Openrouter Fallback Config
jeremylongshore/tons-of-skills-marketplace
Configure automatic model fallbacks for high availability on OpenRouter.
Run and operate SubZeroClaw — the ~550-line C agentic daemon (skill.md + LLM + shell + loop).
Install Subzeroclaw Use
$ npx skills add genlayerlabs/subzeroclaw --skill subzeroclaw-use -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install genlayerlabs/subzeroclaw subzeroclaw-use --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/genlayerlabs/subzeroclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/subzeroclaw-use .claude/skills/subzeroclaw-use && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "subzeroclaw-use" agent skill from https://github.com/genlayerlabs/subzeroclaw/tree/main/.claude/skills/subzeroclaw-use into .claude/skills/subzeroclaw-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subzeroclaw-use", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/genlayerlabs/subzeroclaw/tree/main/.claude/skills/subzeroclaw-useType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add genlayerlabs/subzeroclaw --skill subzeroclaw-use -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install genlayerlabs/subzeroclaw subzeroclaw-use --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/genlayerlabs/subzeroclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/subzeroclaw-use .agents/skills/subzeroclaw-use && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "subzeroclaw-use" agent skill from https://github.com/genlayerlabs/subzeroclaw/tree/main/.claude/skills/subzeroclaw-use into .agents/skills/subzeroclaw-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subzeroclaw-use", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add genlayerlabs/subzeroclaw --skill subzeroclaw-use -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install genlayerlabs/subzeroclaw subzeroclaw-use --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/genlayerlabs/subzeroclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/subzeroclaw-use .cursor/skills/subzeroclaw-use && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "subzeroclaw-use" agent skill from https://github.com/genlayerlabs/subzeroclaw/tree/main/.claude/skills/subzeroclaw-use into .cursor/skills/subzeroclaw-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subzeroclaw-use", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/genlayerlabs/subzeroclaw.git --path .claude/skills/subzeroclaw-use--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add genlayerlabs/subzeroclaw --skill subzeroclaw-use -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install genlayerlabs/subzeroclaw subzeroclaw-use --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/genlayerlabs/subzeroclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/subzeroclaw-use .gemini/skills/subzeroclaw-use && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "subzeroclaw-use" agent skill from https://github.com/genlayerlabs/subzeroclaw/tree/main/.claude/skills/subzeroclaw-use into .gemini/skills/subzeroclaw-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subzeroclaw-use", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install genlayerlabs/subzeroclaw subzeroclaw-useInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add genlayerlabs/subzeroclaw --skill subzeroclaw-use -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/genlayerlabs/subzeroclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/subzeroclaw-use .github/skills/subzeroclaw-use && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "subzeroclaw-use" agent skill from https://github.com/genlayerlabs/subzeroclaw/tree/main/.claude/skills/subzeroclaw-use into .github/skills/subzeroclaw-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subzeroclaw-use", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add genlayerlabs/subzeroclaw --skill subzeroclaw-use -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install genlayerlabs/subzeroclaw subzeroclaw-use --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/genlayerlabs/subzeroclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/subzeroclaw-use .opencode/skills/subzeroclaw-use && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "subzeroclaw-use" agent skill from https://github.com/genlayerlabs/subzeroclaw/tree/main/.claude/skills/subzeroclaw-use into .opencode/skills/subzeroclaw-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subzeroclaw-use", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
subzeroclaw-use- GitHub stars
- 137
- Token cost
- ~1.5k tokens
- SKILL.md length
- 644 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Run and operate SubZeroClaw — the ~550-line C agentic daemon (skill.md + LLM + shell + loop).
- Tasks that involve Linux administration
- SKILL.md covers Build & run, Configuration…, The unhardcoded substrate… and As a service (and credential…, plus 2 more sections
- Calls make, git and curl; needs SUBZEROCLAW_API_KEY
- Tasks that involve Model routing and gateways
What it does
Subzeroclaw Use is an agent skill from genlayerlabs/subzeroclaw. Run and operate SubZeroClaw — the ~550-line C agentic daemon (skill.md + LLM + shell + loop). Load this to build it, configure it (~/.subzeroclaw/config), write an agent skill, run a task, wire it to an unhardcoded router for routing/cache/compaction, or run it as a systemd service with credential isolation. WARNING: it executes arbitrary shell with no sandbox. To develop the runtime itself, use subzeroclaw-contribute.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Linux administration and Model routing and gateways. It works with Linux and OpenRouter. The repository describes itself as: An agent small enough to run anywhere. A minimal agentic runtime in C — ~380 lines, 54KB binary, ~2MB RAM. A skill file + an LLM + a shell loop, no framework. The licence is MIT.
When your agent uses it
- Tasks that involve Linux administration
- Tasks that involve Model routing and gateways
Example prompts
- “/subzeroclaw-use”
Requirements
- A credential in SUBZEROCLAW_API_KEY
What it can do on your machine
Read from SKILL.md and the folder at commit 6b6b5ad. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
makegitcurl
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
SUBZEROCLAW_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Subzeroclaw Use loads about 1.5k tokens when it runs. Until then it costs about 110 tokens; SKILL.md has 644 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from genlayerlabs/subzeroclaw at commit 6b6b5ad, republished under its MIT licence (© genlayerlabs). 644 words, ~1,459 tokens.
Download SKILL.mdSave it as
.claude/skills/subzeroclaw-use/SKILL.md (or your agent's skills folder).- name
- subzeroclaw-use
- description
- Run and operate SubZeroClaw — the ~550-line C agentic daemon (skill.md + LLM + shell + loop). Load this to build it, configure it (~/.subzeroclaw/config), write an agent skill, run a task, wire it to an unhardcoded router for routing/cache/compaction, or run it as a systemd service with credential isolation. WARNING: it executes arbitrary shell with no sandbox. To develop the runtime itself, use subzeroclaw-contribute.
Using SubZeroClaw
Read the warning first. SubZeroClaw runs whatever the model emits through
popen() — no confirmation, no sandbox, rm -rf / included. There is nothing
between the model's output and your system. Run it only where you accept that,
ideally as an unprivileged service user (see As a service).
The whole runtime is: read a skill (markdown) → call an LLM → run shell tools →
loop until done. One tool: shell. The "adapter" for git/curl/email/ffmpeg is
that they're one popen() away — install the CLI, the model uses it.
Two senses of "skill" — don't conflate them. A SubZeroClaw skill is a plain
.mdfile in~/.subzeroclaw/skills/that becomes the agent's system prompt (what the agent knows). This file is a Claude Code skill (how to operate the tool). When the docs below say "write a skill", they mean the former.
Build & run
git clone https://github.com/genlayerlabs/subzeroclaw && cd subzeroclaw
make # ~0.5s → the 55KB binary (needs gcc; curl at runtime)
mkdir -p ~/.subzeroclaw/skills
# ...write ~/.subzeroclaw/config (below) and a skill .md...
./subzeroclaw "check disk usage and clean tmp if over 80%" # one-shot
./subzeroclaw # interactive
make install # → ~/.local/bin/An agent skill is just prose the LLM reads — no format, no registry, no trigger
matching. Drop a .md in ~/.subzeroclaw/skills/ and it joins the system
prompt. The repo's skills/*.md are format examples tied to one setup; write
your own.
Configuration (~/.subzeroclaw/config)
These are the only keys the runtime parses (config_parse_line); config.example
is the canonical template.
| Key | Meaning |
|---|---|
api_key | The unhardcoded router consumer key (llmr_…) — SubZeroClaw is designed to run on the router. A bare OpenRouter/provider key also works but is a degraded loop. Required. |
request_extra | JSON merged into every request body. Carries the model ({"model":"..."}) — there is no dedicated model key. Against a router it also carries the routing policy_ir. Override wins on key collision. |
compact_extra | JSON enabling async compaction: keep_recent + a cheap summariser policy_ir. Unset → no compaction. |
endpoint | default OpenRouter; point at an unhardcoded router for routing/cache/compaction. |
skills_dir, log_dir | defaults under ~/.subzeroclaw/. |
max_turns | tool-call loops per input (default 200). |
Env vars SUBZEROCLAW_API_KEY, SUBZEROCLAW_ENDPOINT, SUBZEROCLAW_REQUEST_EXTRA,
SUBZEROCLAW_COMPACT_EXTRA override the file.
The unhardcoded substrate (routing + compaction)
Routing with prompt-cache affinity and context compaction are not part of
"skill + LLM + shell + loop" — they live in the substrate. Point endpoint at an
unhardcoded router and express them
as JSON:
- Routing:
request_extra = {"model":"policy:auto","policy_ir":[ … ]}. The runtime sends a per-runsessionid so the router keeps the conversation on its cache-hot peer. (Author thepolicy_irwith theunhardcoded-useskill.) - Compaction: on an
x_router.compactsignal, the runtime fires an append-only seal at the router's/v1/compactin the background and keeps taking turns, splicing the sealed block in ahead of the turns that arrived meanwhile — no pause, the cache prefix is never rewritten.compact_extracarrieskeep_recent+ the summariser policy.
Pointed at a bare provider the HTTP call still fires, but it's a degraded loop (no routing, cache, or compaction) — not a supported standalone mode.
Show full SKILL.md (210 more words)Show less
As a service (and credential isolation)
SubZeroClaw doesn't supervise itself — bring your init system. A systemd unit with
Restart=on-failure and an EnvironmentFile (root-owned, chmod 600) holding
SUBZEROCLAW_API_KEY gets you restart + credential isolation. The runtime
scrubs the four provider secrets (SUBZEROCLAW_API_KEY, _ENDPOINT,
_REQUEST_EXTRA, _COMPACT_EXTRA) from its own environment right after
config_load — wiping the value in place, then unsetenv — so the shell it hands
the model never inherits the key (cat /proc/self/environ comes up empty).
Non-secret vars like SUBZEROCLAW_SKILLS are deliberately kept (the genswarms
wrapper sets it). The supervisor owns the secret; the shell stays unguarded by
design — the scrub only keeps the runtime's own secrets out of it.
Gotchas
- A top-level
model =line in the config is ignored — the runtime never parses it. The model rides inrequest_extra. (This is the most common misconfiguration.) - Use a tool-calling model. If the model can't call tools it will loop without
progress. Set it in
request_extra. curlis required at runtime (API calls shell out to it);gcconly to build.- Compaction is opt-in: unset
compact_extra→ context grows until the provider refuses it.
Where to read more
README.md— the full config reference, session logging, troubleshooting table.config.example— the canonical config template.- The
unhardcoded-use/sigma-policy-authorskills — author the routing and summariserpolicy_irthis runtime sends.
© genlayerlabs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/subzeroclaw-use of genlayerlabs/subzeroclaw.
Open the folder on GitHubat commit 6b6b5ad
Compare with similar skills
Subzeroclaw Use next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Subzeroclaw Use this skillgenlayerlabs/subzeroclaw | 137 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Openrouter Fallback Configjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~2.4k | Automated safety check: Pass | MIT | |
| Openrouter Load Balancingjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~2.4k | Automated safety check: Pass | MIT | |
| Openrouter Prod Checklistjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~2.4k | Automated safety check: Notes | MIT | |
| LLM GatewayBagelHole/DevOps-Security-Agent-Skills | 1.1k | — | ~2k | Automated safety check: Pass | MIT | |
| Pinme LLMglitternetwork/pinme | 3.7k | 1 repos | ~2.8k | Automated safety check: Pass | MIT |
Similar skills
Openrouter Load Balancing
jeremylongshore/tons-of-skills-marketplace
Distribute OpenRouter requests across multiple keys and models for high throughput.
Openrouter Prod Checklist
jeremylongshore/tons-of-skills-marketplace
Validate production readiness of your OpenRouter integration.
LLM Gateway
BagelHole/DevOps-Security-Agent-Skills
Deploy an API gateway for LLM traffic with load balancing, rate limiting, key management, semantic caching, fallback routing, and cost tracking.
Pinme LLM
glitternetwork/pinme
A skill your agent uses when a PinMe project (Worker TypeScript) needs to call OpenRouter-backed LLM APIs, including models, chat/completions, streaming, or OpenRouter web search.
FreeRide Free Model Manager
Shaivpidadi/FreeRide
Configures OpenClaw to use free OpenRouter models, setting the best one as primary and adding ranked fallbacks so rate limits do not interrupt work.
More from genlayerlabs/subzeroclaw
Subzeroclaw Contribute
genlayerlabs/subzeroclaw
Develop SubZeroClaw — the single-file ~550-line C agentic runtime.
Related
Works with
Categories
Questions about Subzeroclaw Use
What does Subzeroclaw Use do?
Run and operate SubZeroClaw — the ~550-line C agentic daemon (skill.md + LLM + shell + loop). Subzeroclaw Use is an agent skill from genlayerlabs/subzeroclaw.md + LLM + shell + loop).
When should I use Subzeroclaw Use?
Subzeroclaw Use fits situations like: tasks that involve Linux administration; tasks that involve Model routing and gateways.
How do I install Subzeroclaw Use in Claude Code?
Run `npx skills add genlayerlabs/subzeroclaw --skill subzeroclaw-use -a claude-code`. Or copy the skill folder (.claude/skills/subzeroclaw-use in genlayerlabs/subzeroclaw) into .claude/skills/subzeroclaw-use in your project. Claude Code loads it when a task matches its description.
How do I install Subzeroclaw Use in Codex?
Run `npx skills add genlayerlabs/subzeroclaw --skill subzeroclaw-use -a codex`. Or copy the skill folder (.claude/skills/subzeroclaw-use in genlayerlabs/subzeroclaw) into .agents/skills/subzeroclaw-use in your project. Codex loads it when a task matches its description.
Can I use Subzeroclaw Use in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add genlayerlabs/subzeroclaw --skill subzeroclaw-use -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/subzeroclaw-use, .gemini/skills/subzeroclaw-use, .github/skills/subzeroclaw-use and .opencode/skills/subzeroclaw-use in your project.
What does Subzeroclaw Use need to run?
Going by SKILL.md and its folder, Subzeroclaw Use needs the command-line tools its instructions call (make, git and curl) and credentials named SUBZEROCLAW_API_KEY. Our summary lists: A credential in SUBZEROCLAW_API_KEY.
Does Subzeroclaw Use access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Subzeroclaw Use safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Subzeroclaw Use use?
Subzeroclaw Use is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Subzeroclaw Use use?
About 1.5k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Subzeroclaw Use?
Skills that share tags, products or a category with Subzeroclaw Use: Openrouter Fallback Config (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Openrouter Load Balancing (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Openrouter Prod Checklist (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and LLM Gateway (BagelHole/DevOps-Security-Agent-Skills, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Subzeroclaw Use?
genlayerlabs (a GitHub organization) maintains it in genlayerlabs/subzeroclaw, which has 137 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 25, 2026.
Source: genlayerlabs/subzeroclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.