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/flurdy/agent-skills/model-update-checknpx skills add flurdy/agent-skills --skill model-update-checkgit clone --depth 1 https://github.com/flurdy/agent-skillsWrote 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.
[](https://agentmods.dev/skills/flurdy/agent-skills/model-update-check)<a href="https://agentmods.dev/skills/flurdy/agent-skills/model-update-check"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/model-update-check.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00041 | $0.01487 |
| Opus 5 | $0.00020 | $0.00744 |
| Sonnet 5 | $0.00008 | $0.00297 |
| Haiku 4.5 | $0.00004 | $0.00149 |
Grade A, and why
model-update-check scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
The fixture test replaces both `pi` and `curl`; it must make no real network request. How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Update Check
Check whether the installed Pi distribution or model IDs in these local configurations merit updating:
~/.pi/agent/model-tier-router.json~/.agents/second-opinion/config.json
This is advisory and read-only. It never edits configuration, reads provider credentials, calls an inference API, or treats a newer release date as sufficient reason to replace a model.
Usage
/model-update-check # Hybrid: active Pi catalog + public live metadata
/model-update-check --offline # Active installed Pi catalog only
Procedure
1. Run the helper
Resolve scripts/model-update-check.sh relative to this SKILL.md and invoke it:
/path/to/model-update-check/scripts/model-update-check.sh
Pass --offline only when the user requested it. Hybrid mode fetches public metadata from
models.dev, OpenRouter's public model catalog, and the public npm package record. When Homebrew is
installed, it also reads local brew info --json=v2 pi-coding-agent metadata to determine whether
the installed formula has an available upgrade; it does not run brew update or brew upgrade.
It sends no API keys. The helper emits JSON and degrades each source independently.
Do not replace this with ad-hoc provider API calls. In particular, do not read Pi's auth store, print environment variables, or send Anthropic/OpenAI/OpenRouter credentials merely to list models.
2. Check source health first
Read sources before interpreting models:
- Invalid or missing config is an error requiring local repair.
piCatalog.status != "ok"means active availability is unknown.modelsDev.status != "ok"means live existence and recent candidates are unknown; do not infer staleness from the installed catalog alone.openRouter.status != "ok"means direct OpenRouter availability/expiration evidence is unknown; retain models.dev as secondary evidence rather than treating silence as removal.homebrew.status == "ok"is the authoritative update signal when Pi is installed from Homebrew.piHomebrewUpdateAvailableshows whether the current local Homebrew metadata reports the formula as outdated.piNpmUpdateAvailableis upstream-release context only in that case.- If
piUpdateAvailableis true, recommend updating Pi through its installed distribution and rerunning this check before changing model IDs. Pi ships built-in model metadata, so a stale release can create false config drift.
What ships with it
2 files 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.
- 5d ago First seen · 148 lines · 41 tokens per session scan A b6394cfb6a1a
model-update-check is a skill published in the GitHub repository flurdy/agent-skills (8 stars, last pushed 7d ago), licensed MIT. It adds 41 tokens to every session and 1,487 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.