multitask

multitask is a skill for Claude Code, Codex from GCWing/BitFun. It costs 43 tokens per session (391 once invoked), scanned A, original, MIT.

A workflow for splitting a large task into independent workstreams and assigning them to agents that can work at the same time. The results are later checked and combined.

In plain words
What is it for?
It is for parallel research, implementation branches, and other decomposable tasks.
Why use it?
It reduces waiting when parts of a task do not depend on one another, while keeping shared decisions and final verification coordinated.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit It is for parallel research, implementation branches, and other decomposable tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gcwing/bitfun/multitask
About the project

BitFun is a desktop AI agent that turns tasks into interactive mini-apps while also writing code, creating documents, and controlling computers. It is for software development and general desktop work across Windows, macOS, and Linux. Its catalogue entries extend the agent with skills, agents, and instructions.

GCWing/BitFun · 2,077 stars · on GitHub

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.

Any agent
npx skills add GCWing/BitFun --skill multitask
Clone the repo
git clone --depth 1 https://github.com/GCWing/BitFun

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for multitask

README.md
[![agentmods](https://agentmods.dev/badge/skills/gcwing/bitfun/multitask/github.svg)](https://agentmods.dev/skills/gcwing/bitfun/multitask)
Your own site
<a href="https://agentmods.dev/skills/gcwing/bitfun/multitask"><img src="https://agentmods.dev/badge/skills/gcwing/bitfun/multitask/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.

agentmods 80×15 button for multitask

Your own site · 80×15
<a href="https://agentmods.dev/skills/gcwing/bitfun/multitask"><img src="https://agentmods.dev/badge/skills/gcwing/bitfun/multitask.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 391 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00043 $0.00391
Opus 5 $0.00022 $0.00196
Sonnet 5 $0.00009 $0.00078
Haiku 4.5 $0.00004 $0.00039

Measured 4d ago against content hash d208246df62f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

multitask 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 4d 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.

src/crates/assembly/core/builtin_skills/multitask/SKILL.md · 25 lines

What it actually says

Multitask

Work parallel-first when the task has genuinely independent branches.

Workflow

  1. Identify the dependency graph before implementation. Separate shared contract decisions and blocking prerequisites from branches that can proceed independently.
  2. If at least two useful branches are independent, keep coordination and the critical path local, then delegate one or more other branches to background subagents. If the work is sequential or delegation overhead outweighs the benefit, continue locally.
  3. Give each subagent a non-overlapping scope, expected output, ownership boundary, and focused verification responsibility. State what must remain unverified when a branch depends on in-flight shared state.
  4. Continue independent local work while delegated branches run. Wait for results only when the critical path needs them.
  5. Review the returned work at its interfaces, resolve mismatches, integrate the branches, and run final verification against the combined result.

Rules

  • Use the available Task delegation interface with background execution for real parallel work, and use the corresponding wait interface when results are needed. Do not assume a particular subagent exists; choose only from the available catalog.
  • Keep shared contracts, dependency decisions, overlapping edits, destructive actions, final integration, and final verification under the main Agent's control.
  • Batched or concurrent-looking file edits by the main Agent are not independent execution. Do not claim parallelism unless separate subagents actually ran concurrently.
  • Respect the user's authorization boundaries and repository instructions in every delegated scope. This skill does not authorize extra writes, external actions, worktrees, servers, or UI interaction.
  • Do not create subagent work merely to satisfy the workflow. Each delegated branch must have a concrete deliverable that can progress without blocking another branch.
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. 4d ago First seen · 25 lines · 43 tokens per session scan A d208246df62f

Subscribe to this mod's changes

multitask is a skill published in the GitHub repository GCWing/BitFun (2,077 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 391 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 2026-09-06.

Related

Other skills, from other repositories

memstack-automation-n8n-workflow-builder

Use this skill when the user says 'n8n workflow', 'build a workflow', 'automation workflow', 'connect services', or needs visual workflow design with node mapping, data transformations, and error handling for n8n. Do NOT use for standalone webhook endpoints or cron jobs.

cwinvestments/memstack · 68 tokens

memstack-automation-cron-scheduler

Use this skill when the user says 'cron job', 'scheduled task', 'run every', 'cron expression', 'recurring job', or needs production-grade scheduled jobs with overlap prevention, monitoring, and structured logging. Do NOT use for n8n workflows or event-driven webhooks.

cwinvestments/memstack · 67 tokens

daily-standup-journal

Generate concise daily standups, reflection prompts, and weekly retrospectives for individuals or teams. Use for planning a day, surfacing blockers, reviewing user-provided entries, or drafting a check-in without assuming prior history.

iflytek/skillhub · 51 tokens

task-coordination

Coordinate access to shared task directories using .processing marker files. Use before accessing a Worker's workspace to prevent conflicts when both Manager and Worker might modify files simultaneously.

agentscope-ai/AgentTeams · 36 tokens

mcporter

Discover and call MCP Server tools via the mcporter CLI. Use when your coordinator notifies you about new MCP tools, or when you need to call external APIs. Includes workflow for generating skill documentation for new MCP servers.

agentscope-ai/AgentTeams · 47 tokens

task-management

Use before any Worker taskflow call or assigned-task workflow, including reading task state, acknowledging a task, executing a task, tracking progress, handling blockers/questions, submitting structured results, or reporting completion. Always use this skill when the message mentions assigned task, task ID…

agentscope-ai/AgentTeams · 89 tokens