model-economics

model-economics is a cursor rule for Cursor from hmj1026/dhpk. It costs 7 tokens per session (3,599 once invoked), scanned A, original, MIT.

A set of rules for choosing model tiers and controlling their costs for different agent roles. It covers configured model choices, effort settings, fallbacks, and time limits.

In plain words
What is it for?
It is for routing deep reasoning, fast work, review, and command-line worker roles to configured models and applying their cost-related settings.
Why use it?
It gives the system a consistent way to balance the required work level with resource use instead of choosing models ad hoc.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: mentions subagents; positional $N argument; mentions Claude Code.

Good fit It is for routing deep reasoning, fast work, review, and command-line worker roles to configured models and applying their cost-related settings.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/hmj1026/dhpk/model-economics
View source ↗ hmj1026/dhpk
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.

Clone the repo
git clone --depth 1 https://github.com/hmj1026/dhpk

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 model-economics

README.md
[![agentmods](https://agentmods.dev/badge/rules/hmj1026/dhpk/model-economics/github.svg)](https://agentmods.dev/rules/hmj1026/dhpk/model-economics)
Your own site
<a href="https://agentmods.dev/rules/hmj1026/dhpk/model-economics"><img src="https://agentmods.dev/badge/rules/hmj1026/dhpk/model-economics/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.

agentmods 80×15 button for model-economics

Your own site · 80×15
<a href="https://agentmods.dev/rules/hmj1026/dhpk/model-economics"><img src="https://agentmods.dev/badge/rules/hmj1026/dhpk/model-economics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,599 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00007 $0.03599
Opus 5.5 $0.00003 $0.01440
Sonnet 5.5 $0.00001 $0.00720
Haiku 4.5 $0.00001 $0.00360

Measured yesterday against content hash 3c5cceb82954, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

model-economics 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 yesterday.

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/model-economics.mdc · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Economics — tier map & cost rules

SSOT for which model tier each role runs on, and the cost rules that govern tier and effort choices. The dispatch routing decision — which agent handles which work shape — lives in ${POLICY_BUNDLE_ROOT}/rules/execution-policy.md §Implementation dispatch; this file owns the cost lens over that routing and does not restate its work-shape rows. Native-vs-external candidate selection follows the shared Native dispatch baseline in execution-policy.md; model economics ranks an already-valid candidate and never enables cross-provider probing. Resource-layer markdown, opt-in — referenced from execution-policy.md §Agent dispatch (model-tier + configured-role paragraphs).

Reviewers keep a sonnet floor — no downward tiering. reviewer_target is the only public reviewer entry. Runtime-tunable via userConfig: the four <role>_target keys (worker_target, reasoner_target, planner_target, reviewer_target, format <agent>/<model>[:<effort>]) carry model and effort for every Role, including the CLI-backed codex-worker, codex-reasoner, codex-reviewer, and agy-worker (their model and effort come from the matching <role>_target when its target Agent is that CLI; agy bakes effort into the model name). The former *_model / *_effort keys (fast_worker_*, deep_reasoner_*, codex_fast_worker_*, codex_deep_reasoner_*, agy_fast_worker_model, and the rest) are removed keys, reported BLOCKED and not applied; see the configuration guide's "Removed in 0.69.0" section. Only timeouts stay role-specific: codex_worker_timeout_secs, codex_reasoner_timeout_secs, codex_reviewer_timeout_secs, with the shared codex_timeout_secs; budgets are integer seconds, 0 is an intentional dispatcher-attested no-deadline request, and malformed values fail closed. The portable runner, never a shell timeout backstop, enforces an attested nonzero deadline. The rest of the map is documentation for humans, not a runtime dial.

Read the full file on GitHub · 111 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. yesterday Changed · -1 tokens per session 3c5cceb82954
  2. 2d ago Changed · +11 lines 12bd6e7eb89c
  3. 12d ago Changed · +5 lines dc0ce1749f10
  4. 14d ago Changed · +19 lines 5e17b5401969
  5. 19d ago Changed a47275b882c5
  6. 28d ago Changed · +4 lines 411b7c05d6b6
  7. 1mo ago Changed · +5 lines 93691eaac894
  8. 1mo ago Changed 38062164be99
  9. 1mo ago Changed 7ad5212b2d2b
  10. 1mo ago First seen · 67 lines · 8 tokens per session scan A 0c2079b4864d

Subscribe to this mod's changes

model-economics is a cursor rule published in the GitHub repository hmj1026/dhpk (2 stars, last pushed yesterday), licensed MIT. It adds 7 tokens to every session and 3,599 once invoked, about $0.0000 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 2026-09-05.