multiask

multiask is a skill for Claude Code, Codex from ao92265/claude-code-playbook. It costs 103 tokens per session (688 once invoked), scanned A, original, MIT.

A service that sends a question to several installed AI coding tools and has the answers reviewed for weaknesses. It is designed for cases where a wrong answer could have serious consequences.

In plain words
What is it for?
Use it explicitly with /multiask or for the listed high-stakes coding situations. It is not meant to run automatically for ordinary questions.
Why use it?
It provides independent checks for decisions involving security, production incidents, high-traffic systems, database migrations, or breaking API changes. This can expose disagreements or risks a single answer misses.

Skill for Claude CodeCodex

Part of the playbook plugin — 49 skills, 4 hooks shipped together

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.

agentmods
npx agentmods add skills/ao92265/claude-code-playbook/multiask
Any agent
npx skills add ao92265/claude-code-playbook --skill multiask
Clone the repo
git clone --depth 1 https://github.com/ao92265/claude-code-playbook

Made for: Claude Code, Codex.

Or install playbook, the plugin that ships this one along with the rest of its 49 skills, 4 hooks.

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 multiask

README.md
[![agentmods](https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/multiask.svg)](https://agentmods.dev/skills/ao92265/claude-code-playbook/multiask)
Your own site
<a href="https://agentmods.dev/skills/ao92265/claude-code-playbook/multiask"><img src="https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/multiask.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 688 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00103 $0.00688
Opus 5 $0.00051 $0.00344
Sonnet 5 $0.00021 $0.00138
Haiku 4.5 $0.00010 $0.00069

Measured 3d ago against content hash f09c1175e444, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multiask 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.

skills/multiask/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/multiask — Parallel multi-CLI fan-out with adversarial review

Runs act fanout to dispatch the user's prompt across every installed AI coding CLI in parallel, then runs a Claude-driven review gate on the outputs.

Backend: agent-control-tower at /path/to/agent-control-tower/. CLI entrypoint: act fanout <prompt> [flags]. Playbook: /path/to/your-project/docs/guides/MULTIASK_PLAYBOOK.md.

When you fire this skill

  1. First, decide whether auto-triggering is actually warranted using the strict rules in the description. If the question is not clearly in categories (a)-(d), DO NOT fire — just answer directly or invoke /ask for a single provider.

  2. If firing, announce it briefly BEFORE running so the user can interrupt:

    "This looks security-critical — firing /multiask --adversarial to cross-check. ~1 min and ~1M tokens. Say 'skip' to cancel." Then run act fanout.

  3. Default to --review adversarial when auto-triggering. The whole point of auto-trigger is high-stakes questions where inferior answers cost you.

How to invoke

Use the Bash tool to run:

act fanout "<user's prompt>" --review adversarial

Optional flags:

  • --runtimes claude,codex,gemini,copilot,kiro-cli — explicit subset
  • --timeout 5 — per-runtime timeout (default 10m)
  • -C <path> — working directory (default cwd)

The command prints the verdict.md path on exit. Read it with the Read tool and present it inline to the user. If the command exits non-zero, show stderr and stop.

Known limitations

  • Claude runtime often REJECTs in its own host session due to SessionStart hook noise. If you see claude REJECT with "hook noise" reason, that's expected, not a bug.
  • Copilot uses the standalone copilot CLI with --allow-all-tools, not gh copilot. Requires gh auth login once for GitHub auth underneath.
  • See the playbook for full troubleshooting and observed timings.

When NOT to fire

If you are at all unsure, do one of:

  • Invoke /ask <provider> for a single-provider answer (one-tenth the cost)
  • Answer directly from your own reasoning
  • Ask the user "do you want me to cross-check with /multiask?"

Read the full file on GitHub · 62 lines

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. 3d ago First seen · 62 lines · 103 tokens per session scan A f09c1175e444

Subscribe to this mod's changes

multiask is a skill published in the GitHub repository ao92265/claude-code-playbook (10 stars, last pushed 17d ago), licensed MIT. It adds 103 tokens to every session and 688 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens