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-rulegit 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-rule)<a href="https://agentmods.dev/skills/abysscn/oh-my-dag/omd-rule"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-rule/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-rule"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-rule.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 | $0.00077 | $0.01193 |
| Opus 5 | $0.00039 | $0.00596 |
| Sonnet 5 | $0.00015 | $0.00239 |
| Haiku 4.5 | $0.00008 | $0.00119 |
Grade A, and why
omd-rule 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-rule — 裁决一张票
调 omd MCP map_rule(可能带前缀 mcp__omd__;未加载先 ToolSearch "map_rule"),参数 ticketId + ruling(多图带 slug)。
裁决怎么落地看后端:md 后端写进 docs/plan/pathfinder/<slug>.md 的票 status/ruling;gh 后端写一条 resolution 评论(首行约定 **ruling**: <text>)并 close 对应 issue。两后端语义等价。
裁决成功后工具还把「: <票 title> 裁决 = 」写进 omd 自记忆(omd.pattern fact),供 memory_recall / 会话开场检索复用;这步是增益,写失败只 warn(输出里 ⚠ … memory 是增益)不阻断裁决本身。
纪律:裁决权属于 owner
- 只有 owner 明确表达决定("就用 SQLite"、"按方案 B 来"、"/omd-rule t3 …")才调。你的角色是把口头决定提炼成一句清晰 ruling——task 票的 ruling 会成为将来 slice 节点的执行目标 goal,要写到弱 executor 也能独立完成。
- owner 表达模糊 → 先复述你理解的裁决让其确认,再落。
- 裁决后工具重算前沿回报解锁/散尽。区域散尽只是报信——执行永远等 owner 显式 /omd-deliver,不自作主张接着交付。
写 ruling 前过判定树(承终裁手册)
裁一张 task 票 = 一次终裁。这几件事在 ruling 里先判清,别留给弱执行体乱猜:
1. 真源三层分离(最重要)
「有没有真源」是三个问题,分开答,别混成一个 defer:
| 层 | 问题 | 缺了怎么写 ruling |
|---|---|---|
| 读面 | 契约/端点/字段存在吗 | 缺 → ruling 含「先建读面」 |
| producer | 有东西往里写吗 | 缺 → 照常实装读面,注明 producer 是哪张票的活;不算造假 |
| 数据 | 有样本吗 | 缺 → ruling 含「扩 seed,只用真机制造数」 |
错误做法:因 producer 缺就把票裁成 defer(= 静默砍范围)。
2. 灰态三种合法画法(上游能力物理不存在时)
外部 API / 定时任务 / 凭证链真不存在 → 灰,只三种画法,ruling 指明哪种:
- 无源恒缺席:数据键不出现,前端显 "—"。
- 断链说明卡:禁用态 + 断链图标 + 原因句,零假数据(方案画了假明细也不渲染)。
- 灰常量即真值:管道不存在时状态就是常量,不需要状态端点(端点等上游一起来)。
判别:方案自己画了断链/禁用态 = 灰态确证,不是 defer 借口。
3. 有据偏差(唯一合法的偏离)
实装语义比方案更准时可偏离,条件 = ruling 写明依据一句话。说不清依据 → 照方案做或标 ?。
4. 敏感判定(哪些不能自裁,标 ? 等 owner)
敏感:签核/审批闸、修改/冲销通道、状态机转移与过账、金额/税率派生公式、契约字段语义变更、DB 层不变量迁移、删既有闸。 不敏感(可直接裁):读面聚合、展示派生(排序/格式)、i18n、seed、灰态卡、前端交互态。 判别:错了会污染账面或绕过审计 = 敏感;错了只是显示难看 = 不敏感。
撤销/改判
地图是 docs/plan/pathfinder/<slug>.md 人可编辑 markdown,直接改 status/ruling(未知状态词不丢票,进 unrecognized 分组)。
与既有 skill 的边界
- omd-rule 只裁决(记决定);执行改文件是 /omd-deliver 的权力闸,裁完不自动交付。
- 裁前方案未定 → 先 /omd-grill 审问或 /omd-council 择优;裁不动的敏感项标
?升级 owner。
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 · 57 lines · 77 tokens per session scan A bade234c0317
omd-rule is a skill published in the GitHub repository AbyssCN/oh-my-dag (39 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 1,193 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…