fast-jev-compaction
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.
Runs with mockssource: GitHubTypeScriptMITcommit e3f262a7f4d4
TypeScript, MIT licensed.
fast-jev-compaction runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.1 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
fast-jev-compaction 0.2.0 installs, builds, typechecks, and passes all 29 unit tests; the full compaction pipeline was verified against a mock Jev server standing in for the TypeSafe API
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
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.
- claude CLI not found for plugin validation
- Install time
- under a minute
- Cold machine to finish
- 4 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- npm test: 2 test files, 29 tests, all passed (exit 0); npm run build: tsc compiled without errors; npm run typecheck: tsc --noEmit + hooks typecheck both passed; mock-server demo: compactMessages with baseUrl=http://localhost:4877/v1/systemone reduced 21 messages to 11 (76.6% chars)
- Model tokens used
- 36,502
- Exact commit tested
- e3f262a7f4d4
- 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.
No third-party keys are needed for verification: the unit tests use a `JevAsker` fake, and the full… tokens used 36,502 Let me compile the final verdict. **All steps completed successfully:** - **`npm install`** — 50 packages installed, no errors - **`npm test`** — 29/29 tests passed across 2 test files - **`npm run build`** — TypeScript compiled without errors - **`npm run typecheck`** — `tsc --noEmit` + hooks typecheck both passed - **`npm run validate:plugin`** — failed (`claude` CLI not found), expected since `claude` is a sep… - **Mock Jev server demo** — stood up a local mock on port 4877 and ran `compactMessages` against i… No third-party keys are needed for verification: the unit tests use a `JevAsker` fake, and the full…
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 0.1 minutes, faster than the median of the 18 comparable projects Argusic has measured.
- Recovered from all 1 error 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.
Of the 19 TypeScript projects Argusic has installed and timed, fast-jev-compaction was the 1st fastest to reach a running state, and 16 of 19 reached one at all.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.02 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/fast-jev-compaction)Questions
- Does fast-jev-compaction run?
- fast-jev-compaction runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 0 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test fast-jev-compaction?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit e3f262a7f4d4. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test fast-jev-compaction?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does fast-jev-compaction take to install?
- 0.1 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 fast-jev-compaction need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing fast-jev-compaction?
- 1 thing 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 fast-jev-compaction compare with the alternatives?
- Of the 19 TypeScript projects Argusic has installed and timed, fast-jev-compaction was the 1st fastest to reach a running state, and 16 of 19 reached one at all.
- Where is the evidence for fast-jev-compaction?
- 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.