aigon-research-start

aigon-research-start is a skill for Claude Code from jayvee/aigon. It costs 20 tokens per session (830 once invoked), scanned A, original, Apache-2.0.

A research setup step that prepares the workspace and starts work in either Drive mode or Fleet mode, where one or more agents conduct the research.

In plain words
What is it for?
Use it to start a backlog research topic with no agent, one agent, or several specified agents.
Why use it?
It records the workflow transition and creates the required workspace structure automatically.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: positional $N argument; installed under .agents/ (shared by several agents).

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.

agentmods
npx agentmods add skills/jayvee/aigon/aigon-research-start
Any agent
npx skills add jayvee/aigon --skill aigon-research-start
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 aigon-research-start

README.md
[![agentmods](https://agentmods.dev/badge/skills/jayvee/aigon/aigon-research-start.svg)](https://agentmods.dev/skills/jayvee/aigon/aigon-research-start)
Your own site
<a href="https://agentmods.dev/skills/jayvee/aigon/aigon-research-start"><img src="https://agentmods.dev/badge/skills/jayvee/aigon/aigon-research-start.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 830 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00020 $0.00830
Opus 5 $0.00010 $0.00415
Sonnet 5 $0.00004 $0.00166
Haiku 4.5 $0.00002 $0.00083

Measured 6d ago against content hash 47c0a807d27e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

aigon-research-start 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 6d 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.

.agents/skills/aigon-research-start/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aigon-research-start

Prepare your workspace to conduct research in either Drive or Fleet mode.

CRITICAL: You MUST use the CLI command below to perform setup. Do NOT manually move topic files, lifecycle-view links, or create worktrees — the CLI records the workflow transition and prepares worktree state.

Usage

Argument Resolution

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

  1. List all files in ./docs/specs/research-topics/02-backlog/ 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

Step 1: Run the CLI command

CRITICAL: Run EXACTLY the arguments the user provided. Do NOT add agents that weren't specified.

# Drive mode — user passes only an ID
aigon research-start $1

# Drive worktree mode — user passes ID + agent
aigon research-start $1 <agent>

# Fleet mode — user passes ID + 2+ agents
aigon research-start $1 <agent1> <agent2> [agent3...]

The mode is determined automatically based on what the user provides:

  • No agents: Drive mode - conduct research in the current repo
  • 1 agent: Drive worktree mode - create one research worktree
  • 2+ agents: Fleet mode - create parallel research worktrees/findings contexts

The CLI will:

  • Transition the topic from backlog to in-progress and refresh the generated lifecycle view
  • Commit the topic move before any worktree setup
  • Create findings files for agents when needed
  • Create worktree/session context for parallel research

Step 2: Confirm setup and next steps

Research now follows the same lifecycle shape as features: start -> do -> submit -> eval -> close.

Drive Mode

After the CLI completes, run:

aigon-research-do <ID>

When the research pass is complete, signal completion with aigon agent-status research-complete, then close with:

aigon-research-close <ID>

Drive Worktree Mode

After the CLI completes, the research agent session is ready in the worktree context. Run:

Read the full file on GitHub · 117 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. 6d ago First seen · 117 lines · 20 tokens per session scan A 47c0a807d27e

Subscribe to this mod's changes

aigon-research-start is a skill published in the GitHub repository jayvee/aigon (25 stars, last pushed 4d ago), licensed Apache-2.0. It adds 20 tokens to every session and 830 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.