jevbooks

← All projects

compact-adviser

kunchenguid/compact-adviser · Homepage

Agent plugin that decides when to run /compact using Jev.

Automated README summary

Automatically summarized from the README on 25 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

compact-adviser is an agent plugin for Pi, Claude Code, Codex CLI and Grok Build that judges whether the current session is at a safe boundary to compact, then hints or, where supported, runs /compact.

How it uses Jev

Jev answers two one-sentence questions in one request: whether the unit is finished, and whether this is hands-on work or coordination. Code composes the answers into one score, compared against a floor that relaxes from 0.90 to 0.50 as context fills.

Primitives:choicescore

Technique worth stealing

Two cheap classification questions composed in code into a single threshold score, with the threshold relaxed as context fills.

Try it

Install via your host's plugin command (e.g. `pi install npm:compact-adviser`), set TYPESAFE_API_KEY, then run `/compact-adviser`.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.14.0
Project signals
jev-1.14.0
Category
jev-1.14.0
Pattern tags
jev-1.14.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.87
  • Shows a System One patternFound in material0.90
  • Describes handling uncertaintyunclear0.40
  • Reports measured numbersnot found in the excerpt0.08
  • Is a runnable toolFound in material0.94
  • Top-10 learning shortlist signalunclear0.44
  • Is a replica of the modelnot found in the excerpt0.04
  • Solves a common problem (0–2)score on a 0–2 scale1.09 / 2
  • About JevFound in material0.99
Signals
Jev is core to the project0.87Shows a System One pattern0.90Describes handling uncertainty0.40Reports measured numbers0.08Is a runnable tool0.94Top-10 learning shortlist signal0.44Is a replica of the model0.0400.51Solves a common problem (0–2)1.09 / 2012

no-judgment band (0.40–0.60)

Design patterns
Funnel0.97Questionnaire0.96Fail open, fail closed0.91Scorecard0.87Traffic light0.64Blind review0.53Thermostat0.31Viewfinder0.25Prefetch0.21Ghostwriter0.2000.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 25 Oct 2026.