dispatch-multiple-agents

A workflow for sending two or more independent tasks to separate agents at the same time. It is intended for work that does not share files or depend on results from another task.

In plain words
What is it for?
Splitting independent research or implementation tasks, reviewing the agents' results, and integrating their findings.
Why use it?
Parallel work can reduce waiting time when tasks are separate and can be safely combined afterward.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/s3yed/appie-kit/dispatch-multiple-agents
Any agent
npx skills add S3YED/appie-kit --skill dispatch-multiple-agents
Clone the repo
git clone --depth 1 https://github.com/S3YED/appie-kit

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 413 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.00413
Opus 5 $0.00016 $0.00206
Sonnet 5 $0.00007 $0.00083
Haiku 4.5 $0.00003 $0.00041

Measured 2d ago against content hash e2de84b7faa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dispatch-multiple-agents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/automation/dispatch-multiple-agents/SKILL.md · 76 lines

What it actually says

Dispatch Multiple Agents

When you have multiple independent tasks, don't do them sequentially. Dispatch agents to work in parallel.

When to Use

Use when:

  • 3+ independent tasks need attention
  • Tasks don't share state or resources
  • No dependencies between tasks
  • Speed matters

Don't use when:

  • Tasks are related (fixing one might fix others)
  • Tasks share files/resources (would conflict)
  • You need full system context for all tasks
  • Tasks must happen in specific order

The Pattern

1. Identify Independent Domains

Group work by what's needed:

  • Task A: Research competitor A
  • Task B: Research competitor B
  • Task C: Research competitor C

Each is independent.

2. Create Focused Tasks

Each subagent gets:

  • Specific scope: One clear task
  • All context needed: Don't make them hunt
  • Clear output: What should they return?
  • Constraints: What NOT to touch

3. Dispatch in Parallel

Using sessions_spawn for concurrent execution.

4. Review and Integrate

When agents return:

  • Read each result
  • Verify no conflicts
  • Integrate findings
  • Report summary

Integration with Other Skills

Use dispatch-multiple-agents WITHIN the workflow:

brainstorming → write-plan → dispatch-multiple-agents → verify-task
                                   ↓
                            doing-tasks (per subagent)

Example

Problem: Research 5 competitors

Dispatch:

  • Agent 1 → Competitor A
  • Agent 2 → Competitor B
  • Agent 3 → Competitor C
  • Agent 4 → Competitor D
  • Agent 5 → Competitor E

Result: Full analysis in minutes, not hours.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 76 lines · 33 tokens per session scan A e2de84b7faa9

Subscribe to this mod's changes

dispatch-multiple-agents is a skill published in the GitHub repository S3YED/appie-kit (6 stars, last pushed 6d ago), licensed MIT. It adds 33 tokens to every session and 413 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.