Borrowing it
Nothing to install: this file belongs to chiptoe-svg/nanoclaw_flexagents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chiptoe-svg/nanoclaw_flexagents/main/.claude/skills/add-custom-models/SKILL.mdgit clone --depth 1 https://github.com/chiptoe-svg/nanoclaw_flexagentsWrote 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/chiptoe-svg/nanoclaw_flexagents/add-custom-models)<a href="https://agentmods.dev/skills/chiptoe-svg/nanoclaw_flexagents/add-custom-models"><img src="https://agentmods.dev/badge/skills/chiptoe-svg/nanoclaw_flexagents/add-custom-models/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/chiptoe-svg/nanoclaw_flexagents/add-custom-models"><img src="https://agentmods.dev/badge/skills/chiptoe-svg/nanoclaw_flexagents/add-custom-models.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 | $0.00065 | $0.00644 |
| Opus 5 | $0.00032 | $0.00322 |
| Sonnet 5 | $0.00013 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
add-custom-models 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 12d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Custom Models
Enable support for custom model endpoints — local models, third-party providers, or self-hosted deployments. Uses the Codex SDK as the bridge to any OpenAI-compatible endpoint.
Phase 1: Pre-flight
Check if Codex SDK is installed
ls src/runtime/codex-runtime.ts 2>/dev/null && echo "CODEX_INSTALLED" || echo "CODEX_MISSING"
If CODEX_MISSING, the Codex SDK is required as the bridge for custom models. Invoke /add-agentSDK-codex first, then return here.
Check current state
grep -q 'OMLX_URL\|LITELLM_URL' .env 2>/dev/null && echo "ENDPOINTS_CONFIGURED" || echo "NO_ENDPOINTS"
Phase 2: Configure
Explain to the user
Custom models let you use any OpenAI-compatible endpoint alongside your primary agent SDK.
This works by routing through the Codex SDK — when you select a custom model via
/model, the system automatically uses Codex with the custom endpoint URL.Common endpoints: • OMLX — local models optimized for Apple Silicon (persistent KV cache, tool calling) • Ollama — easy local model hosting • Together AI, Groq, Fireworks — fast third-party inference • HuggingFace Inference — hosted open-source models • Self-hosted vLLM, llama.cpp — your own deployment
Run
/add-model-endpointto add endpoints one at a time.
Update available models in config
After running /add-model-endpoint for each desired provider, verify models appear in /model command output.
Rebuild container
Only needed if this is the first time installing custom model support:
npm run build && ./container/build.sh
Restart service
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
# Linux: systemctl --user restart nanoclaw
Phase 3: Verify
Send /model in Telegram. You should see your custom models listed below the cloud models.
Switch to a custom model:
/model omlx/llama-3.1-8b
Send a message and verify it responds using the local/custom model.
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.
- 12d ago First seen · 81 lines · 65 tokens per session scan A 154fa17154af
add-custom-models is a skill published in the GitHub repository chiptoe-svg/nanoclaw_flexagents (5 stars, last pushed 4mo ago), licensed MIT. It adds 65 tokens to every session and 644 once invoked, about $0.0003 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 skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.