update-ai-docs

update-ai-docs is a command for Claude Code from revaya-ai/revaya-aios-workspace-template. It costs 0 tokens per session (2,211 once invoked), scanned A, original, MIT.

A command that checks live rankings of AI models across categories such as text, code, image, search, and speech. It can research ranking changes and update the related documentation.

In plain words
What is it for?
Use it to update one named category or check all supported categories, detect changes, research new leaders, and revise the documentation automatically.
Why use it?
It removes the manual work of repeatedly checking leaderboards and keeping comparison documents current.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: names the AskUserQuestion tool.

Good fit Use it to update one named category or check all supported categories, detect changes, research new leaders, and revise the documentation automatically.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/revaya-ai/revaya-aios-workspace-template/update-ai-docs
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/revaya-ai/revaya-aios-workspace-template

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 update-ai-docs

README.md
[![agentmods](https://agentmods.dev/badge/commands/revaya-ai/revaya-aios-workspace-template/update-ai-docs/github.svg)](https://agentmods.dev/commands/revaya-ai/revaya-aios-workspace-template/update-ai-docs)
Your own site
<a href="https://agentmods.dev/commands/revaya-ai/revaya-aios-workspace-template/update-ai-docs"><img src="https://agentmods.dev/badge/commands/revaya-ai/revaya-aios-workspace-template/update-ai-docs/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.

agentmods 80×15 button for update-ai-docs

Your own site · 80×15
<a href="https://agentmods.dev/commands/revaya-ai/revaya-aios-workspace-template/update-ai-docs"><img src="https://agentmods.dev/badge/commands/revaya-ai/revaya-aios-workspace-template/update-ai-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,211 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 $0.00000 $0.02211
Opus 5 $0.00000 $0.01105
Sonnet 5 $0.00000 $0.00442
Haiku 4.5 $0.00000 $0.00221

Measured 11d ago against content hash 371d99fef85c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

update-ai-docs 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.

.claude/commands/update-ai-docs.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update AI Docs

Autonomous pipeline: pull live rankings, detect changes, research new leaders, update docs. No human interaction.

Variables

target: $ARGUMENTS (optional — specific category to update, e.g., "code". If empty, checks all 10 categories for changes.)

Instructions

Run this pipeline end-to-end with zero stops, zero prompts, zero AskUserQuestion calls. If nothing changed, report that and exit. If something changed, research it and update the docs — all automatically.

Category Tiers

  • Tier 1 (LMArena): text, code, vision, text-to-image, image-edit, search, text-to-video, image-to-video
  • Tier 2: text-to-speech (TTS Arena V2), speech-to-text (Voice Writer Leaderboard)

Tier 1 uses ELO scores from arena.ai. Tier 2 uses ELO from TTS Arena (for TTS) and WER from Voice Writer (for STT, lower = better).

Phase 1: PULL LIVE RANKINGS

Tier 1 — LMArena (8 categories):

For each of the 8 LMArena categories, fetch the current leaderboard:

WebFetch https://arena.ai/leaderboard/{category}
Prompt: "Extract the complete leaderboard table. For each model return: rank, model name, ELO score (Arena Score), number of votes, organization/provider. Return the top 20 models as a structured list."

Tier 2 — TTS Arena + Voice Writer (2 categories):

For text-to-speech:

WebFetch https://tts-agi-tts-arena-v2.hf.space/leaderboard
Prompt: "Extract the TTS model leaderboard. For each model return: rank, model name, ELO score, win rate, total votes. Return all models."

For speech-to-text:

WebFetch https://voicewriter.io/speech-recognition-leaderboard
Prompt: "Extract the speech-to-text comparison table. For each system return: name, Mean WER, Std Dev, Price per hour. Return all models."

If a specific target category was given, only fetch that one.

Also query OpenRouter DB data for pricing context on text/code models:

SELECT model_name, price_input, price_output, context_length
FROM ai_models
WHERE source = 'openrouter' AND date = (SELECT MAX(date) FROM ai_models WHERE source = 'openrouter')
AND category IN ('text', 'code')
ORDER BY category, rank_in_category
LIMIT 30

Read the full file on GitHub · 213 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. 11d ago First seen · 213 lines · 0 tokens per session scan A 371d99fef85c

Subscribe to this mod's changes

update-ai-docs is a command published in the GitHub repository revaya-ai/revaya-aios-workspace-template (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,211 tokens. 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.