What is update-models?

A maintenance workflow for the model names used by the gpal server, which connects software to Google's Gemini models. It checks whether configured model IDs still exist and identifies newer or replacement models.

Use it when checking model freshness, finding available Gemini models, replacing deprecated IDs, or switching to newer versions. It compares configured constants with the models available through Google's API.

Model providers release new versions and retire old ones, which can make an application fail or use an unintended model. This workflow helps detect and update stale configuration.

How tobert/gpal configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tobert/gpal. 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/tobert/gpal/main/.claude/skills/update-models/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/tobert/gpal

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/tobert/gpal/update-models/github.svg)](https://agentmods.dev/skills/tobert/gpal/update-models)

Your own site

<a href="https://agentmods.dev/skills/tobert/gpal/update-models"><img src="https://agentmods.dev/badge/skills/tobert/gpal/update-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/tobert/gpal/update-models"><img src="https://agentmods.dev/badge/skills/tobert/gpal/update-models.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 697 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.

Model	Per session	Once invoked
Fable 5.1	$0.00066	$0.00697
Opus 5.5	$0.00026	$0.00279
Sonnet 5.5	$0.00013	$0.00139
Haiku 4.5	$0.00007	$0.00070

Measured 2mo ago against content hash 302e8128cfa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

update-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 2mo 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-models/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Models

Maintain and update Gemini model IDs configured in the gpal MCP server.

Overview

gpal configures model IDs as constants at the top of src/gpal/server.py. Google regularly releases new model versions and deprecates old ones. This skill provides the workflow for checking freshness, discovering new models, updating constants, and verifying the changes.

Workflow

Step 1: Check Current Model Freshness

Read the gpal://models/check MCP resource. It compares every configured model against the Google API's available models list and reports status:

ok — Model exists in the API
alias — Uses a -latest alias (resolved server-side, always valid)
not_listed — Model not found in API (may be deprecated or renamed)

Step 2: Discover Available Models

Call the list_models MCP tool to see all models grouped by capability (generateContent, generateImages, embedContent, etc.).

Compare available models against configured constants. Look for:

Newer versions of existing models (e.g., gemini-3-flash-001 replacing gemini-3-flash-preview)
New model families worth adopting
Deprecated models that need replacement

Step 3: Decide on Updates

Apply these rules when choosing model updates:

Slot	Strategy	Rationale
Flash/Pro consult	Pin to specific version	Capabilities matter; test before switching
Search/Code exec	Use `-latest` alias	Stateless utility calls; safe to auto-update
Image generation	Pin to specific version	Output quality varies between versions
Speech	Pin to specific version	Voice behavior changes between versions

Prefer GA models (dated suffix like -001) over preview models when available.

Step 4: Apply Changes

Update all locations listed in references/model-update-checklist.md. The key files:

src/gpal/server.py — Model constants, MODEL_ALIASES, NANO_BANANA_MODELS
CLAUDE.md — Model Strategy table
pyproject.toml + src/gpal/__init__.py — Version bump (both must match)

Read the full file on GitHub · 77 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/model-update-checklist.md 3.2 KB

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.

2mo ago First seen · 77 lines · 66 tokens per session scan A 302e8128cfa6

Subscribe to this mod's changes

update-models is a skill published in the GitHub repository tobert/gpal (10 stars, last pushed 4mo ago), licensed MIT. It adds 66 tokens to every session and 697 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

Building agents

update-models next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
update-modelstobert/gpal	Skill	10	4mo ago	MIT	A	66	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

gpal: Skill for Claude Code