spawn

A command for starting another Claude Code session in a new tmux pane, which is a separate terminal area, with shared context.

In plain words
What is it for?
Use it to run parallel research, hand off an implementation plan, or begin work in another repository.
Why use it?
It lets you delegate work or start fresh when the current session is crowded with context.

Skill for Claude CodeCodex

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/thobustos/openyoko/spawn
Any agent
npx skills add ThoBustos/openyoko --skill spawn
Clone the repo
git clone --depth 1 https://github.com/ThoBustos/openyoko

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,913 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 $0.00000 $0.02913
Opus 5 $0.00000 $0.01456
Sonnet 5 $0.00000 $0.00583
Haiku 4.5 $0.00000 $0.00291

Measured 2d ago against content hash 5a7b789c63e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spawn 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.

.claude/skills/spawn/SKILL.md · 396 lines

How it starts

The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spawn Skill

Spin up a new Claude Code instance in a fresh tmux pane with full context handoff. Use this to delegate work to a parallel session, offload research, or start fresh with a synthesized plan.

Convention:

  • Flow, tmux commands, handoff prompts
  • Repo/vault paths come from arguments, current directory, or config/vault.json (see CLAUDE.md)

Usage

/spawn                          # Interactive - asks for context
/spawn <repo-path>              # Spawn in specific repo
/spawn <repo-path> "<prompt>"   # Spawn with specific initial prompt

Philosophy

Context windows degrade. Fresh sessions are sharp. This skill lets you:

  • Hand off a plan to a fresh instance for execution
  • Spin up parallel research without polluting your main context
  • Delegate a subtask while you continue working
  • Start a new session with synthesized context from current work

The default first action for spawned sessions is review and validate - ensuring no discrepancies in the handed-off plan and enforcing best practices.


Flow

Phase 1: Preflight Checks

Check tmux is running:

if [ -z "$TMUX" ]; then
  echo "ERROR: Not inside a tmux session"
  exit 1
fi

If not in tmux → STOP and tell user: "You must be inside a tmux session to use /spawn. Run tmux first."

Get current window and pane info:

CURRENT_WINDOW=$(tmux display-message -p '#I')
CURRENT_PANE=$(tmux display-message -p '#P')

Phase 2: Gather Context

If no arguments provided, ask:

  1. Target repo path - Where should the new Claude Code run?

    • Default: current working directory ($(pwd))
    • Options: current workspace, vault (from config/vault.json), or another path the user specifies
  2. Initial prompt - What should the new instance do first?

    • Default: "Review the current plan and ensure no discrepancies. Validate approach against best practices before proceeding."
    • Custom: User provides specific instructions
  3. Context to hand off (optional):

    • Current plan/iteration being discussed
    • Key files to read first
    • Specific constraints or decisions made
    • Skills to invoke (e.g., /daily, /scan)

Read the full file on GitHub · 396 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. 2d ago First seen · 396 lines · 0 tokens per session scan A 5a7b789c63e1

Subscribe to this mod's changes

spawn is a skill published in the GitHub repository ThoBustos/openyoko (10 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,913 tokens. 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

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…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

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…

vercel/next.js · 170 tokens