3 findingsStatic scanned
Runs OpenAI's Codex coding agent locally on your computer from the command line.
71.3M installs/moApache-2.0
AI Usage Inspector
mahmoud_helmy · Agent
AI Usage Inspector registers a hook with each coding agent it finds and records every prompt: tokens, model, mode, context fill and cost, priced from published rates or taken from the agent when it reports its own. Records live in the project they came from, and each project gets its own dashboard with provider filters, charts, full-text search and export. Subagent runs appear as a tree under the prompt that launched them. It suits people who run several coding agents and want to see what each prompt used.
Written by ooruby from the README of ai-usage-inspector 2.11.2.
Not claimed by its maker. Is this yours? Prove it and answer the findings
Why it's useful
Your coding agents spend tokens on every prompt, and this records what each one used in the project where it happened.
What you could do with it
- Open a project's dashboard and compare token use and cost across the coding agents you run.
- Turn off recording of prompt text for a project while still keeping tokens, model and cost.
- Set a monthly budget and export the recorded prompts as CSV or JSON.
Written from its documentation: what it says it can do, not what our checks found.
Maintenance
Not measuredNo release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.
Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured
- Command execution is bounded
- inventory
- node child_process (install.mjs:28)
- synchronous shell execution (install.mjs:300)
- synchronous shell execution (install.mjs:348)
- node child_process (viewer/launch.mjs:18)
- An inventory of where the code starts another program, not a verdict on this row: whether each one runs a fixed program or whatever it is handed takes a reading by hand.
Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.
What this does not cover
- Everything. Treat it as you would software from anywhere else.
Receipt history: every signed receipt for every version of this listing, and what changed between them.
In its maker's words
Zero-dependency tool that records every AI coding-agent prompt (tokens, model, mode, cost, context %) from Claude Code, OpenAI Codex, Cursor, OpenCode, and VS Code agents (Cline, Roo Code, Kilo Code), and shows it in a local dashboard.
Compare with
Compare all 4How far this has been checked
Static scanned
- What it establishes
- Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
- What it does not
- How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
- Exactly what was read
- Version 2.11.2, the file with digest sha512-8a5cuGybxLZn2JlyKFZTWkqR07WSSZrzdQx5krMSwVVQsY68hrCotFVTV4AHxWA92KYVhgbCTuYLCyuthBxsGA==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
- Authentication
- Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
Adding it
Run it with:
npx -y ai-usage-inspector@2.11.2Pinned to 2.11.2, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.
Where this came from
- Registry
- npm
- Package
- ai-usage-inspector
- Version read
- 2.11.2
- Resolved
- 2026-10-10
No build provenance published. The repository above is the one the publisher declared, and nothing links it to the package you would install. That is not a mark against this listing, since most packages are published this way, but it is a check nobody can run.
The badge, if this is your listing
It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.
[](https://ooruby.com/market/ai-usage-inspector)About this listing
- Kind
- Agent
- Category
- Developer tools
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-06
Similar agents
All agentsVerification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.