New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Dispatch Agents

by danielvm-git in danielvm-git/bigpowers

Dispatch multiple subagents in parallel on independent tasks.

MITAuto-check passedAgent Workflows

Install Dispatch Agents

skills CLI
$ npx skills add danielvm-git/bigpowers --skill dispatch-agents -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install danielvm-git/bigpowers dispatch-agents --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/danielvm-git/bigpowers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/dispatch-agents .claude/skills/dispatch-agents && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
dispatch-agents
GitHub stars
256
Token cost
~1.3k tokens
SKILL.md length
576 words
Files
1
Skills in repo
39
Repo updated
First seen
Licence
MIT

At a glance

Dispatch multiple subagents in parallel on independent tasks.

  • Works in 6 steps: Confirm independence → Write typed task briefs (Orca message… → Circuit breaker + iterative retrieval… → …
  • Tasks are truly decoupled and speed matters
  • SKILL.md covers When to use, When NOT to use, Process and Subagent depth tiers (e45s30), plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Dispatch Agents is an agent skill from danielvm-git/bigpowers. Dispatch multiple subagents in parallel on independent tasks. No waiting between them — all run concurrently. Use when tasks are truly decoupled and speed matters. Distinct from delegate-task (concurrent here, no inter-task review gate).

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Subagents and Human-in-the-loop approvals. The repository describes itself as: Agent skills synthesizing years of software engineering discipline into a prescriptive methodology for solo developers. The licence is MIT.

When your agent uses it

  • Tasks are truly decoupled and speed matters
  • Tasks that involve Subagents
  • Tasks that involve Human-in-the-loop approvals

Example prompts

  • “/dispatch-agents”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Confirm independence
  2. Write typed task briefs (Orca message protocol)
  3. Circuit breaker + iterative retrieval (max 3 cycles)
  4. Dispatch in parallel
  5. Collect and review results
  6. Integrate

What it can do on your machine

Read from SKILL.md and the folder at commit 812d57a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dispatch Agents loads about 1.3k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 576 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from danielvm-git/bigpowers at commit 812d57a, republished under its MIT licence (© danielvm-git). 576 words, ~1,289 tokens.

Download SKILL.mdSave it as .claude/skills/dispatch-agents/SKILL.md (or your agent's skills folder).
name
dispatch-agents
description
Dispatch multiple subagents in parallel on independent tasks. No waiting between them — all run concurrently. Use when tasks are truly decoupled and speed matters. Distinct from delegate-task (concurrent here, no inter-task review gate).
model
sonnet
effort
standard

story: e09s04

story: e45s38

<!-- story: e45s11 -->

story: e45s30

Dispatch Agents

HARD GATE — HARD GATE — Agent work must be parallelizable and have explicit synchronization points. Do NOT dispatch work that has hidden dependencies between agents.

Run multiple subagents in parallel on independent tasks. Use when tasks are genuinely decoupled — no agent needs the output of another to start.

Distinct from delegate-task: This skill maximizes throughput via concurrency. There is no sequential review gate between tasks. Use delegate-task instead when a single task needs careful two-stage oversight before proceeding.

When to use

  • Tasks that can run simultaneously without shared state
  • Large plans that can be broken into parallel workstreams
  • Exploration: gather information from multiple parts of the codebase at once

When NOT to use

  • Task B depends on Task A's output
  • You need to review Task A before Task B can start safely
  • The tasks share a file and concurrent edits would conflict

Process

1. Confirm independence

Before dispatching, verify each task pair is truly independent:

  • No shared files being written
  • No shared state (DB migrations, config files)
  • No ordering dependency between outcomes

If any two tasks conflict, sequence them with delegate-task or execute-plan instead.

Subagent depth tiers (e45s30)

Map effort: frontmatter and story risk: to prompt depth — do not send minimal_decisive agents a full_maturity brief.

TierWhenBrief shapeToken budget
full_maturityeffort: heavy, risk: P0, security-sensitive diffsFull task_brief + CONVENTIONS excerpts + threat model if presentFull envelope
standardeffort: standard, risk: P1–P2Standard task_brief fields belowDefault
minimal_decisiveeffort: light, risk: P3, read-only explorationgoal + verify + in_scope only≤15 lines

Record depth: <tier> in the Agent tool description when dispatching.

2. Write typed task briefs (Orca message protocol)

Before writing briefs, read specs/state.yaml if it exists — each agent gets only the decisions relevant to its task, nothing else.

Every inter-agent message uses a typed envelope — no freeform prose between waves:

typeWhenRequired fields
task_briefDispatchtask_id, goal, in_scope, out_of_bounds, verify, prior_decisions
checkpointMid-wave progresstask_id, status (running|blocked), comment (one line)
resultAgent returntask_id, exit (pass|fail), summary, verify_output
circuit_open3 consecutive failurestask_id, failures (3), escalate_to (user)

Example task_brief (each agent starts cold — brief size directly controls token cost and hallucination risk):

yaml
type: task_brief
task_id: agent-1
goal: [one sentence — what success looks like]
in_scope: [explicit file or module list]
out_of_bounds: [what NOT to touch]
verify: [runnable command]
prior_decisions: [relevant entries from specs/state.yaml — omit if none]

Emit checkpoint comments when an agent is slow or blocked — one line, no stack traces. Parent reads checkpoints before spawning follow-ups.

Do not include the full conversation, full file contents, or decisions unrelated to this agent's task.

Show full SKILL.md (178 more words)Show less
3. Circuit breaker + iterative retrieval (max 3 cycles)

Track consecutive failures per task_id. On the 3rd consecutive result.exit: fail for the same task, emit type: circuit_open and stop dispatching that task — escalate to user with the three failure summaries. Reset counter on any pass.

After each wave completes:

  1. Dispatch — run parallel agents with typed task_brief envelopes.
  2. Evaluate — read result messages; list gaps vs goal; honor open circuits.
  3. Refine — tighten briefs or spawn follow-up agents (max 3 cycles total).

Stop when gaps empty, circuit opens, or cycle 3 reached — escalate to user. If agents go silent without returning, invoke diagnose-stall before spawning another wave.

4. Dispatch in parallel

Spawn all agents in a single message using multiple Agent tool calls. Each agent gets its own complete brief.

Agent 1: brief for task A
Agent 2: brief for task B
Agent 3: brief for task C
5. Collect and review results

When all agents return: review each result, run verify commands, check diffs for scope violations.

6. Integrate

Merge accepted results. Resolve conflicts manually; note in summary.

Report: which tasks succeeded, which need revision, overall verify status.

Verify

→ verify: test -f skills/dispatch-agents/SKILL.md && test -f scripts/lib/completeness-critic.sh

© danielvm-git, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/dispatch-agents of danielvm-git/bigpowers.

Open the folder on GitHubat commit 812d57a

Compare with similar skills

Dispatch Agents next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Dispatch Agents compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dispatch Agents this skilldanielvm-git/bigpowers256—~1.3kAutomated safety check: PassMIT
Cline Pilotsickn33/agentic-awesome-skills47k1 repos~4.6kAutomated safety check: PassMIT
Kode Permissions DebuggingshareAI-lab/Kode-CLI5.2k—~498Automated safety check: PassApache-2.0
Gemini CLI DelegationCherryHQ/cherry-studio52k—~334Automated safety check: PassAGPL-3.0
GitHub Copilot CLI DelegationCherryHQ/cherry-studio52k—~365Automated safety check: PassAGPL-3.0
Hermes Agent One-Shot DelegationCherryHQ/cherry-studio52k—~390Automated safety check: PassAGPL-3.0

Similar skills

  • Cline Pilot

    sickn33/agentic-awesome-skills

    Acts as a proxy for the Cline CLI, dispatching coding tasks one at a time, monitoring runs by hard evidence, relaying decisions to you and learning per-project preferences.

    47k GitHub starsUsed in 1 repo~4.6k tokens
    Agent WorkflowsAuto-check passed

  • Kode Permissions Debugging

    shareAI-lab/Kode-CLI

    Troubleshoots Kode permission prompts and denials, including allowlists, command-level tool limits, dontAsk mode and subagent inheritance, without loosening permissions.

    5.2k GitHub stars~498 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Gemini CLI Delegation

    CherryHQ/cherry-studio

    Runs Gemini CLI once in headless JSON mode for repository analysis or coding work, keeping its approvals read-only unless you ask for changes.

    52k GitHub stars~334 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • GitHub Copilot CLI Delegation

    CherryHQ/cherry-studio

    Runs GitHub Copilot CLI non-interactively on a repository task and reads its JSONL output, denying tools by default so nothing changes unless you ask.

    52k GitHub stars~365 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Hermes Agent One-Shot Delegation

    CherryHQ/cherry-studio

    Runs Hermes Agent once for a bounded local task, with warnings about its automatic tool approval and advice to use a disposable copy for read-only work.

    52k GitHub stars~390 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • MiniMax Code Delegation

    CherryHQ/cherry-studio

    Sends a bounded task to MiniMax Code with mcode exec, passing the smart permission mode for analysis and never the full one.

    52k GitHub stars~357 tokensUpdated today
    Agent WorkflowsAuto-check passed

More from danielvm-git/bigpowers

All 39 skills in this repo

  • Extract Design

    danielvm-git/bigpowers

    Extract a Google DESIGN.md file from an HTML prototype (claude.ai/design or any styled page) using Puppeteer, producing machine-readable tokens and AI-generated prose.

    256 GitHub stars~1k tokensUpdated 16 days ago
    Auto-check passed

  • Align Grid

    danielvm-git/bigpowers

    Build editorial/magazine/report webpages on a GENUINE Müller-Brockmann modular grid (International Typographic Style) — not a decorative one.

    256 GitHub stars~3k tokensUpdated 16 days ago
    Auto-check passed

  • Assess Impact

    danielvm-git/bigpowers

    Analyze the blast radius of a proposed change before any code is written.

    256 GitHub stars~766 tokensUpdated 16 days ago
    Auto-check passed

  • Audit Code

    danielvm-git/bigpowers

    Self-review checklist for the coding agent to run before dispatching a reviewer.

    256 GitHub stars~1.6k tokensUpdated 16 days ago
    Auto-check: notes

  • Audit Plan

    danielvm-git/bigpowers

    Evaluate an incoming project plan against bigpowers principles and conventions, surface gaps, and produce a READY/NOT READY verdict before engagement begins.

    256 GitHub stars~880 tokensUpdated 16 days ago
    Auto-check passed

  • Compose Workflow

    danielvm-git/bigpowers

    Chain multiple bigpowers skills into a custom workflow recipe saved in specs/.

    256 GitHub stars~723 tokensUpdated 16 days ago
    Auto-check passed

Categories

Questions about Dispatch Agents

What does Dispatch Agents do?

Dispatch multiple subagents in parallel on independent tasks. Dispatch Agents is an agent skill from danielvm-git/bigpowers. Dispatch multiple subagents in parallel on independent tasks.

When should I use Dispatch Agents?

Dispatch Agents fits situations like: tasks are truly decoupled and speed matters; tasks that involve Subagents; tasks that involve Human-in-the-loop approvals.

How do I install Dispatch Agents in Claude Code?

Run `npx skills add danielvm-git/bigpowers --skill dispatch-agents -a claude-code`. Or copy the skill folder (skills/dispatch-agents in danielvm-git/bigpowers) into .claude/skills/dispatch-agents in your project. Claude Code loads it when a task matches its description.

How do I install Dispatch Agents in Codex?

Run `npx skills add danielvm-git/bigpowers --skill dispatch-agents -a codex`. Or copy the skill folder (skills/dispatch-agents in danielvm-git/bigpowers) into .agents/skills/dispatch-agents in your project. Codex loads it when a task matches its description.

Can I use Dispatch Agents in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add danielvm-git/bigpowers --skill dispatch-agents -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dispatch-agents, .gemini/skills/dispatch-agents, .github/skills/dispatch-agents and .opencode/skills/dispatch-agents in your project.

What does Dispatch Agents need to run?

SKILL.md names no scripts, command-line tools or credentials: Dispatch Agents is instructions for the agent only.

Does Dispatch Agents access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Dispatch Agents safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Dispatch Agents use?

Dispatch Agents is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dispatch Agents use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Dispatch Agents?

Skills that share tags, products or a category with Dispatch Agents: Cline Pilot (sickn33/agentic-awesome-skills, 47k stars), Kode Permissions Debugging (shareAI-lab/Kode-CLI, 5.2k stars), Gemini CLI Delegation (CherryHQ/cherry-studio, 52k stars) and GitHub Copilot CLI Delegation (CherryHQ/cherry-studio, 52k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dispatch Agents?

danielvm-git (a GitHub user) maintains it in danielvm-git/bigpowers, which has 256 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on September 21, 2026.

Source: danielvm-git/bigpowers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.