Borrowing it
Nothing to install: this file belongs to 0xlicy/antigravity-brain-bridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/0xlicy/antigravity-brain-bridge/main/.agents/skills/parallel-delegation/SKILL.mdgit clone --depth 1 https://github.com/0xlicy/antigravity-brain-bridgeWrote 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/0xlicy/antigravity-brain-bridge/parallel-delegation)<a href="https://agentmods.dev/skills/0xlicy/antigravity-brain-bridge/parallel-delegation"><img src="https://agentmods.dev/badge/skills/0xlicy/antigravity-brain-bridge/parallel-delegation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/0xlicy/antigravity-brain-bridge/parallel-delegation"><img src="https://agentmods.dev/badge/skills/0xlicy/antigravity-brain-bridge/parallel-delegation.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00026 | $0.01343 |
| Opus 5 | $0.00013 | $0.00672 |
| Sonnet 5 | $0.00005 | $0.00269 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
Parallel Task Delegation 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 9d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Task Delegation
When working on complex tasks that involve multiple independent parts, you can dramatically speed up execution by delegating independent sub-tasks to child conversations using the Brain Bridge MCP tools.
When to Delegate
✅ DELEGATE when:
- The current task has 2+ independent sub-tasks that don't depend on each other's output
- A sub-task is self-contained (has clear input, clear expected output)
- A sub-task would take many steps to complete (e.g., writing tests, refactoring a module, code analysis)
- You're working on multiple files/modules that don't share state
❌ DON'T DELEGATE when:
- Sub-tasks are tightly coupled (Task B needs Task A's output)
- The task is simple enough to complete in a few steps
- The task requires extensive back-and-forth with the user
- The task modifies the same files (would cause merge conflicts)
Workflow: Recursive Decompose + Result Merge
Phase 1 — Analyze & Decompose
Before starting work, analyze the task and identify parallelizable parts:
User: "Add authentication to the API, write tests, and update the docs"
Think:
- Task A: Implement auth middleware → depends on nothing
- Task B: Write auth tests → depends on Task A's interface, but can stub it
- Task C: Update docs → independent
→ Task A: do myself (core work, needs user interaction)
→ Task B: delegate (self-contained, clear spec)
→ Task C: delegate (independent)
Phase 2 — Delegate Sub-Tasks
Use the delegate_task MCP tool with clear, specific instructions:
delegate_task(
task: "Write comprehensive tests for the auth middleware in /src/auth/.
Test files should go in /src/auth/__tests__/.
Cover: login, logout, token refresh, invalid tokens, expired tokens.
Use the existing test framework (jest) and patterns from /src/users/__tests__/.",
cwd: "/path/to/project"
)
Tips for good delegation:
- Be specific about what to do and where
- Mention the tech stack and existing patterns to follow
- Specify the output location (where to write files)
- Include context the child conversation needs (the child starts with zero context)
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.
- 9d ago First seen · 156 lines · 26 tokens per session scan A 63be56ea4706
Parallel Task Delegation is a skill published in the GitHub repository 0xlicy/antigravity-brain-bridge (1 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 1,343 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…