delegate-skills
Delegate a coding task to a separate coding agent CLI, review the diff, land the commit yourself, one per implementer.
Runssource: GitHubhomepageJavaScriptMITcommit 6826b363085d
JavaScript, MIT licensed. The project labels itself: agent skills, ai coding agent, antigravity, claude code, claude code skills, codex, coding agent and cursor.
delegate-skills runs. An Argusic agent installed it in 12 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The delegate-skills package installs all 18 skills, the test suite passes all checks against fake CLI shims, and the POSIX shim no longer depends on the external dirname command.
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
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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- The npx skills CLI command requires Node >=22.20.0 but the container ships Node 18.19.12 minutes
- POSIX fake-CLI shim in test/harness/install-shim.mjs used external dirname command which fails when PATH is stripped in grok Git-unavailable test1 minute
- Install time
- 12 minutes
- Cold machine to finish
- 30 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- All 24 relay-smoke modules run individually (syntax, package-shape, codex, cline, agy, cursor, vibe, opencode, aider, claude, copilot, commandcode, zcode, grok-git-trust, read-only-tripwire, timeout-tree, abort, orphan-stdio, delegate-setup, preflight, atomic, timeout-bounds, qoder, pi, omp) plus relay-parity (46/46), event-scanner (23/23), and relay-isolated (17/17), all green
- Model tokens used
- 108,446
- Exact commit tested
- 6826b363085d
- 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.
ok syntax: zcode-delegate/scripts/relay.mjs ok syntax: commandcode-delegate/scripts/relay.mjs relay smoke: all green EXIT: 0 Now I have comprehensive results. Here's the final assessment: 2026-10-04T02:44:04.405684Z ERROR codex_core::session: failed to record rollout items: thread 01a10… 2026-10-04T02:44:04.405725Z ERROR codex_core::session: failed to record rollout items: thread 01a10… 2026-10-04T02:44:04.405744Z ERROR codex_core::session: failed to record rollout items: thread 01a10… 2026-10-04T02:44:04.405754Z ERROR codex_core::session: failed to record rollout items: thread 01a10… tokens used 108,446 Now I have comprehensive results. Here's the final assessment:
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.
- Recovered from all 2 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.
What did not, or is not known
- Took 12 minutes to install, slower than the median of the 33 comparable projects Argusic has measured.
Of the 34 agent-skills projects Argusic has installed and timed, delegate-skills was the 30th fastest to reach a running state, and 25 of 34 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.
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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 100.00 | 0.10 | |
| Argusic Runner | 1/3 | Ran out of time | 0.00 | 0.60 |
Topics (from GitHub)
agent-skillsai-coding-agentantigravityclaude-codeclaude-code-skillscodexcoding-agentcursorgrokkimimistralopenai-codexopencodeqoderskills-sh
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/delegate-skills)Questions
- Does delegate-skills run?
- Yes. delegate-skills runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test delegate-skills?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6826b363085d. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test delegate-skills?
- The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does delegate-skills 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 delegate-skills need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing delegate-skills?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does delegate-skills compare with the alternatives?
- Of the 34 agent-skills projects Argusic has installed and timed, delegate-skills was the 30th fastest to reach a running state, and 25 of 34 reached one at all.
- Where is the evidence for delegate-skills?
- 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.