agent-models

agent-models is a cursor rule for Cursor from hlalljie/agent-workflow-presets. It costs 471 tokens per session, scanned A, original, MIT.

A registry that assigns named coding-agent roles, such as writer, coder, researcher, or verifier, to specific AI models.

In plain words
What is it for?
Use it to define model choices for planning, writing instructions, coding, research, browser testing, and final checks.
Why use it?
It removes guesswork when choosing which model should handle a delegated task. Roles are referenced with signals such as [MODEL:coder].

Cursor rule for Cursor

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 rules/hlalljie/agent-workflow-presets/agent-models
Clone the repo
git clone --depth 1 https://github.com/hlalljie/agent-workflow-presets

Made for: Cursor.

Wrote 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.

agentmods badge for agent-models

README.md
[![agentmods](https://agentmods.dev/badge/rules/hlalljie/agent-workflow-presets/agent-models.svg)](https://agentmods.dev/rules/hlalljie/agent-workflow-presets/agent-models)
Your own site
<a href="https://agentmods.dev/rules/hlalljie/agent-workflow-presets/agent-models"><img src="https://agentmods.dev/badge/rules/hlalljie/agent-workflow-presets/agent-models.svg" alt="Measured on agentmods" height="20"></a>
Per session 471 This file is loaded in full into every session.
When invoked 471 The same file — it is already loaded in full.
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 $0.00471 $0.00471
Opus 5 $0.00235 $0.00235
Sonnet 5 $0.00094 $0.00094
Haiku 4.5 $0.00047 $0.00047

Measured 3d ago against content hash 61033835dff4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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 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.

.cursor/rules/agent-models.mdc · 39 lines

What it actually says

Agent Model Registry

When you see [MODEL:X] anywhere in a skill or rule, look up the role X below and use that model. Do not guess, substitute, or default to another model.

  • orchestrator: claude-4.6-sonnet-medium-thinking
  • writer: claude-4.6-sonnet-medium-thinking — planning, instruction writing, drafting
  • coder: composer-2.5-fast — standard implementation tasks
  • complex-coder: claude-4.6-sonnet-medium-thinking — tasks the user flags as complex, or after repeated failures in the loop
  • researcher: composer-2.5-fast — codebase and internet research
  • browser-tester: composer-2.5-fast — manual browser testing via MCP
  • verifier: claude-4.6-sonnet-medium-thinking — code quality, architecture review, final checks

Usage

Reference a role inline wherever you delegate: [MODEL:coder], [MODEL:verifier], etc.

When spawning a subagent, pass the model ID from this registry. If the platform does not honor the model field for your plan type, document the intent and proceed — the registry is still the source of truth for what was intended.

Delegation policy

The orchestrator coordinates, plans, reviews, and commits. It delegates implementation, research, and testing to the appropriate model above.

Always spawn subagents when tasks can run in parallel — even if there is only one task. The orchestrator must not occupy itself with a single implementation task when it could be coordinating.

Only act directly when both conditions are met:

  1. Tasks must run sequentially (true dependency — each output feeds the next input)
  2. The current model matches the required model for that task type

If either condition fails, spawn a subagent.

Updating models

Change the value here only. All skills and rules that use [MODEL:X] signals automatically reflect the update.

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. 3d ago First seen · 39 lines · 471 tokens per session scan A 61033835dff4

Subscribe to this mod's changes

agent-models is a cursor rule published in the GitHub repository hlalljie/agent-workflow-presets (2 stars, last pushed 1mo ago), licensed MIT. It adds 471 tokens to every session, about $0.0024 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.