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 ahmedawan-oracle/claude-code-plugins --skill oac-dataset-advisorgit clone --depth 1 https://github.com/ahmedawan-oracle/claude-code-pluginsWrote 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/ahmedawan-oracle/claude-code-plugins/oac-dataset-advisor)<a href="https://agentmods.dev/skills/ahmedawan-oracle/claude-code-plugins/oac-dataset-advisor"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/oac-dataset-advisor/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/ahmedawan-oracle/claude-code-plugins/oac-dataset-advisor"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/oac-dataset-advisor.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 | $0.00176 | $0.03274 |
| Opus 5 | $0.00088 | $0.01637 |
| Sonnet 5 | $0.00035 | $0.00655 |
| Haiku 4.5 | $0.00018 | $0.00327 |
Grade A, and why
oac-dataset-advisor 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 8d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
oac-dataset-advisor — from dashboard intent to a grounded OAC dataset plan
A planning skill. Given "I want a dashboard with supplier spend and GL balance", it answers three questions, in order:
- What gold data actually exists on this tenant? — by inspecting the live AIDP catalog, not by reading pack declarations.
- Does an OAC dataset for it already exist? — via OAC MCP.
- What should the operator do? — reuse an existing dataset, create a new OAC dataset over specific gold table(s), or (if gold can't serve it) author a new mart first.
It advises only — it never creates datasets or marts. Dataset creation is
an OAC action over the AIDP connection (the OAC MCP server has no
create-dataset tool); hand CREATE recommendations to /oac-dataset-setup.
New marts are the job of the mart-authoring skill.
Evidence discipline (the load-bearing rule)
The evidence is the LIVE AIDP catalog — the Delta tables actually
materialized in <catalog>.<goldSchema> on this tenant — captured at advise
time. Never substitute the content-pack gold/*.yaml outputSchema
declarations. Those are design-time intent: they describe what the pack
would build, not what exists or what the real columns are on this pod. Using
them would let the advisor recommend a dataset over a table that was never
seeded, or with columns that don't match. (Same rule as CLAUDE.md "live
evidence is required for any plugin-portability claim.") Pack metadata such as
PII tags may be layered on as an advisory overlay, never as the evidence.
When to use
- "I want a dashboard showing and " / "build me a CFO view of <…>".
- "What OAC dataset do I need for ?" / "which gold tables back this?"
- "Can my current gold layer serve ?" / "do I have the data?"
- Before
workbook-authoring: to decide which dataset the workbook will bind to.
When NOT to use
- Authoring the workbook itself → use
workbook-authoring(after the dataset exists). - Creating a new gold mart (new YAML + SQL) → the mart-authoring skill.
- Running the pipeline / materializing gold →
aidp-fusion-autopilot run --mode seed(or theaidp-fusion-seedskill).
What ships with it
2 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.
- 8d ago First seen · 240 lines · 176 tokens per session scan A 3568f3ed7f93
oac-dataset-advisor is a skill published in the GitHub repository ahmedawan-oracle/claude-code-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 176 tokens to every session and 3,274 once invoked, about $0.0009 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…