help

A help command for an autoresearch plugin, which repeatedly changes one chosen artifact, runs a scoring command, and keeps improvements. The artifact can be any file or other editable output, not only machine-learning code.

In plain words
What is it for?
Learning how to configure an overnight edit-and-score loop, including the artifact, scoring command, and direction of improvement.
Why use it?
It explains how the automated experiment loop works and what must be supplied before running it.

Command

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/fradser/dotclaude/help
Clone the repo
git clone --depth 1 https://github.com/FradSer/dotclaude
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,502 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00007 $0.02502
Opus 5 $0.00003 $0.01251
Sonnet 5 $0.00001 $0.00500
Haiku 4.5 $0.00001 $0.00250

Measured 2d ago against content hash 55ae71698606, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

help scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep '^iteration:' .claude/autoresearch.local.md
autoresearch/commands/help.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autoresearch Plugin Help

Explain the following to the user:

What is autoresearch?

A Claude Code plugin inspired by karpathy/autoresearch — an autonomous research loop where Claude acts as a researcher, continuously editing one artifact, running a scorer, logging results, and iterating overnight without human intervention.

Unlike the original (which is hardwired to ML training), this plugin is domain-agnostic: you supply the editable artifact, the scorer, and the optimization direction, so the loop works on any problem that reduces to "edit something, run a command that prints one number, keep the change if the number improved." ML training is just one configuration of it.

Core idea:

  • Point Claude at one artifact it may edit and one scorer command that prints a number
  • Let it experiment autonomously — make a change, score it, keep or discard, repeat
  • Wake up in the morning to a log of experiments and (hopefully) a better score

How the loop runs (this plugin's mechanism):

Rather than an external shell loop, this plugin uses a Claude Code Stop hook. Every time Claude tries to end its turn, the hook intercepts the exit and re-injects the same research prompt — so Claude keeps experimenting in one continuous session. Claude sees its previous work in git history and results.tsv, building incrementally toward a better score. The hook stops the loop when a configured bound is hit (max experiments, wall-clock budget, or a completion promise).

This is the same spirit as the "ralph-loop" idea behind the original project (re-feeding a prompt until done), adapted to Claude Code's hook system instead of a while loop over a CLI.

Requirements

  • A git repository (the loop runs in a dedicated git worktree so your main checkout, current branch, and even a dirty tree are never touched)
  • At least one bound: --max-experiments and/or --max-wall-clock
  • An evaluator: a --score-cmd (prints a number as its last stdout line) and/or a --check-cmd (objective pass/fail gate, exit 0 = pass)
  • Whatever runtime the evaluator needs (interpreter, data, GPU, ...) — that is its concern, not the plugin's

Read the full file on GitHub · 165 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. 2d ago First seen · 165 lines · 7 tokens per session scan B 55ae71698606

Subscribe to this mod's changes

help is a command published in the GitHub repository FradSer/dotclaude (587 stars, last pushed 20d ago), licensed MIT. It adds 7 tokens to every session and 2,502 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.