align-params-uis

align-params-uis is a command for Claude Code from enricoros/big-AGI. It costs 13 tokens per session (649 once invoked), scanned A, original, MIT.

A code-review task for keeping model-parameter controls consistent between a full model settings window and a chat side panel. It compares their available options and change-handling code.

In plain words
What is it for?
Use it to inspect the named source files, compare parameter option lists and values, check the side panel’s selected settings, and update differences so both editors behave equivalently.
Why use it?
It helps find settings that are missing, mismatched, or handled differently between the two interfaces. The side panel intentionally shows only a selected group of parameters.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to inspect the named source files, compare parameter option lists and values, check the side panel’s selected settings, and update differences so both editors behave equivalently.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/enricoros/big-agi/align-params-uis
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 · 7,114 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 align-params-uis

README.md
[![agentmods](https://agentmods.dev/badge/commands/enricoros/big-agi/align-params-uis.svg)](https://agentmods.dev/commands/enricoros/big-agi/align-params-uis)
Your own site
<a href="https://agentmods.dev/commands/enricoros/big-agi/align-params-uis"><img src="https://agentmods.dev/badge/commands/enricoros/big-agi/align-params-uis.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 649 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 $0.00013 $0.00649
Opus 5 $0.00006 $0.00324
Sonnet 5 $0.00003 $0.00130
Haiku 4.5 $0.00001 $0.00065

Measured 8d ago against content hash 40e25d6d7754, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

align-params-uis 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 8d 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/llms/align-params-uis.md · 64 lines

What it actually says

Audit and sync LLM parameter configurations between the two UI editors. Goal: identical value fields in option arrays + equivalent onChange logic. Labels/descriptions can differ for UI space.

Files to Compare:

  1. Full Model Dialog: src/modules/llms/models-modal/LLMParametersEditor.tsx (main branch)
  2. Chat Side Panel: src/apps/chat/components/layout-panel/ChatPanelModelParameters.tsx (main derived branches only)

Reference Documentation:

  • Parameter system: kb/systems/LLM-parameters-system.md
  • Parameter registry: src/common/stores/llms/llms.parameters.ts

Task: Perform a comprehensive audit

  1. Read both files and extract all option arrays (e.g., _reasoningEffortOptions, _antEffortOptions, _geminiThinkingLevelOptions, etc.)

  2. Check for missing parameters:

    • Parameters handled in LLMParametersEditor.tsx but NOT in ChatPanelModelParameters.tsx
    • Parameters in ChatPanelModelParameters.tsx's _interestingParameters array but missing UI controls
    • Note: The side panel intentionally shows only "interesting" parameters - focus on those listed in _interestingParameters
  3. Check for value mismatches between corresponding option arrays:

    • Different number of options (e.g., 3 vs 4 options)
    • Same label but different value (this causes the bug in issue #926)
    • Different labels for the same value
    • Missing _UNSPECIFIED/Default option in one but not the other
  4. Check onChange handler consistency:

    • Both should remove parameter on _UNSPECIFIED selection
    • Both should set explicit values the same way
    • Watch for conditions like value === 'high' that may differ

Output Format:

## Parameter Sync Audit Report

### Missing Parameters
- [ ] `llmVndXyz` - In full dialog, missing from side panel

### Value Mismatches
- [ ] `_xyzOptions`:
  - Full dialog: [values...]
  - Side panel: [values...]
  - Issue: [description]

### Handler Inconsistencies
- [ ] `llmVndXyz` onChange differs: [explanation]

### Recommended Fixes
1. [Specific fix with code snippet if needed]

Fix Direction: Full dialog is source of truth. Update side panel to match its values when mismatched.

Notes:

  • Side panel uses shorter descriptions (space-constrained) - that's fine
  • Variable names may differ (e.g., _anthropicEffortOptions vs _antEffortOptions) - that's fine, but same is better
  • value fields must be identical sets
  • _UNSPECIFIED must mean the same thing in both
  • onChange: remove on _UNSPECIFIED, set explicit value otherwise
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. 8d ago First seen · 64 lines · 13 tokens per session scan A 40e25d6d7754

Subscribe to this mod's changes

align-params-uis is a command published in the GitHub repository enricoros/big-AGI (7,114 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 649 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 2026-08-30.