cs

codespelunker - CLI code search tool that understands code structure and ranks results by relevance. No indexing required with CLI, TUI, MCP and HTTP support.

Runssource: GitHubGoMITcommit 7b9aa17f8c9f

Go, MIT licensed. The project labels itself: cli, code, command line tool, search and tui.

cs runs. An Argusic agent installed it in 9 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

The cs binary compiles, runs all three modes (CLI/HTTP/MCP), and passes the full test suite (4 test modules, all tests pass).

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

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.17 (measured)
recorded runs
2
last tested
stars
1,078
forks
23
open issues
2
watchers
6
size
19 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.

Install time
9 minutes
Cold machine to finish
5 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
go test ./... passed all test modules; cs --version returns 'cs version 3.2.0'; curl http://localhost:8081/ returned 200; cs 'func' CLI search returns ranked results with BM25 scoring
Model tokens used
99,649
Exact commit tested
7b9aa17f8c9f
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.

2026-11-19T13:20:37.280952Z ERROR codex_core::session: failed to record rollout items: thread 01a1f…
tokens used
99,649
Everything built and verified successfully. Here's the summary:
**Install:** Go 1.27.4 was downloaded from go.dev, extracted to `/home/runner/tools/go/`, and the `…
**Build output:** `cs` binary is 26 MB at `/work/repo/cs`, reports `cs version 3.2.0`.
**Verification:**
- CLI search: `cs "func"` returns rank-sorted results with snippets and BM25 scores
- HTTP server: `curl http://localhost:8081/` returned HTTP 200
- HTTP search: `/search?q=func&format=json` returned 20 ranked files
- MCP server: responds to `tools/list` with `search` and `get_file` tool schemas
- All tests pass: `go test ./...` — `ok` for all 4 test modules (main, ranker, search, snippet) wit…

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.
  • Nothing broke on the way: zero errors between clone and running.
  • 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.

What did not, or is not known

  • Took 9 minutes to install, slower than the median of the 127 comparable projects Argusic has measured.

Of the 128 cli projects Argusic has installed and timed, cs was the 103rd fastest to reach a running state, and 117 of 128 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 9 minutes after the clone.
  • Following its own README: the documented path worked with nothing to fix.

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 Runner2/3Runs100.000.17
Argusic Runner1/3Runs100.000.13

Topics (from GitHub)

clicodecommand-line-toolsearchtui

Embed the badge

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

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

Questions

Does cs run?
Yes. cs runs. Argusic installed and launched it on a clean machine in 9 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test cs?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7b9aa17f8c9f. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test cs?
The run that produced this verdict cost $0.17: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does cs take to install?
9 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 cs need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing cs?
Nothing did, in the recorded run: zero errors between clone and running.
How does cs compare with the alternatives?
Of the 128 cli projects Argusic has installed and timed, cs was the 103rd fastest to reach a running state, and 117 of 128 reached one at all.
Where is the evidence for cs?
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