What is aidp-fusion-status?

A read-only health report for a data pipeline that moves Oracle Fusion data into Oracle AI Data Platform. It checks recorded runs against the live catalog of materialized tables.

Checking pipeline health before a new run, finding nodes that need refreshing, and seeing which gold data marts exist and how many rows they contain.

It shows whether the latest load worked and catches stale, missing, empty, or failed data that run history alone may hide.

aidp-fusion-status — Skill for Claude Code by ahmedawan-oracle

Install

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.

Any agent

npx skills add ahmedawan-oracle/claude-code-plugins --skill aidp-fusion-status

Clone the repo

git clone --depth 1 https://github.com/ahmedawan-oracle/claude-code-plugins

Made for: Claude Code.

Or install oracle-ai-data-platform-fusion-autopilot, the plugin that ships this one along with the rest of its 16 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/aidp-fusion-status/github.svg)](https://agentmods.dev/skills/ahmedawan-oracle/claude-code-plugins/aidp-fusion-status)

Your own site

<a href="https://agentmods.dev/skills/ahmedawan-oracle/claude-code-plugins/aidp-fusion-status"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/aidp-fusion-status/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ahmedawan-oracle/claude-code-plugins/aidp-fusion-status"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/aidp-fusion-status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,270 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00183	$0.01270
Opus 5	$0.00092	$0.00635
Sonnet 5	$0.00037	$0.00254
Haiku 4.5	$0.00018	$0.00127

Measured 10d ago against content hash e951aed65b05, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

aidp-fusion-status 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (status_report.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

claude-code-plugins/oracle-ai-data-platform-fusion-autopilot/skills/aidp-fusion-status/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aidp-fusion-status — is my pipeline healthy, and what's stale?

The read-only observability member of the family. It reports per-node health by reconciling two truth sources and never changes anything.

When to use

"Did my last seed/incremental succeed? what failed?"
"What's stale / hasn't refreshed / needs re-running?"
"Which gold marts are actually materialized, and with how many rows?"
As a pre-check before /aidp-fusion-seed or /aidp-fusion-incremental.

When NOT to use

To run anything — seeding is /aidp-fusion-seed, deltas are /aidp-fusion-incremental. This skill is strictly read-only.

Evidence discipline (load-bearing)

The live table is the evidence; the state row is the overlay. fusion_autopilot_state is run metadata — a success row can sit next to a dropped/empty mart, and a table can exist with no state row. So health keys off the live AIDP catalog (what's materialized), cross-checked against the state row. Never report "healthy" from a state row alone. (Same rule as the seed guard / the advisor — [[feedback_live_catalog_is_evidence]].)

Helper

File	Role	Invoked via
`status_report.py`	Classify per-node health from `{state rows} × {live tables}`.	`Bash`, JSON in/out

Health classes: HEALTHY · EMPTY_OK · STALE (success recorded, table absent) · FAILED · SKIPPED · UNTRACKED (table exists, no run record) · NEVER_RUN (declared node, nothing anywhere).

Workflow

Acquire both signals (cluster-side — the laptop aidp-fusion-autopilot status is local-Spark-only and has no JSON):
```
.venv/bin/python tests/live/aidp_state_probe_live.py \
  --aidp-id <OCID> --workspace-key <key> --cluster-key <key> \
  --cluster-name <name> --out status.json
```
It runs, on an ACTIVE cluster, SHOW TABLES + COUNT(*) over the gold (and optionally silver/bronze) schema → live, and the latest-per-dataset query over <catalog>.<bronzeSchema>.fusion_autopilot_state → state, into one JSON. (When aidp-fusion-autopilot status --json ships, use it instead.)
Classify:
```
python3 skills/aidp-fusion-status/status_report.py --input status.json
```
Optionally add known_nodes (from content-pack info <pack> --json + bundle datasets) so declared-but-never-built nodes show as NEVER_RUN.
Render a per-node ledger + the attention list (STALE/FAILED/UNTRACKED/ NEVER_RUN), with lastRun / lastStatus / stateRowCount vs liveRowCount.
Recommend, don't act — e.g. "re-run gl_balance (STALE) via /aidp-fusion-seed"; "investigate mystery_mart (UNTRACKED — built outside the orchestrator)"; "po_backlog NEVER_RUN — seed it or drop it from the bundle." Never run anything yourself.

Read the full file on GitHub · 87 lines

Files

What ships with it

1 file 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.

status_report.py 5.9 KB runs code

Changes

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.

10d ago First seen · 87 lines · 183 tokens per session scan A e951aed65b05

Subscribe to this mod's changes

aidp-fusion-status is a skill published in the GitHub repository ahmedawan-oracle/claude-code-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 183 tokens to every session and 1,270 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.

Analytics and metrics Data and AI

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

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.

google/skills · 60 tokens

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.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens