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/alleneubank/claude-code/dispatching-parallel-agentsnpx skills add alleneubank/claude-code --skill dispatching-parallel-agentsgit clone --depth 1 https://github.com/alleneubank/claude-codeWhat 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 | $0.00029 | $0.00564 |
| Opus 5 | $0.00015 | $0.00282 |
| Sonnet 5 | $0.00006 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00056 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispatching Parallel Agents
Overview
Use Codex subagents to accelerate sidecar work, not to outsource thinking on the critical path.
Core principle: Keep the next blocking step local. Delegate bounded work that can run in parallel without shared write ownership.
When to Use
Use this skill when:
- There are 2 or more independent questions or implementation slices
- One subtask does not need the result of another
- You can assign clear file or responsibility boundaries
Do not use this skill when:
- The next action is blocked on the delegated result
- Multiple agents would need to edit the same files
- The problem is still too unclear to split safely
Agent Types
explorer: focused codebase questions, read-only analysis, fast context gatheringworker: implementation or fixes with explicit file ownership
Workflow
- Decide the immediate local step first.
- Identify sidecar tasks that are concrete, independent, and useful.
- Give each agent one clear responsibility.
- State file ownership for code changes.
- Continue local work immediately instead of waiting by reflex.
- Integrate results only after reviewing what changed.
Good Delegation Units
- "Inspect how config is loaded in
bin/bin/claude-bootstrapand report the relevant call chain" - "Add tests for
scripts/sync-codex.sh; worker owns new test fixture files only" - "Draft Codex-native replacement text for one skill directory"
Bad Delegation Units
- "Figure out the whole feature"
- "Fix everything failing"
- Two workers editing the same module tree
- Delegating a task and then idling until it returns
Prompt Ingredients
Every spawned agent should get:
- The exact goal
- The reason this subtask matters
- Ownership boundaries
- Constraints
- The output you need back
For workers, explicitly say:
- which files or module they own
- that they are not alone in the codebase
- that they must not revert unrelated changes
Integration Rules
- Prefer a few high-quality agents over many vague ones.
- Do not duplicate delegated work locally.
- Use
waitonly when the result is needed now. - Close finished agents you no longer need.
- Re-run verification after integrating worker output.
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.
- 2d ago First seen · 82 lines · 29 tokens per session scan A 7f1128556a49
dispatching-parallel-agents is a skill published in the GitHub repository alleneubank/claude-code (52 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 564 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
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…