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-pathgit 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-path)<a href="https://agentmods.dev/skills/abysscn/oh-my-dag/omd-path"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-path/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-path"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-path.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 | $0.01432 |
| Opus 5 | $0.00039 | $0.00716 |
| Sonnet 5 | $0.00015 | $0.00286 |
| Haiku 4.5 | $0.00008 | $0.00143 |
Grade A, and why
omd-path 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/omd-path — pathfinder 决策地图
你在驱动 omd 的 pathfinder 模式(TUI-less,经 omd MCP server 的 map_* 工具;工具名可能带前缀如 mcp__omd__path_map,未加载时先 ToolSearch "map_open")。MCP server 的 cwd 决定作用的 repo。
后端(md / gh)
pathfinder 有两个可选后端,同一套 map_* 工具面语义等价:
- md 后端(默认):地图真相存
docs/plan/pathfinder/<slug>.md(人可读可编辑)。 - gh 后端:票据生命周期迁 GitHub Issues(map =
🧭 [map]issue,票 =[<type>]sub-issue,ruling = resolution 评论 + close),AFK research 上 GitHub Actions。
后端选择由 .omd/pathfinder/config.json 落定({"backend":"gh"|"md"}),由 map_init 写入;缺省或无 GitHub remote → md。
map_init — 两步引导流(开图前先接线后端)
新 repo 首次用 pathfinder 先跑 map_init,它是两步流:
- 报告模式:
map_init(不传backend)→ 返回环境探测报告(git repo / GitHub remote /gh authscope / repo 公私 / Actions / 机器级 key)+ 推荐答案。先把报告转述给 owner。 - 执行模式:owner 确认后
map_init带backend(gh|md)+destination(+ gh 时cloudAfk:public 仓开云端 AFK = 决策历史公开可读,须 owner 明示)→ 建 labels / map issue / caller workflow / secrets / workflow_dispatch 干跑金丝雀 / 落 config。- 缺什么报什么 + 修复命令(如
gh auth refresh -s workflow),照报错补齐再重跑。
- 缺什么报什么 + 修复命令(如
已建好后端的 repo 直接用 map_open,不必再 init。
用法
/omd-path无参 → 调map_open(无 destination)列出所有开放地图。/omd-path <目的地或 slug>→ 调map_open带 destination:已存在则 resume 并显示前沿,否则新建空图。- 用户说"把 research 甩后台/预取" → 调
map_prefetch(research 票进 detached AFK 后台,不阻塞对话;结果在下次map_tickets拉取时自动折回)。
开图后的职责(重要)
- 新图是空的——你的第一件事是和用户把目的地拆成待决问题,用
map_add逐张开票:research:需要检索调研的开放问题(会被 AFK 自动跑,烧钱;宁缺毋滥);grill:需要和 owner 审议对齐的决策;prototype:需要沙盒验证的假设;task:已明确到可施工的项(带executorKind,默认 inproc;改文件的用 agent)。垂直切分闸:task 票按用户功能垂直切(一片端到端自带所需的数据/逻辑/界面,能独立验证),不按技术层横切(「先建表」→「再写后端」→「最后前端」)。横切的盲点是末端才可测、前面错后面全毁(反 happy-path);垂直片则即时验证 + 可并行分发。blockedBy表达依赖:前置票全裁决后此票才进前沿。
- 展示前沿后,主动建议下一步:哪张票该先裁(/omd-rule)、research 是否值得 prefetch。
- 绝不替 owner 裁决(/omd-rule)或触发交付(/omd-deliver)——那是 owner 的显式动作;你可以给推荐裁决词让 owner 确认。
票裁决的三通道带宽路由(任何 grill/task 票通用)
从 grill 外移至此:pathfinder 拥有票生命周期,任何票的裁决都适用,不限审议。
轮次落票 = 跨 session 可续传的前提(gh 后端):裁决态长在票上,不长在会话里。
- 开审先读票:
gh issue view <n> --comments拉全评论 → 已裁轮次直接续,不重问; - 每轮双落:每提一问(推荐+理由+证据)→
gh issue comment追一条### [轮 N] <问题>;owner 若在会话里答 → 摘要也落一条(owner 裁: …)。会话可死,票面永远最新; - 终裁走
map_rule:轮次评论是过程,resolution 是终点(**ruling**:首行),前沿只认后者。
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.
- 10d ago First seen · 62 lines · 77 tokens per session scan A 8c5e71e30041
omd-path 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 1,432 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.
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…