An autonomous research command that investigates a chosen topic, writes a report, and scores the report for quality. It can organize research into several user-defined domains and adapt findings to the user’s projects.

Use it for recurring research across selected areas such as psychology or other domains. On first use it sets up research domains and a project profile, then stores results under _autonomous/results/.

It provides a repeatable research process with saved settings and a quality check, reducing the need to manage each research pass manually.

auto-run — Command for Claude Code by primeline-ai

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/primeline-ai/claude-adaptive-research

agentmods

npx agentmods add commands/primeline-ai/claude-adaptive-research/auto-run

Made for: Claude Code.

Or install claude-adaptive-research, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 2 hooks.

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/commands/primeline-ai/claude-adaptive-research/auto-run/github.svg)](https://agentmods.dev/commands/primeline-ai/claude-adaptive-research/auto-run)

Your own site

<a href="https://agentmods.dev/commands/primeline-ai/claude-adaptive-research/auto-run"><img src="https://agentmods.dev/badge/commands/primeline-ai/claude-adaptive-research/auto-run/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/primeline-ai/claude-adaptive-research/auto-run"><img src="https://agentmods.dev/badge/commands/primeline-ai/claude-adaptive-research/auto-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,142 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.

Model	Per session	Once invoked
Fable 5.1	$0.00016	$0.02142
Opus 5	$0.00008	$0.01071
Sonnet 5	$0.00003	$0.00428
Haiku 4.5	$0.00002	$0.00214

Measured 10d ago against content hash 8ec561f0215c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

auto-run 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 10d 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.

commands/auto-run.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/auto-run

Autonomous research loop with quality gate and personalized adaptations.

FIRST RUN CHECK

Check if _autonomous/config.yaml exists in the current project directory.

If NOT exists → run setup automatically:

Show the user what this plugin can do (examples, domains, presets)
Ask how many research domains they want (2-10)
Let them name their domains (with examples)
Ask about their projects for the adaptation section (short interview)
Save config to _autonomous/config.yaml
Save profile to _autonomous/profile.yaml
Create domain folders under _autonomous/results/{domain}/

If exists → proceed with run.

SETUP MODE (/auto-run --setup or /auto-run setup)

Force re-run the setup flow even if config exists.

Step 1: Show what's possible

Welcome to Adaptive Research!

This plugin runs autonomous research loops — you set a topic,
Claude researches it independently, writes a report, and scores
it for quality. Reports adapt findings to YOUR projects.

WHAT YOU CAN RESEARCH:

  Research Domains (knowledge sources you pick)
  Examples:
  · Psychology — cognition, bias, motivation, persuasion
    → adaptable to: agent behavior, UX, conversion optimization
  · Biology — swarm intelligence, evolution, mycelium networks
    → adaptable to: algorithms, network architecture, adaptive systems
  · Physics — entropy, resonance, network theory, thermodynamics
    → adaptable to: system optimization, load balancing, drift prevention
  · Engineering — software patterns, control theory, architecture
    → adaptable to: code quality, DevOps, system design
  · Everyday Life — habits, heuristics, systems in daily life
    → adaptable to: productivity, workflows, life design
  · Finance — income streams, monetization, pricing strategies
    → adaptable to: your business, revenue models

  Free Text (any topic, anytime)
  · /auto-run "How do ant colony patterns apply to database sharding?"
  · /auto-run "Find 10 monetization strategies for open source projects"

  Presets (pre-configured research strategies)
  · technique-scout — find new techniques in your field
  · cross-domain — transfer patterns between disciplines
  · trend-radar — spot emerging trends in any niche

Read the full file on GitHub · 257 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.

10d ago First seen · 257 lines · 16 tokens per session scan A 8ec561f0215c

Subscribe to this mod's changes

auto-run is a command published in the GitHub repository primeline-ai/claude-adaptive-research (12 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 2,142 once invoked, about $0.0001 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 2026-08-30.

Claude Code Research ai-research anthropic autonomous-research claude claude-code-plugin

recall-save

Generate / overwrite .recall/context.md with Recall's local offline summarizer.

raiyanyahya/recall · 15 tokens

notebook-query

Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…

MarcosNahuel/antigravity-plugin-cc · 74 tokens

auto-run