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 rules/hlalljie/agent-workflow-presets/agent-modelsgit clone --depth 1 https://github.com/hlalljie/agent-workflow-presetsWrote 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/rules/hlalljie/agent-workflow-presets/agent-models)<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>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 | $0.00471 | $0.00471 |
| Opus 5 | $0.00235 | $0.00235 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
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.
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:
- Tasks must run sequentially (true dependency — each output feeds the next input)
- 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.
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 · 39 lines · 471 tokens per session scan A 61033835dff4
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.
Other cursor rules, from other repositories
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.
python
Python best practices with type hints, async patterns, and modern idioms.
general-python-project-rules
General Python project rules for all Python files in the project. Enforces specific Python versions and class usage.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.