# Ce Retune

Retune a skill corpus for a new model, measurement-first: mine the run archive for a...

- Repository: https://github.com/EveryInc/compound-engineering-plugin (25818 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add EveryInc/compound-engineering-plugin --skill ce-retune -g -a claude-code -y`
Codex: `npx skills add EveryInc/compound-engineering-plugin --skill ce-retune -g -a codex -y`
Cursor: `npx skills add EveryInc/compound-engineering-plugin --skill ce-retune -g -a cursor -y`
Gemini CLI: `npx skills add EveryInc/compound-engineering-plugin --skill ce-retune -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add EveryInc/compound-engineering-plugin`

## Description

Retune a skill corpus for a new model, measurement-first: mine the run archive for a baseline, establish a noise floor, audit the corpus adversarially, then cut in measured passes until a pre-registered bar clears. Requires a benchmark harness that can A/B two builds of the corpus; refuses without one.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Retune a Corpus for a New Model

A corpus that degrades on a new model is a measurement problem before it is a writing problem: rewriting what looks wrong produces a plausible fix list and no way to know whether any item mattered.

**Outcome:** a corpus whose measured behavior on the target model clears a bar registered before any change, with the regression classes removed and each removal attributable.

**Done:** the bar is cleared, or the run reports the specific claim it could not support. A green test suite is not done: it proves nothing broke, not that behavior improved.

**Non-goal:** word reduction. Leanness and performance are separate programs that share a corpus; only one of them is the result here. Report completion, not word count.


## Phase 0: the measurement gate, check this first

This skill cannot run without a way to observe behavior. Check for all three, and name whichever is missing:

1. **A run archive or a harness that produces one**, per-run logs carrying the tool-call trace, a terminal marker, token counts, and the final message.
2. **A build selector**, the harness can point a run at a specific source checkout of the corpus (a `--plugin-dir`-style override, a configurable skills path, an env var), so two builds are comparable under one runner.
3. **A repeatable task** the corpus actually executes end to end.

If any is missing, **stop and say so**, naming what to build. Do not fall back to a static audit and present it as retuning: an audit can say what looks cuttable and never whether cutting helped. An audit-only pass is a legitimate thing to want; it is a different request.

State the target model and the harness you found before continuing.

## The phases

The rest: https://github.com/EveryInc/compound-engineering-plugin/blob/HEAD/skills/ce-retune/SKILL.md