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.
curl -O https://raw.githubusercontent.com/guzus/ai-research-arm/main/.claude/commands/gen-research-route.mdgit clone --depth 1 https://github.com/guzus/ai-research-armWrote 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.
[](https://agentmods.dev/commands/guzus/ai-research-arm/gen-research-route)<a href="https://agentmods.dev/commands/guzus/ai-research-arm/gen-research-route"><img src="https://agentmods.dev/badge/commands/guzus/ai-research-arm/gen-research-route/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.
<a href="https://agentmods.dev/commands/guzus/ai-research-arm/gen-research-route"><img src="https://agentmods.dev/badge/commands/guzus/ai-research-arm/gen-research-route.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00029 | $0.00799 |
| Opus 5 | $0.00015 | $0.00400 |
| Sonnet 5 | $0.00006 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
gen-research-route 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generative Research — Route to GitHub Workflow
User-supplied topic: $ARGUMENTS
If the topic is empty or just whitespace, ask the user for a topic and stop until they answer.
What this does
Dispatches the generative-research.yml GitHub Actions workflow
with backend=claude by default (Claude Opus 4.7 via
anthropics/claude-code-action@v1). Use backend=deepseek-v4-flash for
the DeepSeek V4 Pro comparison baseline (DeepSeek's Anthropic-compatible
endpoint). The workflow runs on the self-hosted Linux runner and
executes the full deep pipeline documented in the workflow file:
- 16–32 evidence-collection sub-agents (waves of ≤8)
- 5–10 section-writer sub-agents (waves of ≤4)
- Verifier sub-agent + bounded revision pass
- Quality targets: ≥90% claims cited, ≥50% primary sources, ≥12 cites per 1000 words, ≥20 references, 4500–7000 words
Article writes to research/generative/ via the canonical writer
and the runner pushes the commit directly to main. Your local
chat is freed immediately.
Runtime is typically 20–45 min depending on topic complexity.
Steps
-
Verify gh auth (one-liner; if this errors, stop and ask the user to fix their gh auth before continuing):
gh auth status >/dev/null -
Dispatch the workflow. Quote the topic so spaces and special characters survive the shell:
gh workflow run generative-research.yml \ -f topic="$ARGUMENTS" \ -f backend=claudeIf the user passed a brief in their topic that mentions
backend: deepseek-v4-flash(orbackend: deepseek), honor it by switching-f backend=deepseek-v4-flashinstead. Otherwise default toclaude.If the user's entire argument is a Twitter/X status URL, prefer the dedicated Twitter-seed input instead of stuffing the URL into
topic:gh workflow run generative-research.yml \ -f twitter_url="$ARGUMENTS" \ -f backend=claude -
Wait a few seconds for the run to register, then look it up. GitHub takes a moment to enqueue dispatched runs:
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.
- 11d ago First seen · 94 lines · 29 tokens per session scan A 01f9ccb33034
gen-research-route is a command published in the GitHub repository guzus/ai-research-arm (11 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 799 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 2026-08-31.
Other commands, from other repositories
start-11-3
A lesson on building a workflow that fetches news from an RSS feed and distributes it by email or Slack. An RSS feed is a regularly updated list of items from a website.
start-11-3.en
Lesson 11-3: News Fetching → Email/Slack Distribution!
start-11-3.es
Leccion 11-3: Obtencion de noticias y distribucion por correo/Slack!
pi-code-review
Adversarial code review via Codex — break confidence in changes, not validate them.
pi-fact-check
Fact-check content via Gemini search + Claude verification — cross-provider claim validation.
pi-askall
Ask both Codex and Gemini the same question — get three perspectives with Claude synthesis.