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.
npx agentmods add skills/tobert/gpal/update-modelsnpx skills add tobert/gpal --skill update-modelsgit clone --depth 1 https://github.com/tobert/gpalWhat 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 | $0.00066 | $0.00697 |
| Opus 5 | $0.00033 | $0.00349 |
| Sonnet 5 | $0.00013 | $0.00139 |
| Haiku 4.5 | $0.00007 | $0.00070 |
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 2d 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 — 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
-latestalias (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-001replacinggemini-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_MODELSCLAUDE.md— Model Strategy tablepyproject.toml+src/gpal/__init__.py— Version bump (both must match)
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.
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.
- 2d ago First seen · 77 lines · 66 tokens per session scan A 302e8128cfa6
update-models is a skill published in the GitHub repository tobert/gpal (10 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 697 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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.
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…