What is gen-research-tweet?

A command that uses a Twitter/X post as the starting point for a full research article. It sends the post to a GitHub Actions workflow, where automated jobs investigate the underlying question using original sources.

It helps create a deep research article from a direct Twitter/X status URL and reports the workflow and destination.

It turns a short social-media post into a verified research topic instead of treating the post itself as sufficient evidence.

How guzus/ai-research-arm configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to guzus/ai-research-arm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/guzus/ai-research-arm/main/.agents/commands/gen-research-tweet.md

Clone the repo

git clone --depth 1 https://github.com/guzus/ai-research-arm

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/guzus/ai-research-arm/gen-research-tweet/github.svg)](https://agentmods.dev/commands/guzus/ai-research-arm/gen-research-tweet)

Your own site

<a href="https://agentmods.dev/commands/guzus/ai-research-arm/gen-research-tweet"><img src="https://agentmods.dev/badge/commands/guzus/ai-research-arm/gen-research-tweet/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/guzus/ai-research-arm/gen-research-tweet"><img src="https://agentmods.dev/badge/commands/guzus/ai-research-arm/gen-research-tweet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 209 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	$0.00031	$0.00209
Opus 5.5	$0.00012	$0.00084
Sonnet 5.5	$0.00006	$0.00042
Haiku 4.5	$0.00003	$0.00021

Measured 21d ago against content hash 6a16831eb916, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gen-research-tweet 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 21d 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/commands/gen-research-tweet.md · 19 lines

What it actually says

Generative Research From Twitter/X

Input: $ARGUMENTS

Use the gen-research-dispatch skill with this input in tweet mode. It owns the dispatch contract: it validates and normalizes the status URL, passes any extra text as framing, reads backends from data/agent-backends.json, omits -f backend unless the input names one, and reports the run.

If that skill is not available, dispatch directly and report the run URL:

gh workflow run generative-research.yml -f twitter_url='<x.com status URL>'

Add -f backend=<selector> only when the input names a selector that data/agent-backends.json lists. Do not write the article locally in this session.

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.

21d ago Changed · -19 lines · +8 tokens per session 6a16831eb916
2mo ago First seen · 38 lines · 23 tokens per session scan A c984d007e03a

Subscribe to this mod's changes

gen-research-tweet is a command published in the GitHub repository guzus/ai-research-arm (14 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 209 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Research Writing and docs ai ai-agents claude github-actions news

gen-research-tweet next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gen-research-tweetguzus/ai-research-arm	Command	14	today	MIT	A	31	Claude Code
start-11-3.enminicoohei/ai-agent-camp	Command	347	1mo ago	none	B	2	Claude Code
start-11-3.esminicoohei/ai-agent-camp	Command	347	1mo ago	none	B	2	Claude Code
start-11-3minicoohei/ai-agent-camp	Command	347	1mo ago	none	B	2	Claude Code
doctoropensesh/KARIMO	Command	290	24d ago	Apache-2.0	A	0	Claude Code
greptile-reviewopensesh/KARIMO	Command	290	24d ago	Apache-2.0	A	0	Claude Code
pi-code-reviewtznthou/claude-prism	Command	10	yesterday	MIT	A	17	Claude Code

ai-research-arm: Command for Claude Code