3 findingsStatic scanned
Runs OpenAI's Codex coding agent locally on your computer from the command line.
71.3M installs/moApache-2.0
Contextlab
kaushal_shahare · Agent
Contextlab runs your AI coding agent through a local proxy and records what each turn sends, so you can see what is filling the context window. It ranks the waste, such as a large tool result that is re-sent on every turn, and gives the configuration change that would remove it. You can also look at historical spend by day or project, watch a live context gauge, and open a web dashboard on localhost. It works offline with no account, cloud or telemetry, and no language model is called. Codex, Cline and OpenCode also need mitmproxy installed.
Written by ooruby from the README of contextlab 0.1.4.
Not claimed by its maker. Is this yours? Prove it and answer the findings
Why it's useful
Agents report only a token total and a price, and this shows which parts of the history account for it and what to change.
What you could do with it
- Run your coding agent through contextlab, then ask which earlier output keeps being re-sent on every turn.
- After a costly turn, ask contextlab why it was expensive.
- Review historical spend by day or project and watch a live context gauge in the terminal.
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 (src/commands/dashboard.js:11)
- node child_process (src/commands/doctor.js:11)
- synchronous shell execution (src/commands/doctor.js:241)
- synchronous shell execution (src/commands/doctor.js:264)
- 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
See what is actually filling your AI coding agent's context window — and what to change to fix it.
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 0.1.4, the file with digest sha512-/F4jOJcPIdxu0j2JxXsTPMt2aX4lxWA42rXnW4+vPqxyCDQ/FZSukowfWmBgO+C0lH7/fjJdr+aYQWnFBJ79ug==, 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 contextlab@0.1.4Pinned to 0.1.4, 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
- contextlab
- Version read
- 0.1.4
- 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/contextlab)About this listing
- Kind
- Agent
- Category
- Developer tools
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-05
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.