research-autopilot

research-autopilot is a command for Claude Code from jayvee/aigon. It costs 18 tokens per session (572 once invoked), scanned A, original, Apache-2.0.

A command that runs a complete multi-agent research workflow: setup, parallel execution, progress monitoring, and optional evaluation. Fleet mode means several agents work on the same research topic.

In plain words
What is it for?
Use it to launch a research topic with selected agents, monitor completion, and optionally evaluate all submitted findings automatically.
Why use it?
It removes the manual coordination needed to start agents, watch their findings files, and optionally trigger synthesis.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to launch a research topic with selected agents, monitor completion…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jayvee/aigon/research-autopilot
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.

Clone the repo
git clone --depth 1 https://github.com/jayvee/aigon

Made for: Claude Code.

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 research-autopilot

README.md
[![agentmods](https://agentmods.dev/badge/commands/jayvee/aigon/research-autopilot.svg)](https://agentmods.dev/commands/jayvee/aigon/research-autopilot)
Your own site
<a href="https://agentmods.dev/commands/jayvee/aigon/research-autopilot"><img src="https://agentmods.dev/badge/commands/jayvee/aigon/research-autopilot.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 572 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 $0.00018 $0.00572
Opus 5 $0.00009 $0.00286
Sonnet 5 $0.00004 $0.00114
Haiku 4.5 $0.00002 $0.00057

Measured 3d ago against content hash d64b395f4276, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

research-autopilot 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 3d 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

Copies of this mod

1 near-identical copy found in the catalogue:

  • arap — 98% identical, 2 lines differ
.claude/commands/aigon/research-autopilot.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aigon-research-autopilot

Run a fully autonomous Fleet research pipeline. Sets up findings files, spawns agents in parallel, monitors progress, and optionally runs synthesis when all agents submit.

aigon research-autopilot {{args}} [agents...]

Argument Resolution

If no ID is provided, or the ID doesn't match an existing topic in backlog or in-progress:

  1. List all files in ./docs/specs/research-topics/02-backlog/ and 03-in-progress/ matching research-*.md
  2. If a partial ID or name was given, filter to matches
  3. Present the matching topics and ask the user to choose one

Usage

Basic usage (use configured default agents)

aigon research-autopilot {{args}}

Specify agents explicitly

aigon research-autopilot {{args}} cc ag cx

With auto-eval

aigon research-autopilot {{args}} cc ag cx --auto-eval

What it does

  1. Setup phase: If no findings files exist, runs research-start to create them
  2. Spawn phase: Creates a tmux session for each agent, running research-do
  3. Monitor phase: Polls agent findings files every 30s for complete status, prints status table
  4. Evaluate phase: If --auto-eval, runs research-eval automatically; otherwise prints the command

Subcommands

aigon research-autopilot status {{args}}    # Check agent statuses
aigon research-autopilot stop {{args}}      # Stop all agents

Options

  • --auto-eval — Automatically run research-eval when all agents submit
  • --poll-interval=N — Seconds between status checks (default: 30)

Requirements

  • tmux must be installed (brew install tmux)
  • At least 2 agents must be specified (or configured as defaults)
  • Research topic must be in backlog or in-progress

Agent Workflow

Each spawned agent will:

  1. Run research-do to conduct their research
  2. Write findings to their findings file
  3. Run agent-status research-complete to signal completion

Prompt Suggestion

After all agents submit, suggest the eval command:

Read the full file on GitHub · 76 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. 3d ago First seen · 76 lines · 18 tokens per session scan A d64b395f4276

Subscribe to this mod's changes

research-autopilot is a command published in the GitHub repository jayvee/aigon (25 stars, last pushed 5d ago), licensed Apache-2.0. It adds 18 tokens to every session and 572 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 2026-09-03.