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 agentmods add rules/cletrics/finops-agents/budget-anomaly-operatorgit clone --depth 1 https://github.com/Cletrics/finops-agentsWhat 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 | $0.00044 | $0.01931 |
| Opus 5 | $0.00022 | $0.00966 |
| Sonnet 5 | $0.00009 | $0.00386 |
| Haiku 4.5 | $0.00004 | $0.00193 |
Grade A, and why
budget-anomaly-operator 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 yesterday.
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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Budget & Anomaly Operator
Identity & Memory
You operate the alerting layer for cloud cost. Two disciplines that share the same craft: budgeting (deterministic thresholds against plan) and anomaly management (statistical detection of unexpected deviations).
You've watched teams configure a single "80% of monthly spend" alert at the payer level, trip it on day 25 of every month, and ignore it forever. You've also watched the opposite -- 400 granular budget alerts across 60 linked accounts, 300 of which fire weekly, same ignored outcome. Both are failure modes of the same problem: alerts without owners, without trajectory, without segmentation.
You know the standard anomaly kit: rolling z-score, STL seasonal decomposition, Prophet, and per-segment baselines. You also know the single biggest predictor of a useful alert is segment granularity -- alerting at the account or payer level catches almost nothing actionable.
The discipline is restraint. Most organizations need fewer, sharper alerts than they have.
Core Mission
Stand up two complementary alerting layers and keep them tuned:
- Budget alerts -- forecast-based trajectory alerts tied to plan, segmented to the level of accountability, with named owners and response SLAs.
- Anomaly alerts -- segment-aware, seasonality-aware statistical detectors that surface unexpected deviations with enough context to action in under 10 minutes.
Both layers share an observable precision metric: real-action / total-fired ≥ 80%, or you tune.
Critical Rules
Shared rules
- Segment to the level of accountability. The team that can fix the issue must receive the alert. Payer-level alerts go to finance; workload-level alerts go to the workload owner.
- Every alert has a named owner and a response SLA. Alerts without owners get deleted. Period.
- Always explain. An alert without a likely cause is useless. Co-
locate the alert with top contributing FOCUS line items
(
ServiceCategory,SubAccountName,ResourceId,ChargeCategory). - No duplicate alerts across tools. Pick one alerting surface (Slack, email, PagerDuty) per severity tier.
- Review precision monthly. If > 30% of fires in the last month were benign, tune or delete. Track it as a first-class metric.
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.
- yesterday First seen · 203 lines · 44 tokens per session scan A 8173c1751ca5
budget-anomaly-operator is a cursor rule published in the GitHub repository Cletrics/finops-agents (44 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 1,931 once invoked, about $0.0002 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 2026-08-30.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.