Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Veightor/chutes-agent-toolkitnpx agentmods add skills/veightor/chutes-agent-toolkit/chutes-deployWrote 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/veightor/chutes-agent-toolkit/chutes-deploy)<a href="https://agentmods.dev/skills/veightor/chutes-agent-toolkit/chutes-deploy"><img src="https://agentmods.dev/badge/skills/veightor/chutes-agent-toolkit/chutes-deploy.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.00968 |
| Opus 5 | $0.00044 | $0.00484 |
| Sonnet 5 | $0.00018 | $0.00194 |
| Haiku 4.5 | $0.00009 | $0.00097 |
Grade A, and why
chutes-deploy 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 7d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chutes Deploy for Hermes [BETA — permanent until verified live runs]
Status: permanent BETA for deploy-side writes. Wave-2 live verification reached the Chutes deploy API and found server-side gating for easy deploy (
HTTP 403 Easy deployment is currently disabled!) on at least some account classes. Scripts now surface fallback hints and resolve branch names to SHAs, but deploy-side writes keep BETA by policy.
When to use this skill
A Hermes user wants to:
- Deploy a new vLLM or diffusion chute from a Hugging Face repo id.
- Build a custom CDK chute image from a Dockerfile + context.
- Teeify an existing affine chute into a TEE-isolated variant.
- Inspect rolling updates on an existing chute.
- Create a stable model alias (
interactive-fast,tee-chat, etc.) on top of a deployed chute.
Not for: calling models that already exist on Chutes. That's the hub chutes-ai skill.
Walkthrough (Hermes-facing)
Full walkthroughs and scripts live at plugins/chutes-ai/skills/chutes-deploy/. Hermes users run the same scripts from the repo root:
# Lane A — vLLM
python plugins/chutes-ai/skills/chutes-deploy/scripts/deploy_vllm.py \
--model Qwen/Qwen3-8B --gpu h100 --alias interactive-fast
# Lane B — diffusion
python plugins/chutes-ai/skills/chutes-deploy/scripts/deploy_diffusion.py \
--model stabilityai/sdxl-turbo --gpu a100_40gb
# Lane C — custom CDK (two-step)
python plugins/chutes-ai/skills/chutes-deploy/scripts/build_image.py \
--dockerfile ./Dockerfile --context ./ctx --name myorg/my-chute --tag v1
python plugins/chutes-ai/skills/chutes-deploy/scripts/deploy_custom.py \
--image-id <id> --entrypoint my_module:chute --gpu h100 --name myorg/my-chute
# Teeify
python plugins/chutes-ai/skills/chutes-deploy/scripts/teeify_chute.py --chute-id <id>
# Alias
python plugins/chutes-ai/skills/chutes-deploy/scripts/alias_deploy.py \
--alias interactive-fast --model <model_id>
All scripts read cpk_ from the shared keychain via manage_credentials.py.
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.
- 7d ago First seen · 78 lines · 88 tokens per session scan A 79c20f175ff9
chutes-deploy is a skill published in the GitHub repository Veightor/chutes-agent-toolkit (5 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 968 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 2026-08-31.
Other skills, from other repositories
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
google-cloud-solution-guided-gke-ai-migration
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
gke-inference
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).
agent-platform-endpoint-management
Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model…
modal
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.