inshellisense

IDE style command line auto complete

Runssource: GitHubTypeScriptMITcommit 63872c52ebc8

TypeScript, MIT licensed. The project labels itself: autocomplete, bash, cli, fish, linux, macos, nushell and powershell.

inshellisense runs. An Argusic agent installed it in 2 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Dependencies install, tsc build and lint pass, 202 unit tests pass, 'is doctor' reports all checks green after 'is init bash', 'is complete' returns real spec suggestions, and the interactive inshellisense session on bash launches, renders suggestions, runs commands and exits cleanly; only the fish/zsh e2e variants and one flaky truncation e2e case could not be verified here.

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 95 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
95 / 100
cost of the verifying run
$0.36 (measured)
recorded runs
2
last tested
stars
10,777
forks
266
open issues
12
watchers
21
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 inshellisense, 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.

  • Full e2e suite produced no output and timed out because it also spawns fish and zsh, which are not installed in this container22 minutes
  • Jest suite failed: 'No such built-in module: node:sea' when src/utils/node.ts imported node:sea statically on Node v18.19.16 minutes
  • e2e color assertion failed: expected bg #7d56f4 but terminal reported #8787ff (chalk downgraded truecolor)5 minutes
  • npm link failed with EACCES writing to root-owned /usr/local4 minutes
  • 'proper overflow truncation in command' e2e test timed out when run concurrently, reporting only 'do' typed4 minutes
  • npm run test:e2e failed with 'Cannot find module @microsoft/tui-test-linux-x64-gnu' because the optional native package was not installed3 minutes
Install time
2 minutes
Cold machine to finish
48 minutes
Errors hit and fixed
6 hit, 6 fixed with no human help
How the result was proved
npm test exited 0 with '14 passed, 1 skipped, 202 passed, 10 skipped, 93 snapshots'; npm run build and npm run lint exited 0; 'is doctor' exited 0 printing four green checks; 'is complete "git sta"' returned JSON suggestions stage/status/stash; an interactive 'node build/index.js -s bash -T' PTY session typed suggestions, executed 'echo FINAL_OK' which printed FINAL_OK, and exited 0; e2e src/tests/ui/status.test.ts passed 2/2 and the bash autocomplete e2e group passed 13/14
Model tokens used
245,806
Exact commit tested
63872c52ebc8
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

The end of the recording

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

FINAL_OK
> exit
exit
c
Verification complete. Summary of what I did and observed:
**Fixed issue:** `src/utils/node.ts` used a static `import sea from "node:sea"`, which does not exi…
**Other gaps found and handled:** the e2e harness's optional native package `@microsoft/tui-test-li…
tokens used
245,806
Verification complete. Summary of what I did and observed:
**Fixed issue:** `src/utils/node.ts` used a static `import sea from "node:sea"`, which does not exi…
**Other gaps found and handled:** the e2e harness's optional native package `@microsoft/tui-test-li…

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

  • Reached a running state on a clean machine, with the session recorded.
  • Installed in 2 minutes, faster than the median of the 3 comparable projects Argusic has measured.
  • Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

Of the 4 autocomplete projects Argusic has installed and timed, inshellisense was the 1st fastest to reach a running state, and 4 of 4 reached one at all.

What it is a reasonable choice for

  • Trying it on a laptop or a small server: it reached a running state without a GPU.
  • A quick evaluation: it was running 2 minutes after the clone.

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 Runner2/3Runs100.000.36
Argusic Runner1/3Runs90.000.04

Topics (from GitHub)

autocompletebashclifishlinuxmacosnushellpowershellpwshterminalwindowsxonshzsh

Embed the badge

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

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

Questions

Does inshellisense run?
Yes. inshellisense runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 6 errors on the way, and recorded the session.
How did Argusic test inshellisense?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 63872c52ebc8. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test inshellisense?
The run that produced this verdict cost $0.36: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does inshellisense take to install?
2 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 inshellisense need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing inshellisense?
6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does inshellisense compare with the alternatives?
Of the 4 autocomplete projects Argusic has installed and timed, inshellisense was the 1st fastest to reach a running state, and 4 of 4 reached one at all.
Where is the evidence for inshellisense?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion