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.
npx agentmods add commands/emasoft/ghe-marketplace/spawn-agentgit clone --depth 1 https://github.com/Emasoft/ghe-marketplaceWrote 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.
[](https://agentmods.dev/commands/emasoft/ghe-marketplace/spawn-agent)<a href="https://agentmods.dev/commands/emasoft/ghe-marketplace/spawn-agent"><img src="https://agentmods.dev/badge/commands/emasoft/ghe-marketplace/spawn-agent.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.00423 |
| Opus 5 | $0.00008 | $0.00211 |
| Sonnet 5 | $0.00003 | $0.00085 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade C, and why
spawn-agent scanned grade C with 1 finding 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| Bash (sudo, rm -rf /) | DENY | What it actually says
GHE Background Agent Spawner
Spawn a Claude agent in a background Terminal window. The agent works autonomously while you continue chatting.
Task
Task: $ARGUMENTS.task Output: ${ARGUMENTS.output_file:-GHE_REPORTS/$(TZ='Australia/Brisbane' date +%Y%m%d%H%M%S%Z)task_result(Agent).md}
Instructions
Run the spawn script:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/spawn_background.py" \
"Please complete this task and save the result to ${ARGUMENTS.output_file:-GHE_REPORTS/\$(TZ='Australia/Brisbane' date +%Y%m%d%H%M%S%Z)_task_result_(Agent).md}: $ARGUMENTS.task" \
"$(pwd)"
Features
- Background execution: Terminal opens but returns focus to your current app
- Auto-approval: PreToolUse hook auto-approves safe operations (no --dangerously-skip-permissions needed)
- Security: Writes blocked outside project, dangerous commands denied
- macOS only: Uses Terminal.app and AppleScript
Security Model
| Operation | Decision |
|---|---|
| Read, Glob, Grep, LS | ALLOW |
| Write/Edit within project | ALLOW |
| Write/Edit outside project | DENY |
| Bash (git, npm, python) | ALLOW |
| Bash (sudo, rm -rf /) | DENY |
| MCP tools | ALLOW |
| Unknown | ASK user |
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.
- 5d ago First seen · 49 lines · 15 tokens per session scan C 93cf39382f25
spawn-agent is a command published in the GitHub repository Emasoft/ghe-marketplace (4 stars, last pushed 9mo ago), licensed MIT. It adds 15 tokens to every session and 423 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.