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 asfbay-bit/opchain-skills --skill oc-data-opsgit clone --depth 1 https://github.com/asfbay-bit/opchain-skillsWrote 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/asfbay-bit/opchain-skills/oc-data-ops)<a href="https://agentmods.dev/skills/asfbay-bit/opchain-skills/oc-data-ops"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/oc-data-ops/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/asfbay-bit/opchain-skills/oc-data-ops"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/oc-data-ops.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 | $0.00240 | $0.03336 |
| Opus 5.5 | $0.00096 | $0.01334 |
| Sonnet 5.5 | $0.00048 | $0.00667 |
| Haiku 4.5 | $0.00024 | $0.00334 |
Grade A, and why
oc-data-ops 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 26d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Ops
On first invocation, read references/orchestrator.md and follow its welcome protocol.
Data Ops owns the estate level of data: how data enters the system, how it is layered and transformed, and — the part most pipeline work skips — the contracts that make each dataset's shape, freshness, and volume observable and enforceable. Where oc-signal-forge proves one metric answers one question, Data Ops builds and guards the pipelines whole families of metrics ride on.
Tri-agent loop: Designer → Builder → Contract-Verifier. All three roles run in the same session, so the Verifier's separation is a discipline, not a mechanism: it grades from the contracts and the built pipeline alone — never the Builder's reasoning.
Command Reference
DATA OPS COMMANDS
/oc-data-ops Show this menu
/oc-data-ops design Designer: pipeline architecture + layer map
/oc-data-ops contracts Designer: author data contracts per dataset
/oc-data-ops build Builder: implement ingestion + transforms (dbt where chosen)
/oc-data-ops verify Contract-Verifier: replay contracts against the built estate
/oc-data-ops observe Wire freshness/volume/schema monitors → oc-monitoring-ops
/oc-data-ops status Loop position, contract pass rate, open violations
/checkpoint Show oc-data-ops checkpoint
Phase 1: Designer (/oc-data-ops design)
Produce the pipeline architecture before any transform is written:
- Source inventory. Every producer: app DBs, event streams, third-party exports, files. For each: change pattern (append-only, mutable, CDC-able), volume, and arrival cadence.
- Ingestion pattern per source. Batch pull, streaming, CDC, or file-drop — chosen from the source's change pattern, not fashion. State the reason in one line each.
- Layer map. Staging (source-shaped, immutable) → intermediate (conformed, tested) → marts (consumer-shaped). Name every dataset per layer. If the project uses dbt, this map IS the dbt DAG plan; if not, the same layering applies in whatever transform tool oc-stack-forge selected.
- Consumer map. Who reads each mart: dashboards (oc-dash-forge), metrics (oc-signal-forge), app features, exports. A mart with no registered consumer does not get built.
What ships with it
3 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.
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.
- 26d ago Changed 9c607775969c
- 29d ago Changed a40b3966003b
- 1mo ago Changed c267381b9515
- 1mo ago Changed · +11 lines aa008246a549
- 1mo ago First seen · 268 lines · 240 tokens per session scan A c214f4760019
oc-data-ops is a skill published in the GitHub repository asfbay-bit/opchain-skills (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 240 tokens to every session and 3,336 once invoked, about $0.0010 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 2026-09-04.
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…