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.
git 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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 | $0.00261 | $0.00261 |
| Opus 5.5 | $0.00104 | $0.00104 |
| Sonnet 5.5 | $0.00052 | $0.00052 |
| Haiku 4.5 | $0.00026 | $0.00026 |
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 12d 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
Subagent models
- Default: inherit. Every subagent uses the same model as the parent chat. Pass
inherit(or omit the model) on every spawn, for every subagent type. Never choose another model yourself, even for "cheap" or "fast" work like research, exploration, or browser tests. - User override. If the user names a model for subagents, use exactly that model on every spawn until they say otherwise.
- Reset. If the user says to switch back, use the default, or use the same model as this chat, the override ends and subagents inherit again.
- Before each spawn, find the most recent model instruction in the conversation and follow it. If there is none, inherit.
- Unavailable model. If the requested model is not one you can use for subagents, do not substitute. Skip the spawn, say which model was unavailable, and list the available ones.
Delegation
Spawn subagents for work that can run in parallel or that a skill says to delegate. Skills do not choose models; only this rule does.
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.
- 12d ago Changed · -22 lines · -210 tokens per session 7761de1ec023
- 1mo 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 10d ago), licensed MIT. It adds 261 tokens to every session, about $0.0010 per session on Opus 5.5. 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
incremental-verify
Verify each behavior before building the next. One test, one implementation, one commit. No bulk-writing tests for behavior that does not yet exist.
context-discipline
Manage AI context window efficiently - read before write, no re-reads, tool-call budgets, one-pass discipline.
x402-coding
@dexterai/x402 SDK conventions and hosted-only OpenDexter tool usage.
pn-rust-backend
Rust backend style, env, and error handling. Use for API and server code (Actix-web, Axum).
pn-visual-indicator
Tag every pnCore-touched assistant response with a context tag plus 🔺 (red triangle emoji) so the response is visible at a glance in Cursor's chat UI.
pn-tool-risk-policy
MCP tool risk tiers, HITL gates, and when to use approvalcheckpoint and gatelogappend. Use for safety reviews and workflow audits.