pstack-claude

Antigravity, Claude Code, Codex, Copilot, Gemini, Muse, OpenCode, Pi, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.

Runssource: GitHubJavaScriptMITcommit c02fd4922b25

JavaScript, MIT licensed. The project labels itself: agent plugin, agent skills, agentic ai, anthropic, antigravity skills, chatgpt, claude and claude code.

pstack-claude runs. An Argusic agent installed it in 5 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

pstack plugin v0.9.45 is installed, enabled, and registered in Codex 0.167.0; the SessionStart hook injects pstack routing; all 54 skill directories are discoverable; the generator, bun test suite (227/227), and vendored scripts (118/118) all pass; codex exec successfully invoked pstack:poteto-mode through the real model endpoint

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
$0.08 (measured)
recorded runs
2
last tested
stars
4,615
forks
428
open issues
13
watchers
9
size
6 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 pstack-claude, 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.

  • bun binary not installed in the container1.5 minutes
  • bubblewrap kernel-level namespace restriction blocks codex exec --sandbox read-only0.1 minutes
Install time
5 minutes
Cold machine to finish
8 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
bun test tests/ ran 227 pass 0 fail; bun test orch watch-pr ran 118 pass 0 fail; codex exec session with --dangerously-bypass-hook-trust fired SessionStart hook injecting pstack routing, then invoked pstack:poteto-mode skill which read VERSION and returned {"skill":"pstack:poteto-mode","version":"0.9.45"} via real local OpenRouter endpoint at 127.0.0.1:8787
Model tokens used
213,677
Exact commit tested
c02fd4922b25
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.

tokens used
213,677
All checks pass. Now I have the complete picture — here's the final result:
**What was done:**
- Installed `bun` 1.3.14 (missing from container)
- Registered local marketplace + installed `pstack@pstack-claude` into Argusic Agent 0.167.0
- Ran the generator (`bun tools/generate.mjs`) — 15 checks, clean tree
- Ran `bun test tests/` — **227 pass, 0 fail**
- Built and tested vendored scripts (`bun install --frozen-lockfile`, `bun run typecheck`, `bun tes…
- Verified skills-only symlink install (diff passes)
- Launched a Argusic Agent exec session with hook trust: `SessionStart` hook fires and injects the …
- Demonstrated real skill invocation: the model invoked `pstack:poteto-mode`, read `/work/repo/VERS…

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 5 minutes to install, slower than the median of the 126 comparable projects Argusic has measured.

Of the 127 agent-skills projects Argusic has installed and timed, pstack-claude was the 86th fastest to reach a running state, and 96 of 127 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 5 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.08
Argusic Runner1/3Runs100.000.03

Topics (from GitHub)

agent-pluginagent-skillsagentic-aianthropicantigravity-skillschatgptclaudeclaude-codeclaude-code-skillsclaude-pluginclaude-skillscode-reviewcodexcodex-clicodex-plugincodex-skillsgemini-climuse-pluginopencodepstack

Embed the badge

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

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

Questions

Does pstack-claude run?
Yes. pstack-claude runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test pstack-claude?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit c02fd4922b25. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test pstack-claude?
The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does pstack-claude take to install?
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 pstack-claude need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing pstack-claude?
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 pstack-claude compare with the alternatives?
Of the 127 agent-skills projects Argusic has installed and timed, pstack-claude was the 86th fastest to reach a running state, and 96 of 127 reached one at all.
Where is the evidence for pstack-claude?
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