eval-autoresearch-fit

eval-autoresearch-fit is a skill for Claude Code from richfrem/agent-plugins-skills. It costs 85 tokens per session (2,664 once invoked), scanned A, original, MIT.

An assessment tool for deciding whether a skill can be improved by an automated optimisation loop. It checks for a measurable score, automatic evaluation, and one editable file.

In plain words
What is it for?
Use it to score skills as candidates for the Karpathy autoresearch pattern and record the resulting rankings.
Why use it?
It prevents time being spent on autonomous experiments that lack a clear success measure or cannot run without human judgment.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Part of the agent-scaffolders plugin — 33 skills shipped together

Good fit Use it to score skills as candidates for the Karpathy autoresearch pattern and record the resulting rankings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/richfrem/agent-plugins-skills/eval-autoresearch-fit
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.

Any agent
npx skills add richfrem/agent-plugins-skills --skill eval-autoresearch-fit
Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

Made for: Claude Code.

Or install agent-scaffolders, the plugin that ships this one along with the rest of its 33 skills.

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 eval-autoresearch-fit

README.md
[![agentmods](https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/eval-autoresearch-fit/github.svg)](https://agentmods.dev/skills/richfrem/agent-plugins-skills/eval-autoresearch-fit)
Your own site
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/eval-autoresearch-fit"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/eval-autoresearch-fit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for eval-autoresearch-fit

Your own site · 80×15
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/eval-autoresearch-fit"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/eval-autoresearch-fit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,664 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00085 $0.02664
Opus 5 $0.00043 $0.01332
Sonnet 5 $0.00017 $0.00533
Haiku 4.5 $0.00009 $0.00266

Measured 7d ago against content hash 6cd15a53100c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

eval-autoresearch-fit 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/update_ranked_skills.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/agent-scaffolders/skills/eval-autoresearch-fit/SKILL.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluate Autoresearch Fit

Assess whether a skill is a viable candidate for the Karpathy 3-File Autoresearch autonomous optimization loop. Scores each skill on four dimensions, proposes what the 3-file architecture would look like, and updates the canonical summary-ranked-skills.json via the update script.

Background

The Karpathy autoresearch pattern requires three conditions simultaneously:

  1. A Clear Metric — a single number with a clear optimization direction
  2. Automated Evaluation — no human in the loop; scoring runs headlessly from a shell command
  3. One Editable File — the agent mutates only a single predefined target per loop

Skills that lack these properties cannot run an effective autonomous loop.

Data File

The canonical ranked skills list lives at:

plugin-research/experiments/analyze-candidates-for-auto-reseaarch/skills/eval-autoresearch-fit/assets/resources/summary-ranked-skills.json

After every evaluation, update it with the update script (see Step 5).

Scoring Dimensions

Each dimension is scored 1-10. Max total = 40.

Dimension 10 (Best) 1 (Worst)
Objectivity Binary pass/fail or exact numeric output from a shell command Purely subjective, requires human taste judgment
Execution Speed Completes in seconds Requires 30+ min or human input
Frequency of Use Triggered multiple times per day Rarely needed (monthly or less)
Potential Utility Prevents systemic failures or saves hours per session Nice-to-have improvement

Viability thresholds:

  • 32-40 HIGH — Excellent candidate, implement now
  • 24-31 MEDIUM — Good candidate, address identified gaps first
  • 16-23 LOW — Needs significant rework to be viable
  • < 16 NOT_VIABLE — Skip or the metric is unfixable

Evaluation Steps

Step 1: Locate the Skill

If $ARGUMENTS is a path to a directory containing SKILL.md, read it directly.

Otherwise find it by name from the repo root:

PROJECT_ROOT=$(git rev-parse --show-toplevel)
find "$PROJECT_ROOT/plugins" -name "SKILL.md" | grep "$ARGUMENTS" | head -5

Read the full file on GitHub · 258 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 258 lines · 85 tokens per session scan A 6cd15a53100c

Subscribe to this mod's changes

eval-autoresearch-fit is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 2,664 once invoked, about $0.0004 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 2026-09-03.