autoresearch

autoresearch is a skill for Claude Code from FlorianBruniaux/claude-code-plugins. It costs 0 tokens per session (2,378 once invoked), scanned A, original, MIT.

An automated improvement loop that measures selected codebase metrics, proposes a change, and checks whether the measurement improves. It can repeat this process until you stop it, keeping improvements and reverting unsuccessful changes with Git.

In plain words
What is it for?
Use it to experiment with measurable code-quality improvements, such as reducing selected patterns or configuration exceptions.
Why use it?
It reduces the manual work of trying small code-quality changes and comparing their results.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is 4. bash scripts/autoresearch/runner.sh {loop-name} 0 15.

Part of the ai-methodology plugin — 17 skills, 4 commands, 1 agent, 1 hook shipped together

Good fit Use it to experiment with measurable code-quality improvements, such as reducing selected patterns or configuration exceptions.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/FlorianBruniaux/claude-code-plugins
agentmods
npx agentmods add skills/florianbruniaux/claude-code-plugins/autoresearch

Made for: Claude Code.

Or install ai-methodology, the plugin that ships this one along with the rest of its 17 skills, 4 commands, 1 agent, 1 hook.

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 autoresearch

README.md
[![agentmods](https://agentmods.dev/badge/skills/florianbruniaux/claude-code-plugins/autoresearch/github.svg)](https://agentmods.dev/skills/florianbruniaux/claude-code-plugins/autoresearch)
Your own site
<a href="https://agentmods.dev/skills/florianbruniaux/claude-code-plugins/autoresearch"><img src="https://agentmods.dev/badge/skills/florianbruniaux/claude-code-plugins/autoresearch/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 autoresearch

Your own site · 80×15
<a href="https://agentmods.dev/skills/florianbruniaux/claude-code-plugins/autoresearch"><img src="https://agentmods.dev/badge/skills/florianbruniaux/claude-code-plugins/autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,378 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 $0.00000 $0.02378
Opus 5.5 $0.00000 $0.00951
Sonnet 5.5 $0.00000 $0.00476
Haiku 4.5 $0.00000 $0.00238

Measured 1mo ago against content hash ed37d9821415, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

autoresearch 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 1mo 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/ai-methodology/skills/autoresearch/SKILL.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autoresearch: Autonomous Improvement Loop

Scan codebase quality metrics, propose improvement loops, and run autonomous agent iterations. Inspired by karpathy/autoresearch, adapted from ML research to code quality.

Concept: The agent proposes a code change, runs the measurement, keeps the change if the metric improved, reverts via git reset if not, and repeats until manually stopped.

Time: Scan ~30s | Per iteration: depends on scope | Loop: runs indefinitely until you stop it


Mode 1: Scan (default)

Measure current state, detect existing loops, propose next actions.

Instructions

Run the following metrics and display a prioritized proposal table.

Step 1: Measure codebase metrics

Adapt grep patterns to your project's conventions. These are TypeScript defaults, adjust for your stack.

# M1: Function declarations (prefer arrow functions)
M1=$(grep -r "export function " src/ --include="*.ts" --include="*.tsx" -l 2>/dev/null | wc -l | tr -d ' ')

# M2: Interface declarations (prefer type aliases)
M2=$(grep -r "export interface " src/ --include="*.ts" --include="*.tsx" -l 2>/dev/null | wc -l | tr -d ' ')

# M3: ESLint disables
M3=$(grep -r "eslint-disable" src/ --include="*.ts" --include="*.tsx" -l 2>/dev/null | wc -l | tr -d ' ')

# M4: Type casts to any
M4=$(grep -r " as any" src/ --include="*.ts" --include="*.tsx" -l 2>/dev/null | wc -l | tr -d ' ')

# M5: TODO comments
M5=$(grep -r "// TODO" src/ --include="*.ts" --include="*.tsx" -l 2>/dev/null | wc -l | tr -d ' ')

Step 2: Detect existing loops

for dir in scripts/autoresearch/loop-*/; do
  [ -d "$dir" ] || continue
  LOOP_NAME=$(basename "$dir")
  # Check if loop has results
  if [[ -f "$dir/results.tsv" ]]; then
    ITERS=$(wc -l < "$dir/results.tsv" | tr -d ' ')
    BEST=$(sort -t$'\t' -k2 -n "$dir/results.tsv" | head -1 | cut -f2)
    echo "ACTIVE:$LOOP_NAME:iterations=$ITERS:best=$BEST"
  else
    echo "SCAFFOLDED:$LOOP_NAME"
  fi
done

Read the full file on GitHub · 290 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. 1mo ago First seen · 290 lines · 0 tokens per session scan A ed37d9821415

Subscribe to this mod's changes

autoresearch is a skill published in the GitHub repository FlorianBruniaux/claude-code-plugins (42 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,378 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 2026-08-30.

Related

Other skills, from other repositories

app-store-screenshots

Use when building App Store or Google Play screenshot pages, generating exportable marketing screenshots for iOS and/or Android apps, or creating programmatic screenshot generators with Next.js. Triggers on app store, play store, screenshots, marketing assets, html-to-image, phone mockup, android screenshots, feature…

fatihkan/badi · 68 tokens

content

Content production and SEO writing skills. Blog posts, long-form content research, structured content frameworks, audience-targeted writing, content optimization. Triggers on: blog, content writing, article, copywriting, content strategy, content brief, SEO content, audience research.

fatihkan/badi · 0 tokens

expo-app-config

Choosing between app.json vs app.config.ts vs app.config.js, environment variables, variants, extra fields, plugin chain, and slug/scheme/bundle/version discipline. Triggers on app.json, app.config.ts, app.config.js, expo config, environment variable, .env, eas secret, variant, extra field, slug, scheme, bundle…

fatihkan/badi · 86 tokens

expo-modules

Writing Swift/Kotlin native modules with the Expo Modules API, requireNativeModule, async functions, view modules, and the event-emitter pattern. Triggers on expo modules, native module, swift, kotlin, requireNativeModule, expo-module-scripts, expo.modules.json, view module, event emitter, native function, async…

fatihkan/badi · 77 tokens

expo-notifications

Push and local notification setup with expo-notifications. iOS (APNs) + Android (FCM) credentials, permission flow, channels (Android 8+), categories, and scheduled notifications.

fatihkan/badi · 73 tokens

expo-config-plugin

Writing Expo config plugins, withInfoPlist, withAndroidManifest, withDangerousMod, mod compose, plugin testing, and registration in app.config.ts. Triggers on config plugin, with-plugin, withInfoPlist, withAndroidManifest, withDangerousMod, withEntitlementsPlist, withGradleProperties, mod, native config, expo plugin…

fatihkan/badi · 85 tokens