jev-review

Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.

Runs with mockssource: GitHubTypeScriptMITcommit 57690af54ef7

TypeScript, MIT licensed. The project labels itself: agent plugin, ai agents, claude code, code review, codex, coding agents, cursor and developer tools.

jev-review runs, with stand-ins for the services it depends on. An Argusic agent installed it in 8 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 repo installs and builds with Node 20, its 13-test suite passes, the built dist/server.js is registered with the Codex CLI, and it serves an MCP jev_review call end-to-end against a local schema-valid Jev mock.

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

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.08 (measured)
recorded runs
1
last tested
stars
254
forks
27
open issues
6
watchers
1
size
3 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 jev-review, 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.

  • npm test failed: `node --test .test-dist/test/**/*.test.js` matched no files because the double-star glob is not expanded and Node 20's --test treats the literal `**` as a filename4 minutes
  • Container Node is v18.19.1 but the project requires Node 20+ (engines and esbuild target node20); cannot install system packages without root2 minutes
Install time
8 minutes
Cold machine to finish
8 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
`npm run validate` exited 0 with 13 tests passing; MCP initialize returned serverInfo {'name':'jev-review','version':'0.1.1'}, tools/list returned ['jev_review'], and tools/call jev_review against the schema-valid local Jev mock returned 19 metrics (correctness score 8, confidence 0.86) with no error
Model tokens used
373,150
Exact commit tested
57690af54ef7
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
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

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

**Errors**
- `npm run validate` failed on the `test` script: `node --test .test-dist/test/**/*.test.js` — the …
- Container has only Node 18 (`v18.19.1`); the project requires Node 20+ (`engines.node >=20`, `--t…
**Verification (all observed)**
- `npm run validate` with Node 20: `# tests 13`, `# pass 13`, `# fail 0`, build wrote `dist/server.…
- Registered the server in the Argusic Agent CLI as the README instructs: `codex mcp add jev-review…
- End-to-end MCP over stdio against a local mock that implements the Jev response schema: `initiali…
- Demo video decode: `ffmpeg -v error -i public/jev-review-demo.mp4 -f null -` exited 0 (h264, 1920…
**Mock Details**
- Since `/etc/hosts` is read-only, I wired the real `fetch` in the server process to `https://127.0…
**Note**
- My first driver had a client-side bug (`previousEvaluation: null`), which the server correctly re…

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 8 minutes.
  • Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

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 Runner1/3Runs with mocks92.000.08

Topics (from GitHub)

agent-pluginai-agentsclaude-codecode-reviewcodexcoding-agentscursordeveloper-toolsjevlocal-firstmcpmodel-context-protocolopencodesoftware-qualitytypescript

Embed the badge

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

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

Questions

Does jev-review run?
jev-review runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 8 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test jev-review?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 57690af54ef7. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test jev-review?
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 jev-review take to install?
8 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 jev-review need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing jev-review?
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.
Where is the evidence for jev-review?
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