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 instructions/openrouterlabs/spawn/claude-mdgit clone --depth 1 https://github.com/OpenRouterLabs/spawnWhat 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 | $0.00930 | $0.00930 |
| Opus 5 | $0.00465 | $0.00465 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
spawn CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spawn
Spawn is a matrix of agents x clouds. Every script provisions a cloud server, installs an agent, injects OpenRouter credentials, and drops the user into an interactive session.
The Matrix
manifest.json is the source of truth. It tracks:
- agents — AI agents and self-hosted AI tools (Claude Code, OpenClaw, Codex CLI, ...)
- clouds — cloud providers to run them on (Sprite, Hetzner, ...)
- matrix — which
cloud/agentcombinations are"implemented"vs"missing"
File Structure
spawn/
packages/
cli/
src/index.ts # CLI entry point (bun/TypeScript)
src/manifest.ts # Manifest fetch + cache logic
src/commands/ # Per-command modules (interactive, list, run, etc.)
src/commands/index.ts # Barrel re-export of all command modules
package.json # npm package (@openrouter/spawn)
sh/
cli/
install.sh # One-liner installer (bun → npm → auto-install bun)
shared/
github-auth.sh # Standalone GitHub CLI auth helper
key-request.sh # API key provisioning helpers (used by QA)
e2e/
lib/*.sh # E2E helper libraries
test/
macos-compat.sh # macOS compatibility test script
{cloud}/
{agent}.sh # Agent deployment scripts (thin bash → bun wrappers)
README.md # Cloud-specific usage docs
.claude/
rules/ # Modular rules (auto-loaded by Claude Code)
scripts/ # Hook scripts (enforce-worktree, validate-file, pre-merge-check)
skills/setup-agent-team/
trigger-server.ts # HTTP trigger server (concurrent runs, dedup)
discovery.sh # Discovery cycle script
refactor.sh # Dual-mode cycle script (issue fix or full refactor)
start-discovery.sh # Launcher with secrets (gitignored)
start-refactor.sh # Launcher with secrets (gitignored)
.github/workflows/
discovery.yml # Scheduled + issue-triggered discovery workflow
refactor.yml # Scheduled + issue-triggered refactor workflow
manifest.json # The matrix (source of truth)
fixtures/ # API response fixtures for testing
README.md # User-facing docs
CLAUDE.md # This file — project overview
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 · 85 lines · 930 tokens per session scan A 51aa24875930
spawn CLAUDE.md is an instructions file published in the GitHub repository OpenRouterLabs/spawn (233 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 930 tokens to every session, about $0.0047 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 2026-08-30.
Other instructions, from other repositories
autocontext CLAUDE.md
Instructions for greyhaven-ai/autocontext, covering claude.md, project overview, repository layout, commands and setup.
librefang AGENTS.md
Instructions for librefang/librefang, covering stack, layout, build, architecture and kernelhandle trait.
autonomous-os AGENTS.md
Instructions for autonomous-ai/autonomous-os, covering agents.md, multi-ide rules, working style, parallel work / subagents and device access rules.
clawmetry AGENTS.md
Instructions for vivekchand/clawmetry, covering agents.md — for ai coding agents, quick context, where new code goes (open-core split), the rules that bite and common tasks.
OneManCompany CLAUDE.md
Instructions for 1mancompany/OneManCompany, covering gstack and skill routing.
souls-directory CLAUDE.md
Instructions for thedaviddias/souls-directory, covering claude.md — project context for ai assistants, project overview, tech stack, critical rules and database is convex.