research-close

research-close is a command for Claude Code from jayvee/aigon. It costs 9 tokens per session (257 once invoked), scanned A, original, Apache-2.0.

A command that marks a research topic as finished and moves it to the done state. It can close work after evaluation, or warn before closing research that has not been evaluated.

In plain words
What is it for?
Use it to close a research topic after its findings have been evaluated, or to finish a single-agent research pass.
Why use it?
It keeps the research lifecycle accurate and removes completed topics from the active work queues.

Command for Claude Code

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 commands/jayvee/aigon/research-close
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-close

README.md
[![agentmods](https://agentmods.dev/badge/commands/jayvee/aigon/research-close.svg)](https://agentmods.dev/commands/jayvee/aigon/research-close)
Your own site
<a href="https://agentmods.dev/commands/jayvee/aigon/research-close"><img src="https://agentmods.dev/badge/commands/jayvee/aigon/research-close.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 257 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 $0.00009 $0.00257
Opus 5 $0.00005 $0.00129
Sonnet 5 $0.00002 $0.00051
Haiku 4.5 $0.00001 $0.00026

Measured yesterday against content hash 1db8c916b061, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-close 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 yesterday.

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

2 near-identical copies found in the catalogue:

.claude/commands/aigon/research-close.md · 31 lines

What it actually says

aigon-research-close

Run this command followed by the Research ID.

aigon research-close {{args}}

Argument Resolution

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

  1. List all files in ./docs/specs/research-topics/04-in-evaluation/ and ./docs/specs/research-topics/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

This records the research topic as done and refreshes the generated lifecycle view.

Usage

After evaluation: Run after research-eval has completed — the standard parallel-work flow.

Drive mode: Run after research-do is complete and the research pass is ready to finish.

Skipping eval: Closing from in-progress (without running eval) will show a warning but proceed. This is most relevant for single-agent research, just as feature close can skip comparative evaluation when there is nothing to compare.

ARGUMENTS: {{args}}

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. yesterday First seen · 31 lines · 9 tokens per session scan A 1db8c916b061

Subscribe to this mod's changes

research-close is a command published in the GitHub repository jayvee/aigon (24 stars, last pushed 3d ago), licensed Apache-2.0. It adds 9 tokens to every session and 257 once invoked, about $0.0000 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.