nem-analyst

nem-analyst is an agent for Claude Code from brensch/scadaminer-ai-toolkit. It costs 75 tokens per session (728 once invoked), scanned A, original, MIT.

A specialised research assistant for Australia's National Electricity Market (NEM), using AEMO dispatch data. AEMO is the Australian Energy Market Operator, which publishes and manages much of this market data.

In plain words
What is it for?
It helps investigate electricity prices, generation, FCAS, interconnector flows, constraints, bids, demand, and revenue.
Why use it?
It handles entity names, dates, available data, and query selection so market questions can be answered consistently with cited figures and charts.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the scadaminer plugin — 4 commands, 1 agent shipped together

Good fit It helps investigate electricity prices, generation, FCAS, interconnector flows, constraints, bids, demand, and revenue.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/brensch/scadaminer-ai-toolkit/nem-analyst
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.

Clone the repo
git clone --depth 1 https://github.com/brensch/scadaminer-ai-toolkit

Made for: Claude Code.

Or install scadaminer, the plugin that ships this one along with the rest of its 4 commands, 1 agent.

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.

agentmods badge for nem-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/brensch/scadaminer-ai-toolkit/nem-analyst/github.svg)](https://agentmods.dev/agents/brensch/scadaminer-ai-toolkit/nem-analyst)
Your own site
<a href="https://agentmods.dev/agents/brensch/scadaminer-ai-toolkit/nem-analyst"><img src="https://agentmods.dev/badge/agents/brensch/scadaminer-ai-toolkit/nem-analyst/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.

agentmods 80×15 button for nem-analyst

Your own site · 80×15
<a href="https://agentmods.dev/agents/brensch/scadaminer-ai-toolkit/nem-analyst"><img src="https://agentmods.dev/badge/agents/brensch/scadaminer-ai-toolkit/nem-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 728 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.00728
Opus 5 $0.00037 $0.00364
Sonnet 5 $0.00015 $0.00146
Haiku 4.5 $0.00007 $0.00073

Measured 8d ago against content hash 2be99a9acd19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

nem-analyst 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.

plugins/scadaminer/agents/nem-analyst.md · 46 lines

What it actually says

You are a NEM market analyst. You answer questions using the SCADA Miner MCP warehouse (AEMO dispatch data: prices, generation, FCAS, interconnectors, constraints, bids). NEM time is Australia/Brisbane (UTC+10, no DST). Regions are NSW1, QLD1, SA1, TAS1, VIC1.

Workflow for every question:

  1. Open a trace. Call start_question and pass the returned question_id on every subsequent tool call this turn.
  2. Resolve entities. For each station / DUID / region / interconnector / fuel term, call search_entities and choose the candidate that fits the context. Ignore weak matches for generic English words.
  3. Anchor time. If the question is time-bounded, call get_data_freshness to clamp to available data. Resolve undated phrases (e.g. "March 3", "last week") to the most recent past occurrence and always restate the inferred year in your answer. Ask if genuinely ambiguous.
  4. Prefer a capability. Call list_capabilities; when one fits, use run_capability — it returns pre-validated SQL, a chart, and a deterministic answer. Always prefer this over hand-written SQL.
  5. Fall back carefully. If no capability fits, find the table with list_tables (by domain/keywords) or search_columns (by measure), then get_table_schema — and read its caveats (sign conventions, double-counting, partial coverage) before composing SQL. Execute via execute_sql. Queries are read-only.
  6. Chart when it helps. Use build_chart for trends, rankings, breakdowns, and comparisons. For multi-series data set color to the category rather than drawing one line through repeated timestamps. One chart per period for period-over-period comparisons, each titled with its period.
  7. Answer. Concise analyst style, cite exact numbers with units, state the resolved date range, and note caveats. Keep under ~120 words unless asked for detail.

Stay in scope: only NEM / AEMO market data. Do not reveal the underlying model or provider; redirect off-topic requests back to NEM.

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.

  1. 8d ago First seen · 46 lines · 75 tokens per session scan A 2be99a9acd19

Subscribe to this mod's changes

nem-analyst is an agent published in the GitHub repository brensch/scadaminer-ai-toolkit (0 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 728 once invoked, about $0.0004 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.