AtlasBurn
Akhil Anand v1.0.2
Track and control AI spend
Save this plugin to Following and return to review observed changes. Follow up to 10 plugins free.
Description
From the marketplace listing
Connect AtlasBurn to see where your AI spend is going across models, providers, workflows, and agents. Ask ChatGPT to break down usage and costs, identify expensive requests or unusual spending patterns, investigate retries and costly agent behavior, and review forecasts and budget guardrails. AtlasBurn helps teams understand what is driving their AI costs and spot problems before they grow into larger bills. The connection is read-only and content-blind: it reads cost and usage telemetry from your AtlasBurn workspace, never changes your settings, and never sees your prompts or model outputs.
Language: English · Automatically detected from descriptions.
Competitor profile
From the developer’s listing and package; capabilities are not independently tested. Package observed Nov 3, 2026.
Declared capabilities
- Show total AI spend, token usage, and request volume
- Break down AI costs by model and product feature
- Forecast monthly AI bill, daily burn, and budget runway
Declared limitations
- General model pricing question unrelated to the user's own data; AtlasBurn tools should not be called.
- Request to change settings; AtlasBurn is read-only, so it should not attempt a change and should point the user to the AtlasBurn dashboard.
- Non-AI cloud spend that AtlasBurn does not track; AtlasBurn tools should not be called.
Review scenarios; not an exhaustive list.
Cost & access
Pricing and account requirements have not been established from the available package declarations. Unknown pricing does not mean free access.
Starter prompt
How much have we spent on AI in the last 30 days?
Keywords
Files & skills
File archives
Release notes
Initial release. AtlasBurn lets ChatGPT read your AI cost and economics data: total spend and token usage, cost broken down by model and feature, a runway and burn forecast, guardrail status with recent breaches, and runtime signals that flag runaway or looping agents. Read-only and content-blind: it never accesses your prompts or model outputs.
Declared in the saved package. Remote tools may change independently.
Package details
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
- Package author
- Akhil Anand
- Keywords
- See keywords
- Commerce declaration
- Does not support commerceThis does not establish whether access is free or paid.
- Review scenarios
- 5 positive · 3 negativeScenario counts, not test results.
Declared capabilities
- Show total AI spend, token usage, and request volume
- Break down AI costs by model and product feature
- Forecast monthly AI bill, daily burn, and budget runway
- Report guardrail status, budgets, and recent breaches
- Flag retry loops and runaway agent behavior
- Read-only: never changes settings or sees prompts and outputs
Package observed Nov 3, 2026.
Technical details
- First seen
- Oct 28, 2026 · 12:00 UTC
- Last seen
- Nov 3, 2026 · 18:00 UTC
- Collection status
- Collected
plugin_asdk_app_6ac510be5f1481918479513f5a24939e
Download plugin data (JSON)