Runs OpenAI's Codex coding agent locally on your computer from the command line.
Agent Inspect
rajudandigam · Agent
AgentInspect is a local debugger and test kit for AI agents written in TypeScript. It records each run as a local trace, shows it as a readable tree of the agent's steps, and checks it against rules such as which tools must be called, so a CI job fails when the agent takes the wrong path. It works with custom code, LangChain and LangGraph, the AI SDK, OpenAI Agents JS and existing logs, and can package a redacted bundle with file hashes to attach to a pull request.
Written by ooruby from the README of agent-inspect 6.31.17.
Not claimed by its maker. Is this yours? Prove it and answer the findings
Why it's useful
Flat logs show only fragments of what an agent did, while this keeps the whole run as one local trace you can debug, test and share.
What you could do with it
- Add a CI check that fails whenever an agent run skips a tool it is required to call.
- Open the trace of a failed run as an execution tree and follow each tool and model call.
- Bundle a redacted copy of a run with a manifest and attach it to a pull request or incident.
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
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
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents — execution trees, TraceContract checks, Evidence v2, and read-only MCP
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 6.31.17, the file with digest sha512-TBTnuiqg7V3FrYZle2SO3mc+KrAdywbSCe1vaw4qeP+0z/oTNYq7VRuE0AwR1a06pnV2YyBs0aHNI7iiGQjDuw==, 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 agent-inspect@6.31.17Pinned to 6.31.17, 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
- agent-inspect
- Version read
- 6.31.17
- Resolved
- 2026-10-09
Built from source, attested
npm publishes a signed statement that this exact package was built from the repository below, at this commit. It is verifiable without taking our word for it.
- Repository
- github.com/rajudandigam/agent-inspect
- Commit
- 071de49d66ae
- Built by
- github.com/actions/runner/github-hosted
- Registry publish attestation
- signed by npm · 2026-10-10
- Checked
- 2026-10-10
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/agent-inspect)About this listing
- Kind
- Agent
- Category
- Developer tools
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-07
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.