autoresearch

autoresearch is a skill for Claude Code, Codex from YousefNabil-SOC/claude-apex. It costs 32 tokens per session (385 once invoked), scanned A, original, MIT.

An automated improvement loop for tasks with a measurable result. It changes one thing, checks the result, keeps improvements, and rejects changes that make the result worse.

In plain words
What is it for?
Use it for performance tuning, reducing bundle size, increasing test coverage, or improving SEO audit scores.
Why use it?
It provides a repeatable way to optimize work without keeping changes that fail the chosen measurement.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for performance tuning, reducing bundle size, increasing test coverage, or improving SEO audit scores.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yousefnabil-soc/claude-apex/autoresearch
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 YousefNabil-SOC/claude-apex --skill autoresearch
Clone the repo
git clone --depth 1 https://github.com/YousefNabil-SOC/claude-apex

Made for: Claude Code, Codex.

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/yousefnabil-soc/claude-apex/autoresearch/github.svg)](https://agentmods.dev/skills/yousefnabil-soc/claude-apex/autoresearch)
Your own site
<a href="https://agentmods.dev/skills/yousefnabil-soc/claude-apex/autoresearch"><img src="https://agentmods.dev/badge/skills/yousefnabil-soc/claude-apex/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/yousefnabil-soc/claude-apex/autoresearch"><img src="https://agentmods.dev/badge/skills/yousefnabil-soc/claude-apex/autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 385 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.
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 $0.00032 $0.00385
Opus 5 $0.00016 $0.00192
Sonnet 5 $0.00006 $0.00077
Haiku 4.5 $0.00003 $0.00038

Measured 8d ago against content hash 5723a415d5dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 8d 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.

skills/autoresearch/SKILL.md · 60 lines

What it actually says

Autoresearch — Autonomous Optimization

Inspired by iterative research methodology. Apply to ANY task with a measurable metric.

Core Loop

1. Define GOAL (what you want to achieve)
2. Define METRIC (how you measure success)
3. Define DIRECTION (higher is better / lower is better)
4. Define VERIFY (how to check the metric)

REPEAT:
  a. Make ONE modification
  b. Measure the metric
  c. If improved: KEEP the change
  d. If worsened: DISCARD (revert)
  e. Log the attempt and result
  f. Choose next modification
UNTIL: goal is met OR no more improvements found

Example Applications

Performance optimization

  • Goal: Page load under 2 seconds
  • Metric: Lighthouse performance score
  • Direction: Higher is better
  • Verify: Run Lighthouse audit

Bundle size reduction

  • Goal: Main bundle under 200KB
  • Metric: Bundle size in KB
  • Direction: Lower is better
  • Verify: Run build and check output

Test coverage

  • Goal: 80%+ code coverage
  • Metric: Coverage percentage
  • Direction: Higher is better
  • Verify: Run test suite with coverage

SEO score

  • Goal: All pages score 90+
  • Metric: SEO audit score
  • Direction: Higher is better
  • Verify: Run SEO analysis tool

Rules

  • ONE change per iteration (isolate variables)
  • ALWAYS measure before and after
  • ALWAYS revert failed attempts (no accumulating debt)
  • LOG every attempt for learning
  • STOP when goal is met or 3 consecutive iterations show no improvement
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. 8d ago First seen · 60 lines · 32 tokens per session scan A 5723a415d5dc

Subscribe to this mod's changes

autoresearch is a skill published in the GitHub repository YousefNabil-SOC/claude-apex (2 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 385 once invoked, about $0.0002 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.