Dispatching parallel agents
Skill kimtth/agent-skill-100-lines-or-less/skills/dispatching-parallel-agents
🧿 Minimal but effective AI agent skill definitions in 100 lines or less.
npx -y skills add kimtth/agent-skill-100-lines-or-less --skill dispatching-parallel-agentsAssembled 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.
- 2 stars2 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.
What its author says it does
Copied from the file, not written here
Use when: multiple independent coding, debugging, or research tasks can be investigated in parallel.
SKILL.md
1.2 KB, 209 tokens by cl100k_base, as published. Nobody here has run it
Goal: split independent work into isolated agent investigations without losing coordination.
Use for:
- unrelated failing tests across subsystems
- several candidate root causes that do not share state
- broad codebase research where results can be merged later
- independent issue slices after a plan is approved
Do not use for:
- one bug with shared root cause
- tasks that edit the same files concurrently
- work requiring a single global design decision
Workflow:
- Group tasks by independent problem domain.
- Write each subtask with exact scope, files, commands, and output format.
- Give each agent only the context it needs.
- Ask for evidence, not just conclusions.
- Merge results, resolve conflicts, and choose next action.
Output:
- task split: domain | reason independent | assigned prompt
- returned findings: evidence | recommendation | risk
- integration decision
Rules:
- one agent per independent domain
- never let agents edit the same file in parallel
- keep main session responsible for final integration
Gives 1 of the 12 instructions most agent orchestration skills give in 209 tokens
Counted across 742 of the 995 authors here whose files we hold, read 2026-08-06
- run the full test suite after integrating changesin 53 of 742, across 20 files
- reference existing artifacts by path or URLin 52 of 742, across 22 files
- dispatch one agent per independent problem domainhere, and in 50 of 742, across 17 files
- verify fixes do not conflictin 45 of 742, across 13 files
- include a suggested skills section in the documentin 45 of 742, across 15 files
- redact sensitive informationin 41 of 742, across 11 files
- save to the temporary directory of the operating systemin 39 of 742, across 9 files
- tailor the document to user-provided focus argumentsin 39 of 742, across 9 files
- spot check agent changes for systematic errorsin 34 of 742, across 7 files
- write a handoff document summarising the current conversationin 31 of 742, across 6 files
- assign each agent a specific scopein 23 of 742, across 8 files
- provide specific scope and clear goalin 23 of 742, across 5 files
Said here and by no other author read
- ask for evidence not conclusions
- merge results and choose next action
- keep main session responsible for integration
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.