pg-aiguide
MCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better PostgreSQL code.
Runssource: GitHubPythonApache-2.0commit b236d3583fb5
Python, Apache-2.0 licensed. The project labels itself: ai, ai agents, ai coding, claude code plugin, claude code plugins, claude code plugins marketplace, claude marketplace and claude plugin.
pg-aiguide runs. An Argusic agent installed it in 3 minutes and hit 2 errors on a clean machine with no GPU, and the whole session was recorded.
bun i installs 356 packages, tsc -p tsconfig.build.json compiles to dist/, bun test runs 66 passing tests, bun run validate-skills validates all 10 skills, and ./check passes (skipping Python checks for missing uv)
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 90 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 ./bun wrapper script tried to download bun via curl|bash but 'unzip' is not available in the container, so the download step failed silently1 minute
- PostgreSQL is not installed; apt-get requires root which is not available
- Install time
- 3 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 2 hit, 1 fixed with no human help
- How the result was proved
- bun test exited 0, 66 pass, 0 fail, 92 expect calls across 7 files
- Model tokens used
- 60,500
- Exact commit tested
- b236d3583fb5
- 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.
bun version: 1.4.2 node version: v18.19.1 test count: 67 build output: 6 All systems verified. Here's the complete result: **Summary:** The repository works as a brand-new user would see it. Dependencies install, the TypeS… tokens used 60,500 All systems verified. Here's the complete result: **Summary:** The repository works as a brand-new user would see it. Dependencies install, the TypeS…
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.
- Installed in 3 minutes, faster than the median of the 90 comparable projects Argusic has measured.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Hit 2 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 91 ai projects Argusic has installed and timed, pg-aiguide was the 25th fastest to reach a running state, and 64 of 91 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 3 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)
aiai-agentsai-codingclaude-code-pluginclaude-code-pluginsclaude-code-plugins-marketplaceclaude-marketplaceclaude-pluginclaude-skillsdocsdocumentationmcpmcp-serverpostgrespostgresqlskills
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/pg-aiguide)Questions
- Does pg-aiguide run?
- Yes. pg-aiguide runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test pg-aiguide?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit b236d3583fb5. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test pg-aiguide?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does pg-aiguide take to install?
- 3 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 pg-aiguide need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing pg-aiguide?
- 2 things broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does pg-aiguide compare with the alternatives?
- Of the 91 ai projects Argusic has installed and timed, pg-aiguide was the 25th fastest to reach a running state, and 64 of 91 reached one at all.
- Where is the evidence for pg-aiguide?
- 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.