orchestration-patterns
Use when orchestrating a multi-agent or multi-step coding workflow and you need the proven cross-vendor patterns for THIS Windows workspace - the Architect-to-Editor split (an Opus architect emits a typed change-spec, Codex applies it via the mounted codex mcp-server rail, cross-vendor diversity per work-unit), the sandbox ladder (route risky or untrusted exec to WSL2 native, the docker MCP, or a modal_sandbox, because Windows has no native OS-level process sandbox, the constraint that kills a naive local-sandbox build), a Serena-seeded PageRank repo-map (rank the most central symbols by running PageRank over the mounted Serena LSP reference edges, no tree-sitter pipeline and no vector store), Goose-style lead/worker failure-threshold escalation (on N worker failures escalate to the lead for re-decomposition instead of grinding), and a per-edit lint ladder capped at max_reflections=3 (changed-file-only lint, escalate not grind). Triggers include split architect and editor across models, route risky exec to a sandbox, build a repo map without embeddings, cap agent retries, escalate a stuck work-unit, or design the orchestration loop. NOT for wiring the Codex fan-out channel itself (use multi-ai-mingle) or picking among finished candidate patches (use execution-grounded-bon).
- License 许可
- MIT
- 最近更新
- 2026-11-02
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- orchestration-patterns
- description
- Use when orchestrating a multi-agent or multi-step coding workflow and you need the proven cross-vendor patterns for THIS Windows workspace - the Architect-to-Editor split (an Opus architect emits a typed change-spec, Codex applies it via the mounted codex mcp-server rail, cross-vendor diversity per work-unit), the sandbox ladder (route risky or untrusted exec to WSL2 native, the docker MCP, or a modal_sandbox, because Windows has no native OS-level process sandbox, the constraint that kills a naive local-sandbox build), a Serena-seeded PageRank repo-map (rank the most central symbols by running PageRank over the mounted Serena LSP reference edges, no tree-sitter pipeline and no vector store), Goose-style lead/worker failure-threshold escalation (on N worker failures escalate to the lead for re-decomposition instead of grinding), and a per-edit lint ladder capped at max_reflections=3 (changed-file-only lint, escalate not grind). Triggers include split architect and editor across models, route risky exec to a sandbox, build a repo map without embeddings, cap agent retries, escalate a stuck work-unit, or design the orchestration loop. NOT for wiring the Codex fan-out channel itself (use multi-ai-mingle) or picking among finished candidate patches (use execution-grounded-bon).
03 SKILL.md 正文
orchestration-patterns
Five orchestration patterns that ride the already-mounted bus on this Windows 11 machine (codex mcp-server, Serena LSP, the docker + cloud-hub/modal MCPs, WSL2, the smallest-check ladder). They are advisory patterns Claude applies while orchestrating — not a new runtime, not a new gate, not a hook. Every one deliberately re-uses existing infrastructure rather than building a parallel stack (the anti-overfit gate: no 2nd orchestration runtime, no vector/KG memory engine, no tree-sitter chunker, no local sandbox build, no trained router).
When to use
- You are decomposing work into agents / work-units and want the cross-vendor, Windows-correct shape for the loop (who plans, who edits, where risky code runs, how the loop stops grinding).
- You need a repo map / context bundle without embeddings or a tree-sitter pipeline.
- A work-unit is stuck and you must decide "retry vs escalate vs re-decompose".
When NOT to use
- Wiring the Codex fan-out channel or the agent-mail back-channel itself →
multi-ai-mingle. - Choosing among several finished candidate patches →
execution-grounded-bon(execution consensus), not this skill. - Running the smallest test for a diff in isolation →
smallest-check-ladder(this skill only wires its L0 into the per-edit loop).
The bus these ride (no new runtime)
| Pattern | Existing rail it rides | New infra? |
|---|---|---|
| Architect→Editor split | mcp__codex__codex (mounted codex mcp-server) |
none |
Pattern 1 — Architect→Editor split (cross-vendor per work-unit)
Pattern 2 — Sandbox ladder (the Windows constraint that kills the naive build)
Pattern 3 — Serena-seeded PageRank repo-map (no tree-sitter, no vector)
Pattern 4 — Goose-style lead/worker failure-threshold escalation
Pattern 5 — Per-edit lint ladder + reflection cap (max_reflections=3)
Shadow-mode / advisory posture (council C5)
Anti-overfit boundary (what this deliberately does NOT build)
Testing / real proof (how this file was validated)
Evidence
04 同仓库更多 Skills
clarify-requirements
Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.
openmm-md
Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein / protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.
visual-review
Take screenshots of web pages and UI using Playwright for visual review and iteration
status
Diagnostic status report — shows metaswarm installation state, project setup, and potential issues
start
Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work
setup
Interactive project setup — detects your project, configures metaswarm, writes project-local files