Vspawn
vlinx-io/VelaTerm
Explicitly spawn a standalone child session under the current vlx-term session, passing the task in as its first message (mirrors spawntask).
Fan out work to parallel sub-agents with worktree isolation.
Install Spawn
$ npx skills add koolamusic/claudefiles --skill spawn -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install koolamusic/claudefiles spawn --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/koolamusic/claudefiles.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/spawn .claude/skills/spawn && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "spawn" agent skill from https://github.com/koolamusic/claudefiles/tree/main/skills/spawn into .claude/skills/spawn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spawn", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/koolamusic/claudefiles/tree/main/skills/spawnType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add koolamusic/claudefiles --skill spawn -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install koolamusic/claudefiles spawn --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/koolamusic/claudefiles.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/spawn .agents/skills/spawn && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "spawn" agent skill from https://github.com/koolamusic/claudefiles/tree/main/skills/spawn into .agents/skills/spawn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spawn", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add koolamusic/claudefiles --skill spawn -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install koolamusic/claudefiles spawn --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/koolamusic/claudefiles.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/spawn .cursor/skills/spawn && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "spawn" agent skill from https://github.com/koolamusic/claudefiles/tree/main/skills/spawn into .cursor/skills/spawn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spawn", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/koolamusic/claudefiles.git --path skills/spawn--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add koolamusic/claudefiles --skill spawn -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install koolamusic/claudefiles spawn --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/koolamusic/claudefiles.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/spawn .gemini/skills/spawn && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "spawn" agent skill from https://github.com/koolamusic/claudefiles/tree/main/skills/spawn into .gemini/skills/spawn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spawn", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install koolamusic/claudefiles spawnInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add koolamusic/claudefiles --skill spawn -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/koolamusic/claudefiles.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/spawn .github/skills/spawn && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "spawn" agent skill from https://github.com/koolamusic/claudefiles/tree/main/skills/spawn into .github/skills/spawn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spawn", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add koolamusic/claudefiles --skill spawn -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install koolamusic/claudefiles spawn --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/koolamusic/claudefiles.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/spawn .opencode/skills/spawn && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "spawn" agent skill from https://github.com/koolamusic/claudefiles/tree/main/skills/spawn into .opencode/skills/spawn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spawn", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
spawn- GitHub stars
- 130
- Token cost
- ~1.4k tokens
- SKILL.md length
- 545 words
- Files
- 1
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- MIT
At a glance
Fan out work to parallel sub-agents with worktree isolation.
- Works in 5 steps: Parse scope into units → Build the wave map → Present the dispatch plan → …
- User says spawn
- SKILL.md covers Input, Process, Hard rules and Integration with jira, plus 1 more section
- Calls git
What it does
Spawn is an agent skill from koolamusic/claudefiles. Fan out work to parallel sub-agents with worktree isolation. Reads a plan, scope list, or inline description, breaks it into waves of independently-dispatchable units, and orchestrates execution. The orchestrator never implements — it coordinates. Use when user says 'spawn', 'fan out', 'parallelize this', 'orchestrate', or has multiple independent tasks to dispatch.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Subagents and Git worktrees. The repository describes itself as: A minimal catalog of my favourite skills for working with claude. The licence is MIT.
When your agent uses it
- User says spawn
- Parallelize this
- Has multiple independent tasks to dispatch
Example prompts
- “fan out”
- “parallelize this”
- “orchestrate”
- “/spawn”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 297c432. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Spawn loads about 1.4k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 545 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from koolamusic/claudefiles at commit 297c432, republished under its MIT licence (© koolamusic). 545 words, ~1,389 tokens.
Download SKILL.mdSave it as
.claude/skills/spawn/SKILL.md (or your agent's skills folder).- name
- spawn
- description
- Fan out work to parallel sub-agents with worktree isolation. Reads a plan, scope list, or inline description, breaks it into waves of independently-dispatchable units, and orchestrates execution. The orchestrator never implements — it coordinates. Use when user says 'spawn', 'fan out', 'parallelize this', 'orchestrate', or has multiple independent tasks to dispatch.
- argument-hint
- <plan path, scope description, or 'auto' to read active sprint>
Spawn
Dispatch parallel sub-agents with isolation guarantees. You are the orchestrator — you coordinate, delegate, track, and integrate. You never write application code yourself.
Input
$ARGUMENTS is one of:
- A file path — read it as the scope document (PLAN.md, HANDOFF.md, a GitHub issue, any structured doc)
- Inline text — treat it as the scope description directly
auto— look for.jira/CURRENTand read the active sprint's plans. If no sprint, check.project/ROADMAP.mdfor the next unstarted phase. If neither exists, ask.- Empty — ask via
AskUserQuestionwhat work to dispatch
Process
1. Parse scope into units
Read the input and decompose into spawn units — independently executable chunks of work. Each unit must have:
- ID — short label (A, B, C or descriptive slug)
- Objective — one sentence: what this agent delivers
- Inputs — files to read, context to pass
- Outputs — files to create/modify, commits expected
- Depends on — other unit IDs that must complete first (empty = wave 1)
2. Build the wave map
Group units into waves by dependency:
Wave 1: [A, B, C] — no dependencies, run in parallel
Wave 2: [D] — depends on A
Wave 3: [E, F] — depends on DUnits within a wave touch disjoint files. If two units in the same wave would modify the same file, split the wave or merge the units.
3. Present the dispatch plan
Show the user:
## Dispatch Plan
**Total units:** N across W waves
**Isolation:** worktree / same-tree (recommend worktree if >1 unit per wave)
| ID | Wave | Objective | Depends on | Est. complexity |
|---|---|---|---|---|
| A | 1 | ... | — | small |
| B | 1 | ... | — | medium |
| C | 2 | ... | A | small |
Proceed?Wait for explicit approval. The user may reorder, merge, split, or cancel units.
4. Execute wave-by-wave
For each wave in order:
a. Spawn agents in parallel. Single message, one Agent tool call per unit in the wave. Each agent gets:
You are sub-agent <ID> in a spawn dispatch.
## Your objective
<objective>
## Context
<brief from scope doc + any outputs from prior waves>
## Files you own
<list of files this agent may create/modify — no others>
## Constraints
- Commit your work with a descriptive message
- Do NOT push to remote
- Do NOT open PRs
- Do NOT modify files outside your scope
- If blocked, commit what you have and report the blockerIsolation decision:
- If wave has >1 unit: use
isolation: "worktree"on each Agent call - If wave has 1 unit: foreground without worktree (simpler)
- User can override in the dispatch plan approval step
b. Collect results. When all agents in the wave return:
- Read each agent's reported status
- Run
git log --oneline -5(or per-worktree equivalent) to verify commits landed - If any agent reports a blocker: surface it via
AskUserQuestion— retry, skip, or abort - If any agent's worktree has changes: note the worktree branch for integration
c. Integrate worktree results (if using worktrees):
- For each completed worktree agent, cherry-pick or merge its commits onto the working branch
- Resolve conflicts if any — surface to user if non-trivial
- Verify the integrated state compiles / passes basic checks
Show full SKILL.md (187 more words)Show less
5. Report
When all waves complete:
## Spawn Complete
**Units dispatched:** N
**Waves executed:** W
**Status:**
| ID | Status | Commits | Notes |
|---|---|---|---|
| A | complete | abc1234 | — |
| B | complete | def5678 | — |
| C | blocked | — | <blocker description> |
**Integration:** all cherry-picked onto <branch>
**Next step:** <recommendation — run tests, open PR, continue with next spawn>Hard rules
- You are the orchestrator. Never write application code, tests, or configuration yourself. Your job is dispatch, tracking, and integration.
- Wave-safe parallelism. Never dispatch two agents that modify the same file in the same wave.
- Foreground parallel, not background. Use multiple Agent calls in a single message for within-wave parallelism. Background agents have worktree isolation issues.
- Never force-push. If integration has conflicts, surface and ask.
- Never auto-merge PRs. Open them, report them, stop.
- Git state verification after every wave. Don't trust agent self-reports alone — check
git logandgit status. - User approval before dispatch. Always show the dispatch plan and wait for "go."
Integration with jira
When invoked by jira:execute or with auto argument in a jira-managed repo:
- Read wave structure from
*-PLAN.mdfrontmatter (plans already havewave:fields) - Pass CONTEXT.md (locked decisions) to every agent
- Write integration results to EXECUTION.md (append-only)
- Don't duplicate jira:execute's Nyquist/verifier gates — those run after spawn returns
Integration with studio
If .workspacerc exists, resolve all .jira/ and .project/ paths through the workspace. Worktree agents don't get symlinks automatically — pass resolved absolute paths in agent prompts.
© koolamusic, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/spawn of koolamusic/claudefiles.
Open the folder on GitHubat commit 297c432
Compare with similar skills
Spawn next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Spawn this skillkoolamusic/claudefiles | 130 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Vspawnvlinx-io/VelaTerm | 270 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Spec-Driven Development v2LichAmnesia/lich-skills | 234 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Subagent Coordinatorflyxl/datazen | 114 | — | ~908 | Automated safety check: Pass | GPL-3.0 | |
| PmApra-Labs/apra-fleet | 101 | — | ~5.4k | Automated safety check: Pass | Custom licence | |
| Batch Orchestrationrohitg00/pro-workflow | 2.9k | — | ~1.2k | Automated safety check: Pass | None |
Similar skills
Spec-Driven Development v2
LichAmnesia/lich-skills
Organizes long-running agent work into a Project, Sprint and Task hierarchy with per-task state files, isolated worktrees, review loops and script-checked rules.
Subagent Coordinator
flyxl/datazen
Orchestrate multi-track parallel feature development with subagents and git worktrees.
Pm
Apra-Labs/apra-fleet
Project Manager skill. An agent skill from Apra-Labs/apra-fleet.
Batch Orchestration
rohitg00/pro-workflow
Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees.
Codex CLI
kortix-ai/suna
Drive OpenAI's Codex CLI (codex exec) as a non-interactive coding sub-agent from inside Claude Code.
More from koolamusic/claudefiles
All 13 skills in this repoExplainer Formats
koolamusic/claudefiles
A skill your agent uses when asked to explain a topic, codebase, process, or document in a specific output format — plain language or Simplified Technical English (STE, in the style of ASD-STE100…
Breadboarding
koolamusic/claudefiles
Transform a workflow description into affordance tables showing UI and Code affordances with their wiring.
Orchestrator
koolamusic/claudefiles
Turn the current session into a chief-of-staff thread that runs a war room of three role slots — surveyor, executor, auditor — and routes per-branch work to durable, reusable child agents.
Retro
koolamusic/claudefiles
A skill your agent uses when a user completes a phase, sprint, milestone, or meaningful unit of work and needs a retrospective.
Skill Creator
koolamusic/claudefiles
Guide for creating effective skills. An agent skill from koolamusic/claudefiles.
Debug
koolamusic/claudefiles
A skill your agent uses when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework with built-in backward tracing for deep-stack failures…
Related
Categories
Questions about Spawn
What does Spawn do?
Fan out work to parallel sub-agents with worktree isolation. Spawn is an agent skill from koolamusic/claudefiles. Fan out work to parallel sub-agents with worktree isolation.
When should I use Spawn?
Spawn fits situations like: user says spawn; parallelize this; has multiple independent tasks to dispatch.
How do I install Spawn in Claude Code?
Run `npx skills add koolamusic/claudefiles --skill spawn -a claude-code`. Or copy the skill folder (skills/spawn in koolamusic/claudefiles) into .claude/skills/spawn in your project. Claude Code loads it when a task matches its description.
How do I install Spawn in Codex?
Run `npx skills add koolamusic/claudefiles --skill spawn -a codex`. Or copy the skill folder (skills/spawn in koolamusic/claudefiles) into .agents/skills/spawn in your project. Codex loads it when a task matches its description.
Can I use Spawn in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add koolamusic/claudefiles --skill spawn -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spawn, .gemini/skills/spawn, .github/skills/spawn and .opencode/skills/spawn in your project.
What does Spawn need to run?
Going by SKILL.md and its folder, Spawn needs the command-line tools its instructions call (git).
Does Spawn access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Spawn safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Spawn use?
Spawn is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Spawn use?
About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Spawn?
Skills that share tags, products or a category with Spawn: Vspawn (vlinx-io/VelaTerm, 270 stars), Spec-Driven Development v2 (LichAmnesia/lich-skills, 234 stars), Subagent Coordinator (flyxl/datazen, 114 stars) and Pm (Apra-Labs/apra-fleet, 101 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Spawn?
koolamusic (a GitHub user) maintains it in koolamusic/claudefiles, which has 130 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 5, 2026.
Source: koolamusic/claudefiles on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.