dispatching-parallel-agents
Use when parallel workers have a net benefit over coordinated sequential work.
Skill by BB-84C
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/bb-84c-dispatching-parallel-agents
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/dispatching-parallel-agents
What's inside
- Skill name
dispatching-parallel-agents- Description
- Use when parallel workers have a net benefit over coordinated sequential work.
- License
- MIT
- Instructions
- 14 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Dispatching Parallel Agents Choose parallel work from independence, cost, coordination, and harness safety. Dispatch only when the net benefit exceeds added integration and recovery cost. Group related work when splitting it would create more reconciliation than insight. Give each worker a bounded contract, ownership boundary, and expected evidence. Avoid shared mutable targets unless the harness coordinates them safely. After workers return, verify the real impact boundary: shared interfaces, persisted state, user-visible behavior, and integration points their reports could miss. Isolated green results are not integration evidence by themselves.
From BB-84C/superpowers-lite, MIT.
More from BB-84C/superpowers-lite
- 0.499score
using-superpowers
BB-84C
Consult directly matching task playbooks before substantial design, debugging, implementation, review, or completion work without forcing full workflow…
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
subagent-driven-development
BB-84C
Consult before delegating implementation when an approved plan benefits from worker context isolation and durable coordination.
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
writing-skills
BB-84C
Use when creating, revising, validating, or deploying a reusable agent skill.
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
brainstorming
BB-84C
Use for genuinely open, load-bearing product or architecture decisions after inspecting the project.
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
using-git-worktrees
BB-84C
Use when isolation may materially improve feature work; preserve existing isolation and repository preferences.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
systematic-debugging
BB-84C
Consult before attempting a fix when root cause or behavior is unclear, failures repeat, components interact, or guessing would be unsafe.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
executing-plans
BB-84C
Use when a written plan needs coordinated inline execution.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
requesting-code-review
BB-84C
Use independent review at meaningful semantic or risk boundaries and before substantive whole-change closeout.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
finishing-a-development-branch
BB-84C
Use when a real branch, integration, or discard decision needs an authorized closeout.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
verification-before-completion
BB-84C
Consult before making a substantive completion claim; require current trustworthy evidence and semantic acceptance.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
writing-plans
BB-84C
Consult when multi-round implementation, context compaction, or worker handoff requires a durable execution contract.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
receiving-code-review
BB-84C
Consult after receiving review feedback and before implementation when the feedback needs evidence-based evaluation.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Jul 12, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/BB-84C/superpowers-lite
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from BB-84C
- 0.499score
subagent-driven-development
BB-84C
Consult before delegating implementation when an approved plan benefits from worker context isolation and durable coordination.
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
using-superpowers
BB-84C
Consult directly matching task playbooks before substantial design, debugging, implementation, review, or completion work without forcing full workflow…
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
using-git-worktrees
BB-84C
Use when isolation may materially improve feature work; preserve existing isolation and repository preferences.
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
writing-skills
BB-84C
Use when creating, revising, validating, or deploying a reusable agent skill.
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
brainstorming
BB-84C
Use for genuinely open, load-bearing product or architecture decisions after inspecting the project.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
systematic-debugging
BB-84C
Consult before attempting a fix when root cause or behavior is unclear, failures repeat, components interact, or guessing would be unsafe.
SkillCFreshness: C★ 1Claude Code +9
Cite this page
dispatching-parallel-agents skill. Agent Mart. https://agentmart.dev/skills/bb-84c-dispatching-parallel-agents (last updated 2026-10-24)