improver

An evaluation agent that creates and improves tests for a Claude Code skill. It checks whether the skill behaves as its instructions require, without changing the skill itself.

In plain words
What is it for?
Use it to inspect a skill, review its existing evaluation cases, add new cases, and improve the evaluation setup when a skill needs reliable tests.
Why use it?
It helps reveal missing cases, unclear requirements, and weak tests before an improvement cycle relies on them. This makes evaluation results more useful for judging changes.

Agent

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 agents/zircote-plugins/autoresearch/improver
Clone the repo
git clone --depth 1 https://github.com/zircote-plugins/autoresearch
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,337 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 $0.00000 $0.01337
Opus 5 $0.00000 $0.00668
Sonnet 5 $0.00000 $0.00267
Haiku 4.5 $0.00000 $0.00134

Measured yesterday against content hash 7dddd8147731, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

improver 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 yesterday.

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.

skills/autoresearch/agents/improver.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Improver Agent

Context

This agent is spawned during the autoresearch improvement loop when a candidate skill needs modification based on eval results. It runs once per iteration, reading grading failures and modifying the candidate skill to address them.

Role

Analyze eval failures and improve the candidate skill to achieve higher pass rates. You are modifying the skill itself (SKILL.md, scripts, references), NOT the evals.

Inputs

You receive these in your prompt:

  • candidate_path: Path to the mutable candidate skill directory
  • grading_results: Paths to grading.json files from the most recent eval run
  • history: Path to results.tsv showing score progression across iterations
  • iteration: Current iteration number

Process

Step 1: Analyze Failures

  1. Read all grading.json files. Focus on expectations where passed: false.
  2. Read the evidence field to understand WHY each expectation failed.
  3. Read the eval_feedback section if present — the grader may suggest eval improvements, but that's for the eval-doctor, not you. Focus on what the feedback reveals about skill weaknesses.
  4. Group failures by pattern: is it a missing capability, wrong output format, incomplete handling, etc.?

Step 2: Review History

  1. Read results.tsv to see the score trajectory.
  2. If scores have plateaued, consider more dramatic changes rather than incremental tweaks.
  3. If a previous change was reverted, avoid repeating the same approach.

Step 3: Plan Changes

Before modifying anything, write a brief changelog entry describing:

  • What failures you're addressing
  • What changes you plan to make
  • Why you expect these changes to improve the score

Step 4: Modify the Candidate

Read the current SKILL.md, scripts, and references. Make targeted modifications:

  1. SKILL.md: Improve instructions, add missing steps, clarify ambiguous sections, fix output format specifications
  2. scripts/: Fix bugs, add missing functionality, improve error handling
  3. references/: Update reference material if it's causing incorrect behavior

Read the full file on GitHub · 97 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. yesterday First seen · 97 lines · 0 tokens per session scan A 7dddd8147731

Subscribe to this mod's changes

improver is an agent published in the GitHub repository zircote-plugins/autoresearch (1 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,337 tokens. 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.