What is update-provider-models?

A maintenance guide for updating the model lists built into pair-review's AI provider integrations. It covers checking provider command-line tools and changing the source configuration.

Use it when adding or updating provider models, checking provider command-line interfaces, and revising pair-review's model configuration.

It keeps the review tool's built-in model choices aligned with models currently available from its supported providers.

How in-the-loop-labs/pair-review configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to in-the-loop-labs/pair-review. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/in-the-loop-labs/pair-review/main/.claude/skills/update-provider-models/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/in-the-loop-labs/pair-review

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/update-provider-models/github.svg)](https://agentmods.dev/skills/in-the-loop-labs/pair-review/update-provider-models)

Your own site

<a href="https://agentmods.dev/skills/in-the-loop-labs/pair-review/update-provider-models"><img src="https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/update-provider-models/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/in-the-loop-labs/pair-review/update-provider-models"><img src="https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/update-provider-models.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,407 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.04407
Opus 5.5	$0.00000	$0.01763
Sonnet 5.5	$0.00000	$0.00881
Haiku 4.5	$0.00000	$0.00441

Measured 10d ago against content hash 82130711114e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

update-provider-models 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 10d 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/skills/update-provider-models/SKILL.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Provider Models

Update the built-in model configurations for pair-review's AI providers. This skill guides you through checking each provider's CLI for available models, gathering recommendations, and updating the source code.

When to Use

Run this skill periodically (e.g., monthly) or when new model releases are announced for any of the supported AI providers. Skip providers that were recently updated.

Providers to Update

The providers are defined in src/ai/ with these files:

antigravity-provider.js - Antigravity CLI (agy) models
codex-provider.js - OpenAI Codex CLI models
copilot-provider.js - GitHub Copilot CLI models
cursor-agent-provider.js - Cursor Agent CLI models
opencode-provider.js - OpenCode CLI (no built-in models, config-only)
claude-provider.js - Anthropic Claude CLI models
pi-provider.js - Pi coding agent models
omp-provider.js - OMP / Oh My Pi CLI (omp, a Pi fork; only a default mode built in, real models are config-only)
muse-provider.js - Meta Muse Code CLI (muse) models

Each provider file has a *_MODELS array at the top defining models with:

id: The CLI model identifier (passed to --model flag)
name: Display name in the UI
tier: One of fast, balanced, thorough (or free, premium)
tagline, description, badge, badgeClass: UI metadata
default: true: Marks the default model for the provider
aliases: Optional extra ids that resolve to this entry (used to keep saved councils/configs working when an id is renamed, and for Claude's bare opus/fable generation aliases, which move to the newest generation on each update)

Ground Rules for Probing

Never trust a CLI's own model listing over a live probe. Installed binaries lag the backend: on 2026-09-06 agy models (agy 1.0.16) did not list Gemini 3.8 Flash, and Muse's cached catalog did not list Spark 1.3, yet both ids ran fine. Conversely, ids a provider file still carries may be dead (gpt-5.4, gemini-3.5-flash). Probe every id you keep AND every id you add.
Probe every provider's fast-tier entry on every run, even when nothing else in that provider changes. The first fast entry serves JSON extraction and hunk summaries (AIProvider.getFastTierModel; guided tours use the provider default, not the fast tier), so a dead one breaks both silently: gpt-5.4-mini was retired for ChatGPT sign-in on 2026-08-31 while it was Codex's only fast entry, and nobody noticed until the 2026-09-22 run.
macOS has no timeout. Wrap probes with perl instead:
```
perl -e 'alarm 120; exec @ARGV' <cli> <args...>
```
Run probes from the scratchpad directory (some CLIs treat cwd as a workspace) and run slow batches with run_in_background.
Do not print ~/.pair-review/config.json wholesale — it holds tokens. Grep only the command lines you need.

Read the full file on GitHub · 277 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.

10d ago Changed · +10 lines 82130711114e
15d ago Changed · +7 lines 59ca30005be5
26d ago Changed · +8 lines c3f1599559c6
1mo ago Changed · +34 lines ab2f51755963
1mo ago Changed · +72 lines 2c7478b19fc6
2mo ago First seen · 146 lines · 0 tokens per session scan A c1b18f57b1a1

Subscribe to this mod's changes

update-provider-models is a skill published in the GitHub repository in-the-loop-labs/pair-review (73 stars, last pushed 8d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,407 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 2026-08-30.

Building agents

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

pair-review: Skill for Claude Code