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.
git clone --depth 1 https://github.com/revaya-ai/revaya-aios-workspace-templateWrote 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/revaya-ai/revaya-aios-workspace-template/update-ai-docs)<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.
<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>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 | $0.00000 | $0.02211 |
| Opus 5 | $0.00000 | $0.01105 |
| Sonnet 5 | $0.00000 | $0.00442 |
| Haiku 4.5 | $0.00000 | $0.00221 |
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.
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
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 · 213 lines · 0 tokens per session scan A 371d99fef85c
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.
Other commands, from other repositories
flow-nexus-neural
Train and deploy neural networks in distributed sandboxes.
data-pipeline
Design and implement ETL/ELT data pipelines.
atlas
Architect the intelligence layer — RAG pipelines, model selection, embeddings, and evaluation for agentic systems.
enhance-prompt
Command "enhance-prompt" from VoDaiLocz/Enhance-Prompt, covering enhance prompt workflow, 1. intake and scoring (enhance-prompt/skill.md), 5. ambiguity check and 8. iteration (enhance-prompt/references/iteration-mode.md).
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.