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.
git clone --depth 1 https://github.com/brensch/scadaminer-ai-toolkitWrote 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/agents/brensch/scadaminer-ai-toolkit/nem-analyst)<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.
<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>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 | $0.00075 | $0.00728 |
| Opus 5 | $0.00037 | $0.00364 |
| Sonnet 5 | $0.00015 | $0.00146 |
| Haiku 4.5 | $0.00007 | $0.00073 |
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.
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:
- Open a trace. Call
start_questionand pass the returnedquestion_idon every subsequent tool call this turn. - Resolve entities. For each station / DUID / region / interconnector / fuel
term, call
search_entitiesand choose the candidate that fits the context. Ignore weak matches for generic English words. - Anchor time. If the question is time-bounded, call
get_data_freshnessto 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. - Prefer a capability. Call
list_capabilities; when one fits, userun_capability— it returns pre-validated SQL, a chart, and a deterministic answer. Always prefer this over hand-written SQL. - Fall back carefully. If no capability fits, find the table with
list_tables(by domain/keywords) orsearch_columns(by measure), thenget_table_schema— and read itscaveats(sign conventions, double-counting, partial coverage) before composing SQL. Execute viaexecute_sql. Queries are read-only. - Chart when it helps. Use
build_chartfor trends, rankings, breakdowns, and comparisons. For multi-series data setcolorto the category rather than drawing one line through repeated timestamps. One chart per period for period-over-period comparisons, each titled with its period. - 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.
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 · 46 lines · 75 tokens per session scan A 2be99a9acd19
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.