What is autoresearch?

A repeatable improvement loop for one defined task, using an evaluator, saved experiment results, and decision logs.

It helps run repeated experiments, evaluate each iteration, store results, and schedule future reruns for a single mission.

It keeps successive attempts measurable and records why each change was kept or rejected.

autoresearch — Skill for Claude Code by naimkatiman

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 naimkatiman/continuous-improvement --skill autoresearch

Clone the repo

git clone --depth 1 https://github.com/naimkatiman/continuous-improvement

Made for: Claude Code.

Or install oh-my-claudecode, the plugin that ships this one along with the rest of its 37 skills, 17 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/naimkatiman/continuous-improvement/autoresearch.svg)](https://agentmods.dev/skills/naimkatiman/continuous-improvement/autoresearch)

Your own site

<a href="https://agentmods.dev/skills/naimkatiman/continuous-improvement/autoresearch"><img src="https://agentmods.dev/badge/skills/naimkatiman/continuous-improvement/autoresearch.svg" alt="Measured on agentmods" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 780 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 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.00780
Opus 5	$0.00012	$0.00390
Sonnet 5	$0.00005	$0.00156
Haiku 4.5	$0.00002	$0.00078

Measured 4d ago against content hash f98736d700b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 4d 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.

Origin

This is a copy

100% identical to autoresearch — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

third-party/oh-my-claudecode/skills/autoresearch/SKILL.md · 91 lines

What it actually says

<Use_When>

You already have a mission and evaluator from /deep-interview --autoresearch
You want persistent single-mission improvement with strict evaluation
You need durable experiment logs under .omc/autoresearch/
You want a supported path for periodic reruns via Claude Code native cron </Use_When>

<Do_Not_Use_When>

You need evaluator generation at runtime — use /deep-interview --autoresearch first
You need multiple missions orchestrated together — v1 forbids that
You want the deprecated omc autoresearch CLI flow — it is no longer authoritative </Do_Not_Use_When>

<Required_Artifacts> Canonical persistent storage lives under .omc/autoresearch/<mission-slug>/ and/or .omc/logs/autoresearch/<run-id>/.

Minimum required artifacts:

mission spec
evaluator script or command reference
per-iteration evaluation JSON
markdown decision logs

Recommended canonical shape:

.omc/autoresearch/<mission-slug>/
  mission.md
  evaluator.json
  runs/<run-id>/
    evaluations/
      iteration-0001.json
      iteration-0002.json
    decision-log.md

Reuse existing runtime artifacts when available rather than duplicating them unnecessarily. </Required_Artifacts>

<Cron_Integration> Claude Code native cron is a supported integration point for periodic mission enhancement. In v1, prefer documenting/configuring cron inputs over building a large scheduler UI.

If cron is used:

keep one mission per scheduled job
preserve the same mission/evaluator contract
append new run artifacts rather than overwriting prior experiments </Cron_Integration>

<Execution_Policy>

Do not hand execution back to omc autoresearch
Do not create multi-mission orchestration
Prefer reusing src/autoresearch/* runtime/schema helpers where they already match the stricter contract
Keep logs useful to humans, not only machines </Execution_Policy>

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.

4d ago First seen · 91 lines · 24 tokens per session scan A f98736d700b4

Subscribe to this mod's changes

autoresearch is a skill published in the GitHub repository naimkatiman/continuous-improvement (7 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 780 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to autoresearch, differing in 0 lines, and is treated as a copy.

Analytics and metrics Claude Code LLM Research ai-agents coding-agents continuous-improvement hooks

opensrc

Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…

vercel-labs/opensrc · 103 tokens

nopus-configure

Configure nopus complexity sensitivity, extra-simple rewrites, rewrite evidence, and Pi response hiding for this user.

Vistyy/nopus · 27 tokens

nopus-simplify

Rewrite the immediately preceding assistant response with clearer and more direct prose when the user invokes this skill.

Vistyy/nopus · 25 tokens

agentpush

Bridge an imported agentpush MCP server (Telegram, WhatsApp, etc.) with live agentproto sessions via the daemon's transmitter subsystem: transmitmessage sends outbound and binds the recipient to a session, inboundwatcherstart polls agentpush for new messages, and inboundendpointcreate/POST /inbound(/:slug) route…

agentproto/ts · 119 tokens

bureau

Drive Bureau — the browser stack's installable capability server: a stealth Firefox (Camofox) + daemon that exposes browser tools as MCP-over-HTTP on :8830, plus a CLI for saved browser identities (sessions), social capture / search, adapter health probes, declarative workflows, and Guilde connection. Use when working…

agentproto/ts · 131 tokens

agentproto-apps

Operate and build Agentproto apps — AIP-42 app bundles (defineApp().emit(dir), APP.md + agents/ + workflows/ + ui/) and their daemon lifecycle (appinstall, appapply, apprun, appstatus, appstop) plus the app-scoped durable data plane (appdataread/write/list/migrate). Covers serving one with a UI (agentproto app serve →…

agentproto/ts · 178 tokens