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/AG-Dmitry/composer-enhancedWrote 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/ag-dmitry/composer-enhanced/03-design-tradeoffs)<a href="https://agentmods.dev/rules/ag-dmitry/composer-enhanced/03-design-tradeoffs"><img src="https://agentmods.dev/badge/rules/ag-dmitry/composer-enhanced/03-design-tradeoffs.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 5.1 | $0.00027 | $0.00612 |
| Opus 5 | $0.00014 | $0.00306 |
| Sonnet 5 | $0.00005 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
03-design-tradeoffs 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 3 — Design & Trade-offs
Persona: Planner. No code in this phase.
Cheap models grab the first plausible approach and commit. Forcing a second option and an edge-case sweep here prevents expensive rework later.
Steps
-
Sketch the chosen approach at a high level: which files change, what the shape of the change is, and how it satisfies each success criterion from phase 1.
-
Name at least one alternative (required for medium-high and high complexity). State why you rejected it. One sentence each is fine. This forces you out of first-idea tunnel vision.
-
Enumerate edge cases and error paths up front:
- Empty / null / undefined inputs.
- Async failures, races, cancellation, cleanup.
- Boundary values (0, 1, max, off-by-one).
- Existing behavior that must not regress. Decide how each is handled now, not after a bug appears.
-
Confirm scope discipline. The plan must be the minimal diff that meets the criteria — no speculative features, no "while I'm here" refactors.
-
Record the decision as immutable. Write the chosen design + rejected alternatives + rationale into the Decision log of the task-memory file. In later retries you may not silently reverse this decision; if you must change it, add a new dated entry explaining why. This is the main guard against the retry oscillation loop.
Optional: stronger model for design on high-complexity tasks
For tasks classified high in phase 1, if the design space is genuinely
ambiguous or architectural (multiple valid architectures with long-term
consequences), you may spawn a planning subagent with a stronger model
before committing to an approach:
Task(
description: "Design consultant",
subagent_type: "generalPurpose",
readonly: true,
model: "claude-4.6-sonnet-medium-thinking",
prompt: "Given this goal and constraints [paste from working memory], propose
and compare two architectures. Return trade-offs and a recommendation.
Do not implement — design only."
)
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.
- 7d ago First seen · 70 lines · 27 tokens per session scan A eb5fd5a28d3f
03-design-tradeoffs is a cursor rule published in the GitHub repository AG-Dmitry/composer-enhanced (3 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 612 once invoked, about $0.0001 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.