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 commands/jaace/claude-model-advisor/model-checkgit clone --depth 1 https://github.com/Jaace/claude-model-advisorWrote 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/commands/jaace/claude-model-advisor/model-check)<a href="https://agentmods.dev/commands/jaace/claude-model-advisor/model-check"><img src="https://agentmods.dev/badge/commands/jaace/claude-model-advisor/model-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 | $0.00000 | $0.00415 |
| Opus 5 | $0.00000 | $0.00208 |
| Sonnet 5 | $0.00000 | $0.00083 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
model-check 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 3d 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.
What it actually says
Reassess the current session and recommend the right model and effort level.
-
Briefly summarize what this session has been about so far (1-2 sentences).
-
Assess complexity on this scale:
- Simple: lookups, quick edits, factual Q&A, boilerplate
- Moderate: debugging, refactoring, multi-step coding tasks, explanations
- Complex: architecture decisions, hard reasoning, math, novel multi-system design
-
Choose model and effort independently — they are separate axes:
Model (what capability is needed?):
haiku— simple lookups, quick edits, boilerplate, straightforward factual questions; no effort levelsonnet— coding, debugging, refactoring, explanations, conceptual questions with some depthopus— novel architecture, hard math, genuinely ambiguous or open-ended design problems
Effort (how much reasoning is needed? — not applicable for Haiku; max is Opus only):
auto— Claude decides effort based on the task (default)low— the shape of the answer is already known; you are retrieving or explaining established knowledge, even if the topic is complexmedium— some reasoning or multi-step thinking required; the answer isn't immediately obvious but the path is clearhigh— genuinely hard reasoning required; the problem is ambiguous, involves hard tradeoffs with no clear answer, requires novel synthesis, or has many interdependent constraintsmax(Opus 4.6 only) — maximum thinking budget; use for the hardest problems where cost is no concern
-
Give a one-line rationale.
-
If a switch is warranted, tell the user to run
/modelto switch (up/down for model, left/right for effort). To adjust effort level only, they can run/effort [low|medium|high|max|auto].
No tools needed — pure reasoning and output only.
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.
- 3d ago First seen · 26 lines · 0 tokens per session scan A d2920df1f322
model-check is a command published in the GitHub repository Jaace/claude-model-advisor (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 415 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 2026-08-31.
Other commands, from other repositories
github_issues
You are tasked with managing GitHub issues, including creating issues from thoughts documents, updating existing issues, and following the team's specific workflow patterns.
research
A fast, reliable way for agents to understand this monorepo before implementing an issue. Follow this checklist to map scope, find the right code, and de‑risk changes.
plan
Turn your completed research into a minimal, verifiable change plan. This document helps you define scope, sequence work, and specify how you’ll prove success before writing code.
describe_pr
You are tasked with generating a comprehensive pull request description following the repository's standard template.
commit
You are tasked with creating git commits for the changes made during this session.
founder_mode
you're working on an experimental feature that didn't get the proper ticketing and pr stuff set up.