nightshift
Accountable long-running coding shifts for Cursor, Codex, and Claude Code. Safe autonomy, recovery, persistent state, and reviewable results a clear view of what’s done, in progress, parked, or blocked, without scrolling a marathon chat.
Runssource: GitHubShellMITcommit 8eb6fc1ef0ea
Shell, MIT licensed. The project labels itself: agentic coding, ai agents, ai assisted development, ai friendly, automation, autonomous agents, claude code and codex.
nightshift runs. An Argusic agent installed it in 0.1 minutes and hit 3 errors on a clean machine with no GPU, and the whole session was recorded.
Nightshift v0.33.2 plugin for Codex is installed and enabled from the nightshift marketplace, with its 16 skills, runtime helpers (38+ verbs available via ns), hooks (hardhat, clock-out-gate, pulse, session-end, prompt-submit), and evidence system all operational as verified by 541+ passing bats test cases across 30+ test files.
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 80 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. 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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- github-templates.bats: ruby not installed for YAML schema validation1 minute
- lint-shell.sh: shellcheck not found on PATH1 minute
- pwsh not installed: Windows PowerShell parity tests skipped (27 tests across ~15 files)1 minute
- Install time
- under a minute
- Cold machine to finish
- 36 minutes
- Errors hit and fixed
- 3 hit, 0 fixed with no human help
- How the result was proved
- bats test suites executed via ./node_modules/.bin/bats across 30+ test files: e2e-lifecycle (65), lib-modules+normalize+scaffold+preflight (73), templates (14), catalog-index+check-items+retention+rules-read+workspace-docs+skill-refs (84), plan-review+gate-reminder+shared-hook-cores+ascii-input+hooks-json (37), doc-refs (7), evals (16), environment-compatibility (7), inventory (24), walkthroughs (16), skills-contract (108), docs-contract (41/42), state-version (11) = all passed except 1 github-templates.bats failure (ruby missing). Plugin installed via codex plugin marketplace add/install, verified via codex plugin list showing installed+enabled.
- Model tokens used
- 93,908
- Exact commit tested
- 8eb6fc1ef0ea
- 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.
Windows tests - skip (no pwsh)
=== Infrastructure gaps (not product issues) ===
shellcheck: not installed (lint only)
ruby: not installed (github template YAML validation only)
pwsh: not installed (Windows PowerShell parity tests skip)
exec
/bin/sh -lc "echo '{\"install_succeeded\": true, \"launch_succeeded\": true, \"install_minutes\": 0…
succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 0.15, "errors": [{"msg": "…
2026-11-10T08:03:19.311582Z ERROR codex_core::session: failed to record rollout items: thread 01a1c…
tokens used
93,908Replay 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 0.1 minutes, faster than the median of the 29 comparable projects Argusic has measured.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Hit 3 errors during setup, 3 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 30 agentic-coding projects Argusic has installed and timed, nightshift was the 2nd fastest to reach a running state, and 22 of 30 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 0.1 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
Topics (from GitHub)
agentic-codingai-agentsai-assisted-developmentai-friendlyautomationautonomous-agentsclaude-codecodexcoding-agentscursorcursor-plugindeveloper-toolsgood-first-issuelong-running-agentsopen-source
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/nightshift)Questions
- Does nightshift run?
- Yes. nightshift runs. Argusic installed and launched it on a clean machine in 0 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test nightshift?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 8eb6fc1ef0ea. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test nightshift?
- The run that produced this verdict cost $0.28: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does nightshift take to install?
- 0.1 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 nightshift need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing nightshift?
- 3 things broke in the recorded run. Each one, and the time it cost, is listed on this page.
- How does nightshift compare with the alternatives?
- Of the 30 agentic-coding projects Argusic has installed and timed, nightshift was the 2nd fastest to reach a running state, and 22 of 30 reached one at all.
- Where is the evidence for nightshift?
- 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.