paul

Plan-Apply-Unify Loop, Structured AI-assisted development for Claude Code. Quality over speed-for-speed's-sake.

Could not verifysource: GitHubhomepageJavaScriptMITcommit f8552c72d0e6

JavaScript, MIT licensed. The project labels itself: ai development, ai tools, claude, claude code, development framework, project orchestration, spec driven and vibe coding.

Argusic could not get paul running. An Argusic agent installed it in 2 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

The PAUL Framework installer deploys 97 markdown files (28 commands, 27 templates, 23 workflows, 14 references, 5 rules) to a .claude/ directory with correct path replacements, across local, global, and custom-config install modes; the --help flag prints usage; all error cases exit with proper error messages.

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

verdict
Could not verify
Argusic Score
80 / 100
cost of the verifying run
$0.04 (measured)
recorded runs
2
last tested
stars
1,275
forks
144
open issues
11
watchers
14
size
0 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.

Install time
2 minutes
Cold machine to finish
3 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
node bin/install.js --local deployed 97 files to .claude/; node bin/install.js --global deployed 97 files to ~/.claude/; node bin/install.js --config-dir /tmp/paul-custom --global deployed 97 files to /tmp/paul-custom/; interactive mode (echo 1 | node bin/install.js) printed Done; node bin/install.js --help printed usage banner; all path replacements (~/.claude/ to ./.claude/ or custom path) confirmed in installed files; all 3 error cases exit with proper messages
Model tokens used
57,268
Exact commit tested
f8552c72d0e6
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
Whether it works at all
this run verified nothing, so this page makes no claim either way

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

### What was verified
- **4 install modes** — `--local`, `--global`, `--config-dir <path>`, and interactive (prompt)
- **97 files deployed** per mode (28 commands, 27 templates across 2 dirs, 23 workflows, 14 referen…
- **Path replacement** — `~/.claude/` references in source files correctly rewritten to `./.claude/…
- **`--help`** prints the full usage banner
- **All 3 error cases** — `--global --local` conflict, `--config-dir` with `--local`, missing `--co…
- **`npm pack`** produces a valid tarball (179 KB, 101 files)
- **`npm install -g`** works (with `--prefix` since `/usr/local` is not writable)
### What couldn't be tested
- No test suite exists in the repository
- No app to launch — the project is a Claude Code extension (markdown-based commands and workflows)
- No third-party keys or mocks needed

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 2 minutes.
  • Nothing broke on the way: zero errors between clone and running.
  • 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

  • An agent with no time limit did not get it running.

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 Runner2/3Unverified80.000.04
Argusic Runner1/3Unverified80.000.08

Topics (from GitHub)

ai-developmentai-toolsclaudeclaude-codedevelopment-frameworkproject-orchestrationspec-drivenvibe-coding

Embed the badge

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

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

Questions

Does paul run?
Argusic could not verify that paul runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test paul?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit f8552c72d0e6. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test paul?
The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does paul take to install?
2 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 paul need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing paul?
Nothing did, in the recorded run: zero errors between clone and running.
Where is the evidence for paul?
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