session-kit

Close the terminal windows, not the AI coding sessions. One number takes you back in. Every Claude Code and Codex session in one menu: named, numbered, colour-coded. Open, close, and jump to whichever needs you.

Runs with mockssource: GitHubPythonMITcommit 3978d9845d6c

Python, MIT licensed. The project labels itself: ai coding, claude code, cli, codex, developer tools, linux, macos and session manager.

session-kit runs, with stand-ins for the services it depends on. An Argusic agent installed it in 12 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Session Kit installed and CLI commands verified; shpool 0.11.0 built from source; all helper binaries deployed to ~/.local/bin/; 31/45 doctor checks pass (remaining non-ok due to container without systemd)

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.26 (measured)
recorded runs
1
last tested
stars
464
forks
30
open issues
0
watchers
2
size
6 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing session-kit, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • shpool not on PATH; preflight failed11 minutes
  • systemd user manager unavailable (container without systemd init)1 minute
Install time
12 minutes
Cold machine to finish
55 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
sp list exits 0 with Sessions: none.; sp help prints complete reference; session-kit doctor --json returns valid output with 31/45 checks ok; 535+ tests pass across 20+ test modules
Model tokens used
184,348
Exact commit tested
3978d9845d6c
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

 succeeded in 0ms:
/bin/sh: 1: true,: not found
Done
exec
/bin/sh -lc "printf 'ARGUSIC_RESULT: %s\\n' '{\"install_succeeded\": true, \"launch_succeeded\": tr…
 succeeded in 0ms:
exec
/bin/sh -lc 'export PATH="$HOME/.cargo/bin:$HOME/.local/bin:$PATH" && cd /work/repo && timeout 30 p…
2026-10-17T11:10:49.345190Z ERROR codex_core::session: failed to record rollout items: thread 01a14…
2026-10-17T11:10:49.345235Z ERROR codex_core::session: failed to record rollout items: thread 01a14…
tokens used
184,348

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Took 12 minutes to install, slower than the median of the 6 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 7 ai-coding projects Argusic has installed and timed, session-kit was the 7th fastest to reach a running state, and 6 of 7 reached one at all.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks92.000.26

Topics (from GitHub)

ai-codingclaude-codeclicodexdeveloper-toolslinuxmacossession-managershpoolsshterminaltui

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/session-kit.svg)](https://argusic.com/subject/session-kit)

Questions

Does session-kit run?
session-kit runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 12 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test session-kit?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3978d9845d6c. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test session-kit?
The run that produced this verdict cost $0.26: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does session-kit take to install?
12 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does session-kit need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing session-kit?
2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does session-kit compare with the alternatives?
Of the 7 ai-coding projects Argusic has installed and timed, session-kit was the 7th fastest to reach a running state, and 6 of 7 reached one at all.
Where is the evidence for session-kit?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion