pickfit

BrowseDeveloper CLIs

agent-inspect

Local-first toolkit to inspect TypeScript agent runs, check trajectories in CI, and share offline evidence.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: node>=20
  1. global install agent-inspect via npm

    npm install -g agent-inspect
  2. local npm install so demo import resolves

    npm init -y 2>&1 && npm install agent-inspect
Where the README and reality differ
  • README: npm install agent-inspect then npx agent-inspect init --yes then node examples/agent-inspect-demo.mjs
    What worked: ran npm init -y && npm install agent-inspect locally before node examples/agent-inspect-demo.mjs; global install alone leaves Cannot find package 'agent-inspect' (init prints No dependencies were installed)

Check that it works

agent-inspect --version 2>&1

The output should contain “6.31.30”.

First thing to try

agent-inspect init --yes && node examples/agent-inspect-demo.mjs && agent-inspect list --dir .agent-inspect
f=(.agent-inspect/run_*.jsonl); RUN=${f[0]##*/}; RUN=${RUN%.jsonl}; echo "RUN=$RUN" && agent-inspect view "$RUN" --dir .agent-inspect --summary

Run agent-inspect init --yes in your project, then agent-inspect list --dir .agent-inspect to see recorded runs.

What it does

  • Run repeatable trajectory checks in CI
    How to use it
    1. Find the run ID with agent-inspect list --dir .agent-inspect.
    2. Run agent-inspect check <run-id> --dir .agent-inspect --preset trajectory.
    3. Look for Trajectory: PASS in the output.
    Tested
  • Create offline evidence bundles you can share
    How to use it
    1. Run agent-inspect bundle <run-id> --dir .agent-inspect --profile share --out <folder>.
    2. Verify the bundle with agent-inspect bundle verify <folder>.
    Tested
  • Inspect agent execution trees on your machine
    Not shown working

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. 2 of 3 features work
  4. Works offline

Good for

  • read the execution path of a local agent run
  • fail CI on the wrong agent trajectory
  • create reviewable offline evidence bundle

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 6.31.30

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.