roll-aix

roll-aix is a command for Claude Code from enricoros/big-AGI. It costs 8 tokens per session (279 once invoked), scanned A, original, MIT.

A release-management command that increases the AIX monotonic version number, a counter used to mark a protocol-level release. It updates one source file and creates a Git commit.

In plain words
What is it for?
Use it only for protocol-level changes. It checks that the current branch is main and the target file is unchanged, then increments the value, commits the edit, and reports the new version.
Why use it?
It provides a controlled way to trigger a full vendor refresh when a protocol change requires it, while avoiding unnecessary refreshes for ordinary model-definition updates.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Good fit Use it only for protocol-level changes. It checks that the current branch is main and the target file is unchanged, then increments the value, commits the edit, and reports the new version.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/enricoros/big-agi/roll-aix
About the project

Big-AGI is an open-source workspace for using multiple AI models through chat and other AI functions. It is intended for engineers, founders, researchers, and other users who want to work with AI personas, model comparisons, image generation, voice, documents, and code-related features. The catalogue entries provide commands, instructions, and a skill for working with Big-AGI.

enricoros/big-AGI · 7,113 stars · on GitHub · big-agi.com

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/enricoros/big-AGI

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 roll-aix

README.md
[![agentmods](https://agentmods.dev/badge/commands/enricoros/big-agi/roll-aix/github.svg)](https://agentmods.dev/commands/enricoros/big-agi/roll-aix)
Your own site
<a href="https://agentmods.dev/commands/enricoros/big-agi/roll-aix"><img src="https://agentmods.dev/badge/commands/enricoros/big-agi/roll-aix/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 roll-aix

Your own site · 80×15
<a href="https://agentmods.dev/commands/enricoros/big-agi/roll-aix"><img src="https://agentmods.dev/badge/commands/enricoros/big-agi/roll-aix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 279 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 $0.00008 $0.00279
Opus 5 $0.00004 $0.00139
Sonnet 5 $0.00002 $0.00056
Haiku 4.5 $0.00001 $0.00028

Measured 9d ago against content hash 5f4da9d2ee69, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

roll-aix 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 9d 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/aix/roll-aix.md · 25 lines

What it actually says

Increment Monotonics.Aix in src/common/app.release.ts and commit it.

NOTE: rolling AIX refreshes every vendor on every client. Model-definition updates no longer need it (per-vendor versions auto-roll, see kb/modules/LLM-defs-refresh.md); to force-roll a single vendor bump its epoch in src/modules/llms/server/llms.defs.manifest.ts instead. Reserve AIX rolls for protocol-level changes.

Pre-flight checks (MUST pass or abort):

  1. Run git branch --show-current - MUST be on main branch
  2. Run git status src/common/app.release.ts - file MUST be unmodified (no changes on this specific file)

Execute:

  1. Read current Monotonics.Aix value from src/common/app.release.ts
  2. Increment by 1
  3. Update ONLY that line
  4. Run: git add src/common/app.release.ts && git commit -m "Roll AIX"

Confirm new version number.

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. 9d ago First seen · 25 lines · 8 tokens per session scan A 5f4da9d2ee69

Subscribe to this mod's changes

roll-aix is a command published in the GitHub repository enricoros/big-AGI (7,113 stars, last pushed 2d ago), licensed MIT. It adds 8 tokens to every session and 279 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 2026-08-30.