omd-contract

omd-contract is a skill for Claude Code, Codex from AbyssCN/oh-my-dag. It costs 105 tokens per session (6,649 once invoked), scanned A, original, MIT.

A guide for turning a debated technical decision into a formal software design contract saved in a project document. The contract records decisions, requirements, work breakdown, exclusions, and unresolved questions.

In plain words
What is it for?
Use it after agreeing on a design to record acceptance checks, dependencies, parallel work, non-goals, evidence, and issues that still need an owner or test.
Why use it?
It gives an implementer a clear source of truth even when they were not part of the earlier discussion.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after agreeing on a design to record acceptance checks, dependencies, parallel work, non-goals, evidence, and issues that still need an owner or test.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/abysscn/oh-my-dag/omd-contract
Install

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.

Any agent
npx skills add AbyssCN/oh-my-dag --skill omd-contract
Clone the repo
git clone --depth 1 https://github.com/AbyssCN/oh-my-dag

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for omd-contract

README.md
[![agentmods](https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-contract/github.svg)](https://agentmods.dev/skills/abysscn/oh-my-dag/omd-contract)
Your own site
<a href="https://agentmods.dev/skills/abysscn/oh-my-dag/omd-contract"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-contract/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.

agentmods 80×15 button for omd-contract

Your own site · 80×15
<a href="https://agentmods.dev/skills/abysscn/oh-my-dag/omd-contract"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-contract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,649 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 187
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00105 $0.06649
Opus 5 $0.00053 $0.03325
Sonnet 5 $0.00021 $0.01330
Haiku 4.5 $0.00011 $0.00665

Measured yesterday against content hash dafb640845d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

omd-contract 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 yesterday.

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.

client-skills/omd-contract/SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/omd-contract — 审议结晶成执行契约

审议(/omd-grill、pathfinder 裁决)收敛后,把结论写成结构化 SDD 落盘——它是 /omd-execute 的执行契约,写给没有对话上下文的执行器,不是给人读的散文。

承接 /omd-grill 的决策记录表

# 决策 定论 落点(/omd-note · pathfinder 票 · SDD 章节) 证据

落点标「SDD 章节」的行 → 进「决策」与「契约」段;标 /omd-note 的留台账;标 pathfinder 票的附票 id 进「未决」段。「待 owner / 待实测」项原样进「未决」,不写成结论。

落盘

路径:docs/plan/YYYY-MM-DD-<slug>.md。每段可被无上下文执行器独立消费:

# <标题>
## 目标 (Destination)   一句话讲清做成什么样
## 决策 (Decisions)     D-1..D-N:每条已定型裁决 + 一句为什么 + 证据
## 契约 (Contracts)     不变量 + GWT 验收点——/omd-execute 逐条判 pass/fail 的依据
## 分解 (Breakdown)     依赖图 + 并行波形(写法见下)
## 非目标 (Non-goals)   明确不做什么
## 未决 (Open)          未裁的问题;附 pathfinder 票 id;待实测的标「待实测」

GWT 验收点越可证伪,验收越不含糊;一个模糊验收点 = 执行器和你各自解读的裂缝。

分解段 —— 默认并行,串行必须给理由

  • 只写真实依赖边,每条带理由:「B 依赖 A 因 <B 消费 A 的产物 X>」——且 X 必须出现在 A 的写集清单里(机器可锚)。写不出被消费产物的边,删——那是顺序偏好,不是依赖。
  • 接口依赖就地消解:B 只需要 A 的类型/签名/schema 而非实装 → 把该接口冻进本 SDD(契约段),边删掉,两片并行。接口从此是契约的一部分:A 的实装必须符合它,偏离 = 回流改契约,不是恢复边。(实例:内环 v2 切片 2 只消费切片 1 的 SddSlice 结构——冻进 SDD 即可并行,当时没冻,白等一层。)
  • 定稿前过一遍并行性审问:串行率(关键路径长 ÷ 切片数,编译器 parallelismReadout 同口径)= 1 的链,逐边重跑上面两问再定稿;审完仍是真串行就如实保留——读数只点名,不否决诚实的线性分解。
  • 切片表:| 切片 | 写集 | 依赖(带理由) | verify |。写集两两不相交 = 可并行的机器判据。
  • verify 列必须是可跑命令串(如 bun test src/x.test.ts),不是验收点引用——G 点引用的家在契约段。编译器(sdd-compile)按首词白名单拒不可跑的 verify;写引用 = 这份 SDD 吃不到直通 v2,回落 conductor 铺图税(owner 2026-08-11 裁:直通就是为了消铺图税与墙钟)。全量回归命令不进 verify 列(它只属终局 accept,D-4)。
  • 收尾写并行波形一行,conductor 照铺:并行波形:{1,3,5} → {2} → {4}。全串行波形须给整体理由,默认视为写错。
  • 优先序(哪片价值高)写波形注释或 Open 段,不进依赖边。

⚠ 分解表的四条机器硬要求(写错 = 点火当场拒 / 静默回落,而它只在点火那一刻才响)

真源 src/harness/goal/sdd-direct.ts + sdd-compile.ts。2026-08-18 量过全量语料: 149 份 plan 文档、52 份有分解段,只有 14 份吃得下 sddPath 直通 —— 而直通是夜批的默认路径。 73% 的失败全部来自下面四条,一条都没写进过本模板:

  1. 切片列必须裸数字开头 —— | 1 span 计算 …。写 S1 / **S1 …** / Phase 一律拒 (sdd-direct.ts/^(\d+)/;编号是波形/依赖引用它的唯一方式)。
  2. 波形行独占一行 —— WAVE_LINE 锚行首。写成「写集两两不相交 ✓。并行波形:…」会被 静默忽略(不报错,图退回按依赖边排;2026-08-18 实测)。
  3. 写集只收相对路径,且不许留空 —— 写「无」/「dispatch」这类词会被拒;空写集直接拒 (写集是并行安全的机器判据)。
  4. verify 列要过 #251 判据自证的三条 lint —— 真源 src/harness/goal/ignition-criteria-check.ts,点火期接线在 goal.ts:1153这是六道点火闸里唯一没有 force 出口的一道:给了出口就等于放虚判据进图, 而虚判据让整跑判不出真假(实账 run 85a18995 零改动 4 分钟假 done; bca0a0c7bun test 多 filter 静默忽略缺失,二次假 done)。三条逐条写:

Read the full file on GitHub · 289 lines

Changes

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.

  1. yesterday Changed · +93 lines dafb640845d6
  2. 10d ago First seen · 196 lines · 105 tokens per session scan A fae086a5d6f4

Subscribe to this mod's changes

omd-contract is a skill published in the GitHub repository AbyssCN/oh-my-dag (39 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 6,649 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.

Related

Other skills, from other repositories

skill-test

Verifies that the skill system is working correctly.

andrefetch/postal · 13 tokens

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 /…

doeixd/opencode-ralph-rlm · 89 tokens

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…

doeixd/opencode-ralph-rlm · 89 tokens

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.

synthetic-sciences/openscience · 47 tokens

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…

synthetic-sciences/openscience · 86 tokens

pysam

Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.

synthetic-sciences/openscience · 47 tokens