菜单
GEODE runtime architecture and repo-shape context. Use for architecture, packaging, release, docs, CI, AgenticLoop, async runtime, and plugin boundary questions.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/mangowhoiscloud/geode --skill geode-context命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | geode-context |
| visibility | public |
| triggers | geode, harness, agent, runtime, release, packaging, docs, plugin, architecture |
| description | GEODE runtime architecture and repo-shape context. Use for architecture, packaging, release, docs, CI, AgenticLoop, async runtime, and plugin boundary questions. |
Version-agnostic runtime context. Use geode version / geode about for the
installed version and runtime facts; never trust numbers remembered from this
skill.
AgenticLoop(while tool_use).core/ — agent loop, tools, MCP, memory, hooks, wiring, CLI, server, gateway.evals/ — Petri audits, benchmarks, seed generation, and GEO measurement.evolve/ — scaffold search and Crucible experiment supervision.site/ is the public Next.js docs/site, not a Python package.evolve -> evals -> core; reverse imports are forbidden.AgenticLoop.arun(), tool aexecute(), async provider clients.core/agent/loop/agent_loop.py is the implementation. DEFAULT_MAX_ROUNDS = 0 means no round cap. Model completion and runtime guard exits are distinct TerminationReason values in core/agent/loop/models.py; a diagnostic or budget exit is not task success.core/agent/sub_agent.py (SubAgentManager) — max depth 1 (no recursion), session-wide cap 15, global Lane concurrency 50 (core/wiring/container.py).core/server/supervised/services.py: run_bash and delegation remain denied; DAEMON desktop control requires explicit gateway.allow_computer_use, while SCHEDULER keeps the desktop denial. The active tool plan and profile can further restrict access.core/agent/system_prompt.py builds the base prompt; core/agent/loop/_context.py composes skill and session context. core/llm/prompt_assembler.py contains shared formatting helpers, not another assembler.PROMPT_CACHE_BOUNDARY is the opening <dynamic_context> tag. Stable instructions precede it; per-turn context stays inside the closed envelope. core/agent/loop/agent_loop.py emits PROMPT_ASSEMBLED after each per-round rebuild.<available_skills> (metadata only); full skill bodies load on demand via the use_skill tool.CHANGELOG.md.ruff check / ruff format --check (core, evals, evolve, tests, scripts), mypy core/ evals/ evolve/, lint-imports, pytest -m "not live", geode version smoke.plugins, geode_product, or
core.self_improving packages. Evaluation and evolution stay explicit outer
consumers of core.Docs 사이트 (`site/` Next.js) 의 본문/JSX/markdown 링크 audit. broken 내부 링크 탐지, build-time copy 인지, 옵트인 HTTP probe. 신규 페이지 추가 / slug 이전 / chapter 삭제 후 회귀 방지. Triggered by "broken link", "404", "docs link", "hyperlink", "링크 점검", "링크 깨짐", "audit links", "link checker" 키워드.
Scope, preregister, execute, audit, normalize, and publish GEODE evaluations with research-question, reproduction, attempt-lineage, trajectory, verifier-receipt, and immutable artifact contracts. Use for benchmark runs or comparisons, eval-artifact and cache-accounting audits, GPT or subscription result normalization, research question or hypothesis framing, retry diagnosis, trajectory publication, DPO or reward-data readiness reviews, and requests involving MCPMark, tau2, BFCL, Agent-World, HAL, Terminal-Bench, or Toolathlon.
GEODE evidence-first development workflow. Use for feature work, provider/model changes, GUI/computer-use work, PDF/document ingestion, observability/schema/event/state changes, verification planning, GitFlow merge prep, and requests to "follow the workflow" or "scaffold the process".