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/yoavaa/design-log-methodologyWrote 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/yoavaa/design-log-methodology/design-log)<a href="https://agentmods.dev/rules/yoavaa/design-log-methodology/design-log"><img src="https://agentmods.dev/badge/rules/yoavaa/design-log-methodology/design-log/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/yoavaa/design-log-methodology/design-log"><img src="https://agentmods.dev/badge/rules/yoavaa/design-log-methodology/design-log.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 | $0.01041 | $0.01041 |
| Opus 5.5 | $0.00416 | $0.00416 |
| Sonnet 5.5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
design-log 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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Log Methodology
The project follows a rigorous design log methodology for all significant features and architectural changes.
Before Making Changes
- Check design logs in
./design-log/for existing designs and implementation notes - For new features: Create design log first, get approval, then implement
- Read related design logs to understand context and constraints
When Creating Design Logs
- Structure: Decisions for the Implementer (TL;DR) → Background → Problem → Prior Art / Adjacent Mechanisms → Questions and Answers → Design → Implementation Plan → Examples → Trade-offs
- Lead with a "Decisions for the Implementer" TL;DR: at the very top, list the settled decisions and the non-obvious constraints (the things a dev would otherwise reconstruct by reading the whole Q&A thread). Thoroughness lives below; navigability lives on top.
- Prior Art / Adjacent Mechanisms section: before designing, enumerate the existing mechanisms in the same area (related primitives, subsystems, and related design logs) and state whether each solves or constrains the problem. This is the author's job up front — do not rely on review to surface what already exists.
- Minimize new surface (null hypothesis first): for every proposed new mechanism (API, type, syntax, runtime facility), first state why an existing primitive does not already suffice. Prefer subtraction. The simpler model is often also the more correct one — reach for new surface only after the null hypothesis fails.
- Trace it through the real code: for any design touching runtime behavior or a data/update path, walk one concrete change through the actual functions with file:line citations before declaring the design sound. Do not reason about runtime behavior abstractly — update gates, reference checks, and lifecycle order are where designs break.
- Be specific: Include file paths, type signatures, validation rules
- Show examples: Use ✅/❌ for good/bad patterns, include realistic code
- Explain why: Don't just describe what, explain rationale and trade-offs
- Ask Questions (in the file): For anything that is not clear, or missing information
- When answering question: keep the questions, just add answers
- Be brief: write short explanations and only what most relevant
- Draw Diagrams: Use mermaid inline diagrams when it makes sense
- Define verification criteria: how do we know the implementation solves the original problem
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.
- 1mo ago Changed · +4 lines · +279 tokens per session a246055dca04
- 1mo ago First seen · 62 lines · 762 tokens per session scan A 6a90dd7aa012
design-log is a cursor rule published in the GitHub repository yoavaa/design-log-methodology (42 stars, last pushed 1mo ago), licensed MIT. It adds 1,041 tokens to every session, about $0.0042 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 2026-08-30.
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).