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 ibm-self-serve-assets/building-blocks --skill ttm-inferencegit clone --depth 1 https://github.com/ibm-self-serve-assets/building-blocksWrote 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/ibm-self-serve-assets/building-blocks/ttm-inference)<a href="https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/ttm-inference"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/ttm-inference/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/ibm-self-serve-assets/building-blocks/ttm-inference"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/ttm-inference.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 | $0.00073 | $0.03192 |
| Opus 5.5 | $0.00029 | $0.01277 |
| Sonnet 5.5 | $0.00015 | $0.00638 |
| Haiku 4.5 | $0.00007 | $0.00319 |
Grade A, and why
ttm-inference 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TTM Inference — Path Selection & Service Code
Step 1 — Choose Your Inference Path
Before writing any code, ask the user (or infer from context) which path applies. The three paths are mutually exclusive:
┌─────────────────────────────────────────────────────────────────────────┐
│ PATH 1 — IBM watsonx.ai Native API (RECOMMENDED for production) │
│ Trigger : TTM_MODEL_ID is set in .env │
│ Needs : WML_API_KEY, WML_SPACE_ID or WML_PROJECT_ID, IBM_CLOUD_REGION│
│ Model : ibm/granite-ttm-512-96-r2 (IBM SaaS hosted — no download) │
│ Latency : ~1-2 s per call │
│ Docker : Single-stage, no model weights in image │
├─────────────────────────────────────────────────────────────────────────┤
│ PATH 2 — Local HuggingFace Pipeline (macOS dev / air-gapped) │
│ Trigger : USE_TTM_MODEL=True, TTM_MODEL_ID not set │
│ Needs : granite-tsfm, torch, transformers installed │
│ Model : ibm-granite/granite-timeseries-ttm-r2 (~2-3 GB download) │
│ Latency : ~2-3 s on CPU after load; ~30-60 s first cold start │
│ Docker : 2-stage build (download on ARM, copy to AMD64 image) │
├─────────────────────────────────────────────────────────────────────────┤
│ PATH 3 — Mock / Statistical Fallback (development / CI only) │
│ Trigger : TTM_MODEL_ID not set AND USE_TTM_MODEL=False │
│ Needs : nothing extra │
│ Output : Simulated sine-wave forecast — NOT suitable for production │
└─────────────────────────────────────────────────────────────────────────┘
- Do you have an IBM Cloud account with WML enabled?
- Yes → use Path 1. Add
TTM_MODEL_ID,WML_API_KEY,IBM_CLOUD_REGION, and eitherWML_SPACE_ID(deployment space) orWML_PROJECT_ID(Watson Studio project) to.env. Use only one — not both. - No → go to question 2.
- Yes → use Path 1. Add
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 · 302 lines · 73 tokens per session scan A 89f1bca6e9af
ttm-inference is a skill published in the GitHub repository ibm-self-serve-assets/building-blocks (28 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 3,192 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-15.
Other skills, from other repositories
etl-integration-nifi
Apache NiFi specialist for flow-based data integration, routing, and provenance tracking. Deep expertise in processors, FlowFiles, connections, process groups, clustering, record-oriented processing, and NiFi 2.x modernization. WHEN: \"Apache NiFi\", \"NiFi\", \"NiFi processor\", \"FlowFile\", \"process group\"…
eks-genai
Use whenever someone is building, training, fine-tuning, or serving a generative AI / LLM workload on Amazon EKS — phrased as "GPU vs Trainium/Inferentia", "vLLM on EKS", "Ray Serve / KubeRay", "distributed training on EKS", "FSx for Lustre for ML", "Karpenter for GPU", "EFA / NCCL multi-node", "DCGM / Neuron…
companion-clis
Companion CLIs for Runpod workflows — HuggingFace, GitHub, Docker, and AWS.
external-gitcode-ascend-verl-feature-deploy
A deployment tool for running Verl distributed training services on Ascend NPU clusters. It configures training containers, Ray, a system for coordinating distributed jobs, SwanLab monitoring, and accelerator options for models such as Qwen3-8B.
agentic-eks-bootstrap
Bootstrap an AWS EKS cluster optimized for Agentic AI workloads — Karpenter v1.2+ GPU node pools, EKS Auto Mode, Kubernetes 1.32+ with DRA 1.35 GA, VPC CNI, GPU Operator, and baseline observability. Use when starting a new EKS cluster that will host vLLM, Inference Gateway, Langfuse, or Kagent.
alterlab-modal
Part of the AlterLab Academic Skills suite. Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.