dscode

A DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry

Runs with mockssource: GitHubhomepageJavaScriptMITcommit 2a94518ee0a5

JavaScript, MIT licensed. The project labels itself: agentic, ai agent, cli, code review, coding agent, deepseek, deepseek harness and developer tools.

dscode runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1.5 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Install and setup complete, 570/586 unit tests pass, dscode exec mode works end-to-end with mocked LLM, TUI app needs real TTY: this is a headless-container limitation, the binary itself is healthy

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

At a glance

verdict
Runs with mocks
Argusic Score
86 / 100
cost of the verifying run
$0.13 (measured)
recorded runs
2
last tested
stars
1,002
forks
6
open issues
3
watchers
0
size
8 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 dscode, 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.

  • 4 tests fail, 6 cancelled out of 586: version mismatch in vendored TUI @deepseek-ai/dsh-agent (0.1.5-rc.3 vs 0.1.7-alpha.2), trigger poll error message mismatch, and related TypeScript compilation5 minutes
  • Node.js v18.19.1 present, project requires ^22.19.0 || >=24.0.01 minute
  • npm ci failed: lockfile out of sync with package.json (dev checkout, not a release tarball)1 minute
  • TUI requires real TTY for Ink raw mode — cannot launch in headless container1 minute
Install time
2 minutes
Cold machine to finish
13 minutes
Errors hit and fixed
4 hit, 4 fixed with no human help
How the result was proved
DEEPSEEK_API_KEY=mock-key DEEPSEEK_BASE_URL=http://127.0.0.1:18999 node bin/dscode.mjs exec --quiet --approve-all --timeout 15 'What is 2+2?' returned 'The answer is 42.' with exit code 0
Model tokens used
341,951
Exact commit tested
2a94518ee0a5
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.

2026-10-11T08:20:55.355572Z ERROR codex_core::session: failed to record rollout items: thread 01a12…
2026-10-11T08:20:55.355613Z ERROR codex_core::session: failed to record rollout items: thread 01a12…
tokens used
341,951
Now I have the full picture. Let me compile the results:
**Installation**: Worked after fixing Node.js version (installed v22 via nvm) and using `npm instal…
**Test suite**: 570 pass, 4 fail, 6 cancelled out of 586. The 4 failures are pre-existing:
1. Version mismatch in vendored TUI dependencies (packages/tui uses 0.1.5-rc.3 vs root's 0.1.7-alph…
2. Trigger poll check error message mismatch
3-4. TypeScript compilation errors from those version mismatches
**App launch**: TUI requires real TTY (Ink raw mode), but `exec` mode works. Verified end-to-end wi…
Here's my final report:

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

  • Installed in 1.5 minutes, faster than the median of the 5 comparable projects Argusic has measured.
  • Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
  • 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

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.

Of the 6 agentic projects Argusic has installed and timed, dscode was the 1st fastest to reach a running state, and 3 of 6 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 Runner2/3Unverified80.000.20
Argusic Runner1/3Runs with mocks92.000.13

Topics (from GitHub)

agenticai-agentclicode-reviewcoding-agentdeepseekdeepseek-harnessdeveloper-toolsjevllmmacosmcpnodejsterminaltui

Embed the badge

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

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

Questions

Does dscode run?
dscode runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 2 minutes, hitting 4 errors on the way, and recorded the session.
How did Argusic test dscode?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 2a94518ee0a5. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test dscode?
The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does dscode take to install?
1.5 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 dscode need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing dscode?
4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does dscode compare with the alternatives?
Of the 6 agentic projects Argusic has installed and timed, dscode was the 1st fastest to reach a running state, and 3 of 6 reached one at all.
Where is the evidence for dscode?
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