sudocode

Lightweight agent orchestration dev tool that lives in your repo

Runs with mockssource: GitHubhomepageTypeScriptApache-2.0commit 632de1910bc4

TypeScript, Apache-2.0 licensed. The project labels itself: agents, ai, automation, claude code, cli, coding agents, mcp and mcp server.

sudocode runs, with stand-ins for the services it depends on. An Argusic agent installed it in 12 minutes and hit 8 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

CLI builds and all core commands work end-to-end for spec and issue management. Test runner (vitest) crashes with bus error on Node 18. Server fails to start due to ESM module resolution issues. Frontend has pre-existing TypeScript errors. Project requires Node >=20 for full compatibility.

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
$0.43 (measured)
recorded runs
1
last tested
stars
296
forks
28
open issues
12
watchers
2
size
29 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 sudocode, 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.

  • Vitest test runner crashes with bus error (SIGBUS=135) on Node 185 minutes
  • Server cannot start due to ESM resolution on Node 18 (async-mutex, iconv-lite)3 minutes
  • sudocode meta-package bin links break install (ENOENT on chmod dist/cli.js)2 minutes
  • CLI: @types/[email protected] fetch Response type mismatches Node 18 global fetch; @types/[email protected] too old for chokidar v42 minutes
  • Frontend: @testing-library/jest-dom not installed in workspace; tsc types referenced it2 minutes
  • Server: pre-existing strict typing errors1.5 minutes
Install time
12 minutes
Cold machine to finish
36 minutes
Errors hit and fixed
8 hit, 8 fixed with no human help
How the result was proved
node cli/dist/cli.js --version returned 0.2.0; init succeeded; spec create/list returned valid JSON; issue create/list returned valid JSON; link created relationships; status --json returned correct counts; export produced valid markdown files. All CLI functional workflows verified.
Model tokens used
337,052
Exact commit tested
632de1910bc4
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.

priority: 2
created_at: '2026-10-25 23:13:09'
status: open
exec
/bin/sh -lc 'cd /work/repo && echo "engine-strict=true" > .npmrc' in /work/repo
 succeeded in 0ms:
exec
/bin/sh -lc 'cat /work/repo/.npmrc' in /work/repo
 succeeded in 0ms:
engine-strict=true
tokens used
337,052

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 8 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed Apache-2.0, 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 40 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 41 agents projects Argusic has installed and timed, sudocode was the 29th fastest to reach a running state, and 29 of 41 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 mocks92.000.43

Topics (from GitHub)

agentsaiautomationclaude-codeclicoding-agentsmcpmcp-servermulti-agenttypescriptvibe-engineeringworkflows

Embed the badge

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

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

Questions

Does sudocode run?
sudocode runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 12 minutes, hitting 8 errors on the way, and recorded the session.
How did Argusic test sudocode?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 632de1910bc4. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test sudocode?
The run that produced this verdict cost $0.43: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does sudocode 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 sudocode need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing sudocode?
8 things broke in the recorded run, and 8 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does sudocode compare with the alternatives?
Of the 41 agents projects Argusic has installed and timed, sudocode was the 29th fastest to reach a running state, and 29 of 41 reached one at all.
Where is the evidence for sudocode?
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