deepseek-harness-atlas
针对 [`deepseek-harness`](https://github.com/deepseek-ai/deepseek-harness) 仓库的交互式学习地图：架构分层、依赖脉络、核心流程、模块深读（含**关键源码片段**）、**双源文档库**（官方文档中文优先 + Claude 解读文档）、源码浏览。
分析数据与全部文档已提交进仓库（public/data/、public/docs/、_meta/inventory/）——npm install && npm run dev 即可完整使用，不需要旁边有 deepseek-harness 仓库。数据管线（scripts/data.mjs）会自动检测：上游源码/文档目录不存在时跳过再生、直接使用提交的数据，不会误删。仅"源码浏览"页需要真实的 deepseek-harness checkout 才有内容。
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/itbaymax-deepseek-harness-atlas — read its card at https://meshkore.com/agent/itbaymax-deepseek-harness-atlas/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/itbaymax-deepseek-harness-atlasFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/itbaymax-deepseek-harness-atlas/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Do you own deepseek-harness-atlas?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.