deliver")。多图带 slug。
这是权力闸,不是普通命令
- 只有 owner 明令("交付"、"执行吧"、"/omd-deliver")才调。区域散尽的报信不构成执行授权。
- 闸不上云:deliver 永远在本地由 owner 扣扳机执行,永不由 GitHub issue 事件触发;云端(金丝雀 / Actions)只碰 research 派发,绝不碰交付。gh 后端也一样——改文件的活不上 CI。
- 调用前向 owner 确认交付范围:哪些 ruled task 票、各票 ruling 即节点目标。
- 工具行为:零 LLM 编译 slice(票→DAG 节点,blockedBy→依赖边)→ 跑 executor DAG(agent 叶子带工具真改文件)→ 全节点 done 才把票翻 delivered;有节点失败则不标记、报错、可修复重试。
- 跑几分钟是预期(真 DAG 跑模型),别中途放弃重调。
- 报"未配 leaf 模型" → 让用户设
OMD_ITER_LEAF_MODEL(或OMD_RUNTIME_PROVIDER/OMD_RUNTIME_MODEL),任何 provider 都行。
交付后验收:delivered ✅ ≠ 东西真在(承终裁手册交叉验证)
工具把票翻 delivered 只代表"节点跑完",不代表你要的东西真落到位。转述前逐票核对真身:
- 契约 vs 真身:票说建了端点/函数,去代码里核实真存在(不是只看契约镜像/声明)。
- 复用既有必须验对象:ruling 写"复用 X" → 去 X 真身里逐元素核对确实包含,别整屏扫一眼就签。
- 存储形回归钉:新读面要有断言存储形字段的测试,防 seed 与读法用同一错误形状躲过 oracle。
- 重放幂等:涉及造数时,重放整个 seed 计数应归零/跳过;"新建 N"出现在重放输出 = 幂等撒谎,查库确认行数。
核对后:转述执行摘要 + 建议 owner review git diff,再继续裁下一层前沿。
与既有 skill 的边界
- omd-deliver = pathfinder 增量交付(裁完的散尽区域)。把已有 SDD/plan 整体交 DAG 执行 + 四选一验收 → /omd-execute。
- 只裁决不执行 → /omd-rule(deliver 的前置闸)。
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 · 33 lines · 81 tokens per session scan A cecb89d05242
omd-deliver is a skill published in the GitHub repository AbyssCN/oh-my-dag (39 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 775 once invoked, about $0.0004 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…