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/nicograef/handbook/dispatching-parallel-agentsnpx skills add nicograef/handbook --skill dispatching-parallel-agentsgit clone --depth 1 https://github.com/nicograef/handbookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nicograef/handbook/dispatching-parallel-agents)<a href="https://agentmods.dev/skills/nicograef/handbook/dispatching-parallel-agents"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/dispatching-parallel-agents.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00055 | $0.01062 |
| Opus 5 | $0.00028 | $0.00531 |
| Sonnet 5 | $0.00011 | $0.00212 |
| Haiku 4.5 | $0.00006 | $0.00106 |
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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispatching Parallel Agents
Adapted from the MIT-licensed superpowers plugin.
- Cost — delegating to isolated subagents costs roughly 15× the tokens of a chat interaction, about 4× a single agent pass.
- Reserve for — genuinely independent, each-substantial work.
- Do it yourself — two small related fixes.
Workflow
- Check independence first. Group the failures or tasks by root cause.
- Two items are independent only if neither shares a file/region with the other.
- Independence also requires that fixing one has no chance of fixing the other.
- Related items — investigate together instead; don't force a split.
- Write one focused prompt per domain (the four-part delegation contract). Each prompt
must include:
- Scope — specific: one file, one subsystem, one bug; not "fix everything".
- Context — self-contained: paste the actual error messages, test names and stack traces.
- Never a summary of them.
- Tools and sources — name the tools and source files each agent should use.
- Repo rules — restate the rules that apply; anything they must obey has to be in the prompt.
- Subagents see none of this session's history.
- Explore/Plan-style agents don't load CLAUDE.md.
- Constraints — explicit, including file ownership, so no two agents write the same file.
- Examples: "only modify files under
src/agents/", "fix tests only, don't touch production code". - Return format — state it exactly, per the report shape.
- Dispatch all of them in the same response so they run in parallel.
- Then keep dispatching. Act on each result as it lands, not after the slowest one.
- Waiting for the set before starting anything is a barrier you rarely need.
- A barrier is earned only when the next step reads across all results.
- That means dedup, a total count, or a comparison between findings.
- Your own reading and thinking belongs inside someone else's runtime.
- Read every summary as it returns, then check for collisions.
- Diff or grep to confirm no two agents touched the same file or region.
- Resolve any overlap by hand before trusting either result.
- Integrate and verify as a whole. Run the full test suite or build after merging all
results.
- Passing in isolation doesn't guarantee passing together.
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.
- today Changed · +8 lines 65cf5fa2c9d5
- 4d ago First seen · 75 lines · 55 tokens per session scan A 92dd3ee85cd3
dispatching-parallel-agents is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,062 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…