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 skills/openrouterlabs/spawn/update-metadatanpx skills add OpenRouterLabs/spawn --skill update-metadatagit 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 | $0.00000 | $0.00439 |
| Opus 5 | $0.00000 | $0.00219 |
| Sonnet 5 | $0.00000 | $0.00088 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
update-metadata 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
Update Agent & Cloud Metadata
Refresh icons and metadata/stats for agents and cloud providers in manifest.json.
When to use
Run this when:
- An agent or cloud provider's logo changes
- An icon URL breaks (404 or stale redirect)
- A new agent or cloud is added without an icon
- GitHub star counts need refreshing
- Agent repo info changed (license, language)
- You want a full metadata audit
- You need to validate that all source URLs are still reachable
Arguments
--agent <id>— Update only the specified agent (e.g.--agent openclaw).--cloud <id>— Update only the specified cloud (e.g.--cloud hetzner).--agents-only— Only process agents, skip clouds.--clouds-only— Only process clouds, skip agents.--icons-only— Only refresh icons, skip GitHub metadata.--stats-only— Only refresh GitHub stats, skip icon downloads.--validate— Check all source URLs are reachable without downloading. Exits with code 1 if any are broken.--dry-run— Print what would change without writing files.
Procedure
Run the update script, passing through any arguments:
bun run .claude/skills/update-metadata/update.ts [arguments]
Fixing broken sources
If --validate reports broken URLs (marked with ✗), fix them by editing the relevant .sources.json file:
- Agent sources:
assets/agents/.sources.json - Cloud sources:
assets/clouds/.sources.json
Each entry maps an id to { "url": "...", "ext": "png" }. Update the url to a working icon source (apple-touch-icon, GitHub org avatar, or favicon), then re-run the script without --validate to download and update everything.
Review the output, then commit the changed files (manifest.json, .sources.json files, and any updated icon files).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 45 lines · 0 tokens per session scan A b236531b4337
update-metadata is a skill published in the GitHub repository OpenRouterLabs/spawn (233 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 439 tokens. 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 skills, from other repositories
nemoclaw-maintainer-refactor-docs
Plan and execute maintainer-owned refactors of oversized NemoClaw Fern documentation sections into focused one-topic pages with concise prose, journey-based nested navigation, non-clickable group nodes, canonical troubleshooting and reference ownership, deduplicated content, variant-aware route-style links, and…
nemoclaw-contributor-implement-issue
Implement an accepted NemoClaw GitHub issue in the current checkout. Use when a user asks to pick up an issue for implementation, implement or fix a named issue, or add the issue's tests. Confirm accepted scope, deliver the smallest independently valuable capability slice, and record validation and remaining gates…
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
add-resend
Add Resend (email) channel integration via Chat SDK.
add-macos-statusbar
Add a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether NanoClaw is running, with Start, Stop, and Restart controls. macOS only.