spawn-session

spawn-session is a skill for Claude Code, Codex from gtapps/claude-code-hermit. It costs 57 tokens per session (1,454 once invoked), scanned A, original, MIT.

A command for starting a Claude Code helper in the background, using a separate Git worktree—a separate checkout of the project. It watches for the helper to become idle and passes its report back.

In plain words
What is it for?
Use it to delegate a coding task or another skill to a background helper, optionally choosing its name, model, effort level, or remote control.
Why use it?
It lets another coding session work without taking over the current checkout. The separate worktree keeps its file changes apart from the main session.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the claude-code-hermit plugin — 31 skills, 4 agents shipped together

Good fit Use it to delegate a coding task or another skill to a background helper, optionally choosing its name, model, effort level, or remote control.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gtapps/claude-code-hermit/spawn-session
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 gtapps/claude-code-hermit --skill spawn-session
Clone the repo
git clone --depth 1 https://github.com/gtapps/claude-code-hermit

Made for: Claude Code, Codex.

Or install claude-code-hermit, the plugin that ships this one along with the rest of its 31 skills, 4 agents.

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 spawn-session

README.md
[![agentmods](https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/spawn-session/github.svg)](https://agentmods.dev/skills/gtapps/claude-code-hermit/spawn-session)
Your own site
<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/spawn-session"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/spawn-session/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 spawn-session

Your own site · 80×15
<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/spawn-session"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/spawn-session.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,454 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.
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 $0.00057 $0.01454
Opus 5 $0.00028 $0.00727
Sonnet 5 $0.00011 $0.00291
Haiku 4.5 $0.00006 $0.00145

Measured today against content hash d22c47ea3592, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

spawn-session 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 today.

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.

plugins/claude-code-hermit/skills/spawn-session/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spawn Session

Launch a background Claude Code session in its own git worktree, subscribe to its idle notice, and relay the report through /claude-code-hermit:watch.

Usage

/claude-code-hermit:spawn-session <prompt-or-/skill> [--name <n>] [--model <m>] [--effort <e>]

From <abs>, the project root, that composes:

claude --bg --worktree <n> --name <n> [--permission-mode <p>] [--remote-control <n>] [--model <m>] [--effort <e>] '<prompt>'

--remote-control <n> is present when config.json's remote is true and absent otherwise; --model and --effort only when the operator passed them. Four limits sit on that command:

  • The helper's worktree .claude-code-hermit/ is a projection (OPERATOR.md, config.json, compiled/ only). Any file the helper must Read is passed as an absolute path in the prompt.
  • A worktree carries no .claude/settings.local.json (it is gitignored, so nothing checks it out), so the helper inherits none of this hermit's permission rules. --permission-mode <p> from config.json's permission_mode is what keeps it in this session's permission class, which is also what lets its idle notice reach here rather than being held for an operator who is not watching. config.json accepts one value the CLI has no choice for, default, so it and null and an absent key all mean: leave the flag off entirely and let the helper take the box default. scripts/hermit-start.ts resolves the same value the same way; match it rather than inventing a second answer. Every other value passes through unchanged, bypassPermissions included.
  • The prompt is one single-quoted argument. An apostrophe in it ends the quote, so replace every ' with '\'' before composing. Anything after the closing quote is a second command the operator never asked for.
  • The launch is not pre-approved, and what the operator sees depends on the mode they run in. On auto, the shipped default, the classifier decides and no prompt reaches them on any channel. On acceptEdits or manual the native approval is relayed to their DM and is allow-once, so every spawn asks again. On bypassPermissions there is none. Say what is about to be spawned before running it either way: it is the only thing that makes the launch legible when an approval does arrive, and the only record when none does.

Read the full file on GitHub · 99 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. today Changed · +9 lines d22c47ea3592
  2. 2d ago First seen · 90 lines · 57 tokens per session scan A e124dd5f9d72

Subscribe to this mod's changes

spawn-session is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,454 once invoked, about $0.0003 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 2026-09-07.

Related

Other skills, from other repositories

github-pr-creation

Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…

fvadicamo/dev-agent-skills · 75 tokens

github-pr-merge

Merges GitHub Pull Requests after validating pre-merge checklist. Use when user wants to merge PR, close PR, finalize PR, complete merge, approve and merge, or execute merge. Runs pre-merge validation (tests, lint, CI, comments), confirms with user, merges with proper format, handles post-merge cleanup.

fvadicamo/dev-agent-skills · 72 tokens

git-commit

Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.

fvadicamo/dev-agent-skills · 49 tokens

update-architecture-atlas

Create or refresh a versioned Curie architecture-atlas JSON snapshot from a git diff, including current and vision flows, maturity-rated seams, ADRs, and documentation drift. Use when asked to update, regenerate, compare, or add a version to the interactive architecture atlas.

curie-eng/curie · 61 tokens

ccc-upgrade

Audit and update vendor submodules. Lists every submodule under vendor/, fetches latest, reports per-submodule current/latest commits and changed file counts, prompts…

KevinZai/commander · 36 tokens

ccc-rollback

CC Commander rollback workflow. Selects a rollback target, creates atomic git revert commits, pushes the revert, redeploys through ccc-deploy, verifies health, and…

KevinZai/commander · 39 tokens