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/anshulixyz/multi-agent-loop-kit/spawngit clone --depth 1 https://github.com/anshulixyz/multi-agent-loop-kitWhat 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 | $0.00013 | $0.00252 |
| Opus 5 | $0.00006 | $0.00126 |
| Sonnet 5 | $0.00003 | $0.00050 |
| Haiku 4.5 | $0.00001 | $0.00025 |
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.
What it actually says
Spawn a new coding agent for this repo.
Run, passing the codename / slug / base-branch the user gave in $ARGUMENTS:
bash "${CLAUDE_PLUGIN_ROOT}/bin/loop-spawn" $ARGUMENTS
This creates a sibling git worktree (../<repo>-<codename>) on branch <codename>/<slug>
and seeds the agent's journal at agents-status/<codename>.md. The base branch defaults to
the repo's default branch.
If $ARGUMENTS is empty, ask the user for at least a codename (e.g. frontend, anvil)
before running. After it succeeds, relay the worktree path and branch, and remind the user to
open that path in their agent of choice and paste prompts/<codename>.md (or
prompts/coding-agent.md).
(If the plugin's bin/ is on your PATH, loop-spawn <codename> [slug] is the same command.)
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.
- 2d ago First seen · 24 lines · 13 tokens per session scan A d9eaf749ffa0
spawn is a command published in the GitHub repository anshulixyz/multi-agent-loop-kit (5 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 252 once invoked, about $0.0001 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.
Other commands, from other repositories
unlatch
Confirmed toggle for latch Unlatched mode.
latch-compact
Manually trigger a latch compaction for the current session.
latch-gate
Manual gate (LLM go/no-go judgement) on a coding/build request.
latch-tree
Rebuild the hierarchical cluster/summary tree for this project's KB.
latch-budget-approve
Unlock the rest of today for unlimited latch LLM invocations in this project.
latch-decay
Apply weekly decay + promote staging nodes that cleared the refcount bar.