Mola-maker/mstack / skills/m-dispatch
m-dispatch
VerifiedFan independent subtasks out to Claude subagents, DSH headless, Codex or Orca; isolate, merge, verify. Use for 分派/并行/开N个agents.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.7 KB |
| references/decisions.md | markdown | 1.1 KB |
| references/dsh-native.md | markdown | 4.9 KB |
| references/harness-commands.md | markdown | 8.7 KB |
| references/model-routing.md | markdown | 7.4 KB |
| references/subtask-prompt-template.md | markdown | 2.2 KB |
| scripts/cluster-diffs.mjs | script | 2.5 KB |
| scripts/cluster-diffs.test.mjs | script | 2.2 KB |
references/decisions.md
View on GitHub# Decisions
- Candidate patches cluster on exact diff text. Near-duplicate clustering was described in the papers and is not what §11 specifies. Newline differences and a git `index <sha>..<sha>` header are ignored so metadata does not split one patch. Any other difference, including whitespace inside a hunk, is a different cluster.
- A strict majority is the leading patch, not a pass. The different-family verifier still sees every candidate. Agreement alone does not prove correctness.
- Own subagents are the default. "Orca when it is on PATH" is narrowed to two cases: another vendor's agent, or a worktree a human will keep using.
- Judge family means a different vendor family (claude, gpt, gemini, deepseek, kimi…), not a different tier of one vendor. Tiers inside Claude were all that pstack's panel varied (research/round3/pstack-craft.md §3.1). If no free family exists, the verdict is marked `same-family` and counts as weaker evidence.
- DSH workflow and teammates cannot take a cwd, so isolated edits go to `subagent` or to a worktree the lead made. The opt-in preset keeps `subagent` on for that reason (dsh/mstack-team/README.md).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |