optimize-classifier

A procedure for adjusting a local Model Matchmaker classifier based on the times you overrode its recommendations. A classifier is a set of rules that sorts inputs or chooses among options.

In plain words
What is it for?
Use it after collecting enough recommendation and override records to inspect the local logs, suggest keyword changes, and approve updates to the classifier.
Why use it?
It finds recurring patterns in your disagreements so future model recommendations can better reflect your preferences.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/coyvalyss1/model-matchmaker/optimize-classifier
Any agent
npx skills add coyvalyss1/model-matchmaker --skill optimize-classifier
Clone the repo
git clone --depth 1 https://github.com/coyvalyss1/model-matchmaker

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,656 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.01656
Opus 5 $0.00015 $0.00828
Sonnet 5 $0.00006 $0.00331
Haiku 4.5 $0.00003 $0.00166

Measured 2d ago against content hash 3d9c7fc30662, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

optimize-classifier 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.

skills/optimize-classifier/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Optimize My Classifier

This skill helps you personalize your Model Matchmaker classifier based on your actual usage patterns. After you've collected 50+ recommendations, this skill analyzes when you disagreed with the advisor and tunes your local classifier to match your preferences.

What This Skill Does

  1. Reads your local Model Matchmaker logs (~/.cursor/hooks/model-matchmaker.ndjson)
  2. Analyzes when you overrode the advisor's recommendations
  3. Finds patterns in the prompts where you disagreed (common words, task types)
  4. Suggests keyword additions to your model-advisor.sh file
  5. Updates your classifier (with your approval) so future recommendations match your preferences

Privacy: Everything happens locally. No data leaves your machine. You review and approve every change.

Instructions for the AI

You are helping the user optimize their Model Matchmaker classifier based on their personal override patterns. Follow these steps:

Step 1: Read and Validate Log File

Read the NDJSON log file at ~/.cursor/hooks/model-matchmaker.ndjson.

Check if there's enough data:

  • Need at least 50 recommendation events total
  • Need at least 5 OVERRIDE events to find patterns
  • If not enough data, tell the user: "You need more usage data. Come back after 50+ prompts with at least a few overrides."

Step 2: Analyze Override Patterns

Filter to action: "OVERRIDE" events and group by model direction:

Group A: User preferred Opus over recommended Haiku/Sonnet

  • These are prompts where the classifier said "use a cheaper model" but you said "no, I need Opus"
  • Extract common words from prompt_snippet fields in this group

Group B: User preferred Sonnet over recommended Opus

  • These are prompts where the classifier said "use Opus" but you said "no, Sonnet is fine"
  • Extract common words from prompt_snippet fields in this group

Group C: User preferred Sonnet over recommended Haiku

  • Extract common words from prompt_snippet fields in this group

Read the full file on GitHub · 192 lines

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.

  1. 2d ago First seen · 192 lines · 30 tokens per session scan A 3d9c7fc30662

Subscribe to this mod's changes

optimize-classifier is a skill published in the GitHub repository coyvalyss1/model-matchmaker (168 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 1,656 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

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.

microsoft/vscode · 62 tokens