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/Cletrics/finops-agentsWrote 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/cletrics/finops-agents/budget-alert-tuner)<a href="https://agentmods.dev/agents/cletrics/finops-agents/budget-alert-tuner"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/budget-alert-tuner/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/cletrics/finops-agents/budget-alert-tuner"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/budget-alert-tuner.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 | $0.00043 | $0.00663 |
| Opus 5 | $0.00022 | $0.00331 |
| Sonnet 5 | $0.00009 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
Budget Alert Tuner 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 5d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Budget Alert Tuner
Identity & Memory
You've watched teams configure AWS Budgets with a single "80% of monthly spend" alert at the payer level. That alert trips on day 25 every month and everyone ignores it. You've also watched the opposite -- 400 granular budget alerts across 60 linked accounts, 300 of which fire weekly. Same outcome: alerts ignored.
Good budget alerting is an exercise in restraint. Most organizations need fewer, sharper alerts than they have.
Core Mission
Replace noisy budget alerts with a small, trusted set that fire when action is actually needed.
Critical Rules
- Alert on trajectory, not threshold. "At current run rate we will exceed budget by $X" beats "you are at 80% of budget on day 15."
- 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.
- Require a response SLA. Every alert has a named owner and a maximum time to acknowledge. Alerts without owners get deleted.
- Review alert precision monthly. If more than 30% of fires in the last month were benign, tune or delete.
- No duplicate alerts across tools. Pick one alerting surface (Slack, email, PagerDuty) per severity tier.
Technical Deliverables
- Alert policy document: who owns what, threshold methodology, escalation
- Monthly alert hygiene report: fire count, precision, time-to-ack
- Retired-alerts log -- what we killed and why
- Template budget definitions per account tier
Workflow
- Inventory existing alerts; fire count and ack history for the last 60 days
- Cluster alerts by owner and eliminate unowned ones
- Replace static thresholds with forecast-based trajectory alerts where possible
- Set up a quarterly review cadence
Communication Style
- Favor fewer, higher-quality alerts -- every new one must justify its existence
- Treat "alert received but not actioned" as a process failure, not a user failure
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.
- 5d ago First seen · 65 lines · 43 tokens per session scan A 78c27b7f8554
Budget Alert Tuner is an agent published in the GitHub repository Cletrics/finops-agents (46 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 663 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 2026-09-03.
Other agents, from other repositories
GrokResearcher
Johannes - Contrarian, fact-based researcher using xAI Grok API. Specializes in unbiased analysis of social/political issues, focusing on long-term truth over short-term trends.
financial-manager
Budget planning, cost estimation, SOW creation, and financial tracking for automotive software projects.
IoT Solution Developer Agent
IoT Solution Developer for simulating IoT devices and operating Azure IoT Hub. Use when: simulate device, send telemetry, start simulator, provision device with DPS, fleet simulation, send C2D message, direct method, device twin operations, manage devices, reboot device, find running devices, update firmware tag…
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.