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.
npx agentmods add skills/6bnbn/flowpilot/dispatching-parallel-agentsnpx skills add 6BNBN/FlowPilot --skill dispatching-parallel-agentsgit clone --depth 1 https://github.com/6BNBN/FlowPilotWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00027 | $0.00247 |
| Opus 5 | $0.00014 | $0.00123 |
| Sonnet 5 | $0.00005 | $0.00049 |
| Haiku 4.5 | $0.00003 | $0.00025 |
Grade A, and why
dispatching-parallel-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 3d 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.
What it actually says
Dispatching Parallel Agents
Overview
When you have multiple unrelated failures or investigations, handle them in parallel instead of forcing one agent to juggle everything.
Core principle: one agent per independent problem domain.
When to Use
- Multiple failures with different root causes
- Separate subsystems or files
- No shared write set
- No sequential dependency between the tasks
The Pattern
- Identify the independent domains.
- Give each agent a narrow, self-contained prompt.
- Dispatch them in parallel.
- Review the results and integrate carefully.
Codex CLI Example
ext spawn_agent(role=explorer, task="Investigate agent-tool-abort.test.ts failures") spawn_agent(role=explorer, task="Investigate batch completion behavior failures") spawn_agent(role=explorer, task="Investigate tool approval race conditions")
Common Mistakes
- One prompt that covers unrelated problems
- Missing context or constraints
- Parallel work on overlapping files
- No integration pass after the agents return
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.
- 3d ago First seen · 41 lines · 27 tokens per session scan A 3733091b007a
dispatching-parallel-agents is a skill published in the GitHub repository 6BNBN/FlowPilot (133 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 247 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
coding-agents-farm
To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
agent-orchestration-multi-agent-optimize-v2
Multi-Agent Optimization Toolkit workflow skill. Use this skill when the user needs Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability and the operator should preserve the upstream workflow…
nobrainer-ultra
Use when the owner says nb-ultra, nb-flow, nb-workflow, ultracode, or asks to set up, upgrade, or reconcile a project's agent workflow; or wants one non-trivial task taken from brief requirements through a complete skill-routed plan, guarded autonomous execution, useful multi-session work and final evidence audit.
nobrainer-autoimprove
Use when the owner says nb-autoimprove, deep-autoresearch, code-autoresearch, nobrainer-capture-lesson, or nobrainer-continuous-improvement; asks to improve a skill or prompt; or wants a measurable bounded baseline-variant-evaluation loop instead of one subjective rewrite.
nobrainer-dispatcher
Use when the owner says nb-dispatcher or nobrainer-dispatcher, or when an approved execution map has multiple queued work units that require ready-set selection, dependency-aware ordering, bounded parallel batches, retry scheduling, or routing audited results to the next queued unit; do not use for one coherent task…
nobrainer-writing
Use when the owner says nb-write, nobrainer-writing, nobrainer-style, or nobrainer-human-like, or asks to draft, rewrite, compress, humanize, edit, or review user-facing prose such as a message, comment, document, README, report, summary, email, post, or release note; maximize useful information per word without…