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 instructions/jaace/claude-model-advisor/claude-mdgit 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/instructions/jaace/claude-model-advisor/claude-md)<a href="https://agentmods.dev/instructions/jaace/claude-model-advisor/claude-md"><img src="https://agentmods.dev/badge/instructions/jaace/claude-model-advisor/claude-md.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 | $0.00584 | $0.00584 |
| Opus 5 | $0.00292 | $0.00292 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
claude-model-advisor CLAUDE.md 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 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.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repo is
A Claude Code plugin that injects model/effort guidance at session start. It has no build system, no dependencies, and no tests — it's a shell script and a set of prompt/config files.
Plugin structure
.claude-plugin/plugins/model-advisor/
├── .claude-plugin/plugin.json # Plugin metadata (name, version, author)
├── hooks/hooks.json # Registers the SessionStart hook
├── hooks-handlers/session-start.sh # Core logic: outputs JSON with additionalContext
└── commands/model-check.md # Prompt for the /model-check skill
The marketplace.json at the root registers this repo as a marketplace source pointing to ./.claude-plugin/plugins/model-advisor.
How it works
hooks.jsonregisters aSessionStarthook that runssession-start.sh(5s timeout)session-start.shemits a JSON blob withhookSpecificOutput.additionalContext— this is the text Claude receives at session startmodel-check.mdis a skill prompt used for mid-session reassessment via/model-check
The model/effort guidance matrix
The core content this plugin delivers (defined in session-start.sh and model-check.md):
Model — what capability is needed?
haiku: simple lookups, quick edits, boilerplate, single-fact questionssonnet: coding, debugging, refactoring, explanations, any question with tradeoffs or nuanced judgmentopus: novel multi-system architecture, hard math, genuinely ambiguous open-ended design problems
Effort — how much reasoning is needed? (not applicable to Haiku; max is Opus only)
auto: Claude decides based on the task (default)low: established knowledge retrieval/explanation; shape of answer is knownmedium: some reasoning required; path is clearhigh: ambiguous problems, hard tradeoffs, novel synthesis, many interdependent constraintsmax(Opus 4.6 only): maximum thinking budget; for the hardest problems where cost is no concern
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 · 56 lines · 584 tokens per session scan A 4fc7d2d8cc38
claude-model-advisor CLAUDE.md is an instructions file published in the GitHub repository Jaace/claude-model-advisor (2 stars, last pushed 4mo ago), licensed MIT. It adds 584 tokens to every session, about $0.0029 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 instructions, from other repositories
gradio AGENTS.md
AGENTS.md instructions for gradio-app/gradio, covering agents.md, repository structure, pull request rules, code style and agentic contribution policy.
huggingface_hub AGENTS.md
AGENTS.md instructions for huggingface/huggingface_hub, covering agent guide for huggingfacehub, project overview, setup, key commands and code structure.
relarena AGENTS.md
AGENTS.md instructions for PriorLabs/relarena, covering relarena — agent notes, this repo is public, adding or changing a model, refactor-friendly structure rules and macos: run tests / cli with ompnumthreads=1.
llamafarm AGENTS.md
Instructions for llama-farm/llamafarm, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
llamafarm CLAUDE.md
Instructions for llama-farm/llamafarm, covering llamafarm, monorepo overview, building and running and examples.
relarena CLAUDE.md
Claude Code instructions for PriorLabs/relarena: All package notes live in AGENTS.md — read that first.