TopologyPlanner
Choose the right Beads collaboration topology. USE WHEN deciding between embedded single-clone, shared-remote clones, per-clone remotes, or server mode for concurrent writers.From its SKILL.md
npx -y skills add mj-deving/pai-skills --skill TopologyPlannerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.4 KB, 266 tokens by cl100k_base, as published. Nobody here has run it
Beads Topology Planner
Use this skill when the question is not "how do I use Beads?" but "which Beads operating shape fits this collaboration model?"
Outcome rule:
- recommend the smallest topology that fits
- make tradeoffs explicit
- give a concrete command sketch, not only theory
Workflow
- Read references/topology-matrix.md.
- Collect only the facts that matter:
- how many active agents or humans write at once
- one clone or multiple clones/worktrees
- whether everyone must see one shared queue
- whether isolated branches/remotes are acceptable
- whether true multi-writer access is required
- If the environment is unclear, run
beads-version-auditfirst. - Produce:
- recommended topology
- why smaller options fail
- minimal command or setup sketch
Default decision bias
- solo or one active writer: embedded single clone
- multiple clones, shared visibility, no true multi-writer need: shared remote
- many agents, low conflict tolerance, no need for one global queue: per-clone remotes
- true concurrent writers to one repo state: server mode
Do not recommend server mode just because it sounds advanced.
What ships with it: 2 files
1.9 KB alongside SKILL.md
agents/
- openai.yaml277 B
references/
- topology-matrix.md1.6 KB
Gives 0 of the 12 instructions most plan spec skills give in 266 tokens
Counted across 1,099 of the 1,860 authors here whose files we hold, read 2026-08-07
- Ask one question at a timein 51 of 1099
- Break plans into vertical slicesin 29 of 1099, across 11 files
- Publish issues in dependency orderin 27 of 1099, across 9 files
- Iterate until user approves the breakdownin 25 of 1099, across 7 files
- Explore the repository to understand the codebase statein 24 of 1099, across 7 files
- Use domain glossary vocabularyin 23 of 1099, across 5 files
- Apply correct triage labels to published issuesin 23 of 1099, across 5 files
- Prefer AFK slices over HITLin 22 of 1099, across 7 files
- Write a specification before writing any codein 22 of 1099, across 14 files
- Write failing tests before implementation codein 22 of 1099, across 20 files
- Ask clarifying questions until requirements are concretein 21 of 1099, across 13 files
- Respect existing architecture decision recordsin 20 of 1099, across 5 files
Said here and by no other author read
- recommend the smallest fitting topology
- make tradeoffs explicit
- provide a concrete command sketch
- collect concurrency and visibility requirements
- run beads-version-audit if the environment is unclear
- explain why smaller topology options fail
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.