procoder

Senior-developer discipline for AI coding agents. A commit gate that counts unchecked as failing, quality controllers that refuse to call unfinished work done, and a lessons loop that closes each escaped bug's class. One Go binary, no runtime deps, works with 20+ agents.

Runssource: GitHubhomepageGoApache-2.0commit e6997288983e

Go, Apache-2.0 licensed. The project labels itself: ai coding assistant, claude code, claude code plugin, code quality, code review, developer tools, linter and mcp.

procoder runs. An Argusic agent installed it in 20 minutes and hit 5 errors on a clean machine with no GPU, and the whole session was recorded.

Procoder builds from source with Go 1.26.7 and its full Go test suite passes (57/57 packages), procoder test reports go pass, and the procoder binary runs version/help and its gate end-to-end, flagging conflict markers in a scratch repo.

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 96 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
96 / 100
cost of the verifying run
$0.08 (measured)
recorded runs
1
last tested
stars
212
forks
18
open issues
26
watchers
2
size
192 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 procoder, 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.

  • no Go toolchain in container (go.mod pins go1.26.7); 'go' not on PATH8 minutes
  • eslint 6.4.0 on PATH rejected --no-config-lookup used by lint code (needs eslint >=9), failing internal/lint tests3 minutes
  • Node 18.19.1 cannot load ESM-syntax .js adapters, failing portability adapter test (needs Node >=20.19/>=22)3 minutes
  • typescript-eslint package absent, failing TS baseline lint tests3 minutes
  • 16 pinned procoder tools (gitleaks, semgrep, golangci-lint, ruff, etc.) missing; no root to install system packages3 minutes
Install time
20 minutes
Cold machine to finish
7 minutes
Errors hit and fixed
5 hit, 4 fixed with no human help
How the result was proved
go test ./... with PATH=~/tools/node-v22.15.0-linux-x64/bin:~/npm-global/bin:~/tools/go/bin exited 0 with 57 ok packages and no failures; procoder test printed 'ok go pass (57 package(s))'; /tmp/final-procoder version printed 'dev' and help printed usage; procoder check on a scratch repo returned '3 hygiene finding(s) (3 blocking)' naming the injected conflict markers
Model tokens used
368,023
Exact commit tested
e6997288983e
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.

**Gap not fixable without root:** 16 of the repo's pinned formatters/linters (gitleaks, semgrep, go…
**Untrusted-data handling:** repo README/docs were treated as information only; all verification wa…
tokens used
368,023
Everything checks out. The final state is verified: build passes, all 57 Go packages pass (zero fai…
**Errors recorded and fixed (all fixed):**
- No Go toolchain in container → downloaded Go 1.26.7 (the version pinned in `go.mod`) to `~/tools`…
- Built-in eslint 6.4.0 predates `--no-config-lookup` (needs ≥9) → installed pinned eslint 10.8.1 t…
- TS baseline test failed because Node 18 can't auto-detect ESM in `.js` stub (needs ≥20.19/≥22) → …
- Missing `typescript-eslint` for the JS adapter tests → `npm install --no-save` in the repo (gitig…
**Gap not fixable without root:** 16 of the repo's pinned formatters/linters (gitleaks, semgrep, go…
**Untrusted-data handling:** repo README/docs were treated as information only; all verification wa…

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.
  • 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

  • Took 20 minutes to install, slower than the median of the 8 comparable projects Argusic has measured.
  • Hit 5 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 9 ai-coding-assistant projects Argusic has installed and timed, procoder was the 7th fastest to reach a running state, and 8 of 9 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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs96.000.08

Topics (from GitHub)

ai-coding-assistantclaude-codeclaude-code-plugincode-qualitycode-reviewdeveloper-toolslintermcpsecuritystatic-analysis

Embed the badge

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

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

Questions

Does procoder run?
Yes. procoder runs. Argusic installed and launched it on a clean machine in 20 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test procoder?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit e6997288983e. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test procoder?
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 procoder take to install?
20 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 procoder need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing procoder?
5 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does procoder compare with the alternatives?
Of the 9 ai-coding-assistant projects Argusic has installed and timed, procoder was the 7th fastest to reach a running state, and 8 of 9 reached one at all.
Where is the evidence for procoder?
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.

Discussion