evolve-rubric

evolve-rubric is a command for coding agents from aminry/auto-claude-plugins. It costs 14 tokens per session (2,183 once invoked), scanned A, original, MIT.

A command for reviewing the results of an automated improvement cycle and finding quality problems that the current scoring checklist misses. A rubric is a set of questions or criteria used to evaluate results.

In plain words
What is it for?
Use it after an auto-improve run to inspect its output, identify gaps in the evaluation criteria, and refine the rubric for a feature such as comparisons, products, or other application areas.
Why use it?
It helps uncover real issues that are not being measured by existing checks. It can propose additional evaluation questions and, after approval, update the rubric.

Command

Part of the auto-improve plugin — 1 command shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/aminry/auto-claude-plugins/evolve-rubric
Clone the repo
git clone --depth 1 https://github.com/aminry/auto-claude-plugins

Or install auto-improve, the plugin that ships this one along with the rest of its 1 command.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for evolve-rubric

README.md
[![agentmods](https://agentmods.dev/badge/commands/aminry/auto-claude-plugins/evolve-rubric.svg)](https://agentmods.dev/commands/aminry/auto-claude-plugins/evolve-rubric)
Your own site
<a href="https://agentmods.dev/commands/aminry/auto-claude-plugins/evolve-rubric"><img src="https://agentmods.dev/badge/commands/aminry/auto-claude-plugins/evolve-rubric.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.02183
Opus 5 $0.00007 $0.01092
Sonnet 5 $0.00003 $0.00437
Haiku 4.5 $0.00001 $0.00218

Measured 4d ago against content hash 311a71eacaa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolve-rubric scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/auto-improve/commands/evolve-rubric.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze the latest auto-improve results to find quality issues not covered by the current evaluation rubric, then update the rubric accordingly.

The auto-improve skill to analyze: $ARGUMENTS


Overview

After running an auto-improve cycle, the evaluation rubric may have blind spots — quality issues that exist in the output but aren't captured by any rubric question. This skill:

  1. Reads the latest extraction results from the most recent auto-improve run
  2. Performs a deep, rubric-independent quality analysis
  3. Identifies gaps where real issues exist but no rubric question catches them
  4. Proposes new rubric questions and gets user approval
  5. Updates the evaluation rubric

Phase 1: Load Context

  1. Identify the feature: Parse $ARGUMENTS to determine the auto-improve skill name. Expected format: a feature name like comparisons, products, features, etc.

  2. Load the current rubric: Read .claude/commands/evaluate-{feature}.md (or the appropriate evaluate file — check .claude/commands/ for the matching evaluate skill).

  3. Load the latest results: Find the debug/output directory by reading the auto-improve skill file (.claude/commands/auto-improve-{feature}.md) and locating its configured paths (typically .debug/auto-improve-{feature}/ but may vary). Read the most recent extraction files from the extractions subdirectory. Sort by modification time and take the latest iteration's files.

  4. Load the results TSV: Read the results.tsv file from the auto-improve output directory to understand the score trajectory and which failures were already addressed.

  5. Load the latest evaluations: Read the evaluations subdirectory for the most recent iteration to see which rubric questions passed/failed.

If any of these files don't exist, report what's missing and stop.


Phase 2: Deep Quality Analysis

For each extraction file from the latest iteration, perform a rubric-independent quality review. This means: forget the rubric exists and evaluate the output fresh, looking for ANY quality issue regardless of whether a rubric question covers it.

Read the full file on GitHub · 250 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 250 lines · 14 tokens per session scan A 311a71eacaa6

Subscribe to this mod's changes

evolve-rubric is a command published in the GitHub repository aminry/auto-claude-plugins (1 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 2,183 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.