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 skills add OPPO-Mente-Lab/X-OmniClaw --skill model-configgit clone --depth 1 https://github.com/OPPO-Mente-Lab/X-OmniClawWrote 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/skills/oppo-mente-lab/x-omniclaw/model-config)<a href="https://agentmods.dev/skills/oppo-mente-lab/x-omniclaw/model-config"><img src="https://agentmods.dev/badge/skills/oppo-mente-lab/x-omniclaw/model-config/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/oppo-mente-lab/x-omniclaw/model-config"><img src="https://agentmods.dev/badge/skills/oppo-mente-lab/x-omniclaw/model-config.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00089 | $0.00446 |
| Opus 5 | $0.00044 | $0.00223 |
| Sonnet 5 | $0.00018 | $0.00089 |
| Haiku 4.5 | $0.00009 | $0.00045 |
Grade A, and why
model-config 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 11d 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
Model Config
For X-OmniClaw, model configuration is stored in:
/sdcard/.xomniclaw/xomniclaw.json
Relevant paths:
agent.defaultModelmodels.providers.<providerName>.baseUrlmodels.providers.<providerName>.apiKeymodels.providers.<providerName>.apimodels.providers.<providerName>.authHeadermodels.providers.<providerName>.models
Workflow
- Read
/sdcard/.xomniclaw/xomniclaw.jsonfirst. - Check current
agent.defaultModeland existing providers undermodels.providers. - If the target provider already exists, update only the necessary fields.
- If the target provider does not exist, create a provider entry under
models.providers. - For self-hosted or other OpenAI-compatible endpoints, add a new
models.providers.<yourKey>entry (any stable key name) with:api: "openai-completions"- provider-specific
baseUrl apiKey- one or more model entries in
models
- Update
agent.defaultModelto the requested model. - Preserve unrelated providers and settings.
- If asked to verify, send a simple test prompt after config is saved.
Notes
- Do not overwrite the full config if only one provider/model needs to change.
- If the user provides a compatible endpoint/key, add it as a new provider block under
models.providerswithapi: "openai-completions"(or another supported API type per app). - Keep model IDs exact.
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.
- 11d ago First seen · 41 lines · 89 tokens per session scan A 4ca990e3783a
model-config is a skill published in the GitHub repository OPPO-Mente-Lab/X-OmniClaw (261 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 89 tokens to every session and 446 once invoked, about $0.0004 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 skills, from other repositories
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
nano-banana-pro-openrouter
Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.
skill-creator-linter
Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to lint a candidate meta-skill SKILL.md against G1 (parse + reference check + xmlescape grep + structural lint) and G2 (scheduler dry-run with stub executors). Deterministic, sub-second, no LLM. Returns JSON diagnostics.
paper-abstract-author
Write the abstract after the paper body has been revised, using the final claims and evidence.
openalex-database
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly…