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-forecastinggit 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-forecasting)<a href="https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/ttm-forecasting"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/ttm-forecasting/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-forecasting"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/ttm-forecasting.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 | $0.00076 | $0.01155 |
| Opus 5.5 | $0.00030 | $0.00462 |
| Sonnet 5.5 | $0.00015 | $0.00231 |
| Haiku 4.5 | $0.00008 | $0.00115 |
Grade A, and why
ttm-forecasting 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TTM Time-Series Forecasting — Master Skill
Overview
This skill provides 96-step-ahead time-series forecasting using IBM Granite TTM (Tiny Time Mixer). It is split into focused sub-skills — load only the one relevant to your task.
| Sub-skill | File | When to use |
|---|---|---|
| TTM Inference | ttm-inference/SKILL.md |
Generating forecast service code, selecting inference path, .env setup, credentials, troubleshooting |
| TTM Dashboard | ttm-dashboard/SKILL.md |
Scaffolding dashboard.html, wiring to live API, visualising forecast output |
| TTM Fleet | ttm-fleet/SKILL.md |
Concurrent multi-truck forecasting, cargo normalisation, OpenScale governance logging |
Routing Instructions
When the user's request matches one of the following, read the corresponding sub-skill file before responding:
- Inference / service code /
.env/ credentials / API path / troubleshooting errors → readttm-inference/SKILL.md - Dashboard / visualise / chart / plot / forecast UI /
dashboard.html→ readttm-dashboard/SKILL.md - Fleet / multi-truck / concurrent / cargo / governance / OpenScale → read
ttm-fleet/SKILL.md
If the request spans multiple areas, read all relevant sub-skill files.
Project Folder Convention
Always create a named project subfolder before writing any files. Never drop files into the workspace root.
<project_name>/
├── ttm_model.py
├── forecasting_service.py
├── app.py
├── requirements.txt
├── .env.example
└── README.md
Use a descriptive name derived from the use case (e.g. stock_forecast, cold_chain, energy_monitor). If adding TTM to an existing project, place files in the most logical existing subfolder.
Input / Output Summary
Minimum input: 512 historical data points as [{"timestamp": "...", "value": ...}]
Output:
{
"predictions": [{"timestamp": "...", "value": 2.5}, "...96 steps"],
"model": "ibm/granite-ttm-512-96-r2",
"inference_path": "native_api | local_pipeline | mock",
"risk_assessment": {"risk_score": 45, "action": "MONITOR"},
"metadata": {"inference_time_ms": 1450}
}
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- sample_data/scenarios/custom_template.json 1.8 KB
- sample_data/scenarios/iot_sensor_scenario.json 39 KB
- sample_data/scenarios/README.md 7.5 KB
- sample_data/scenarios/sales_scenario.json 39 KB
- sample_data/scenarios/stock_price_scenario.json 39 KB
- sample_data/scenarios/website_traffic_scenario.json 38 KB
- ttm-dashboard/SKILL.md 7.6 KB
- ttm-fleet/SKILL.md 5.8 KB
- ttm-inference/SKILL.md 12 KB
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 · 104 lines · 76 tokens per session scan A ce6a15aa855e
ttm-forecasting 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 76 tokens to every session and 1,155 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
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 designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
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.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…