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/Intense-Visions/harness-engineeringWrote 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/intense-visions/harness-engineering/respect-architecture)<a href="https://agentmods.dev/rules/intense-visions/harness-engineering/respect-architecture"><img src="https://agentmods.dev/badge/rules/intense-visions/harness-engineering/respect-architecture.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 | $0.00460 | $0.00460 |
| Opus 5 | $0.00230 | $0.00230 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
respect-architecture 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Respect architecture
If the project has layer definitions in harness.config.json (intermediate adoption level or above), every new or modified import must stay within the allowed direction.
How to check before adding an import
Before adding import X from 'foo':
- Identify which layer the importing module belongs to (by file path, mapped through
harness.config.json→layers). - Identify which layer
foobelongs to. - Cross-reference against
harness.config.json→constraints(or equivalent). If the direction is forbidden, do not add the import.
harness check-deps will catch the violation, but waiting for it wastes the human's time. Catch it at design time.
Common forbidden patterns
- Skipping the service layer — routes/controllers importing directly from db/repositories. Almost always wrong; route through services.
- Upward imports — data layer importing from business layer, business layer importing from presentation. Inverts the dependency direction.
- Circular deps — module A imports B, B imports A.
harness check-archtracks these against a baseline; net-new circles are blockers.
When the constraint feels wrong
The constraint exists for a reason — typically a real incident or a deliberate architectural decision. Before proposing to relax it:
- Read
AGENTS.mdand any architecture-relevant docs indocs/. Is the rationale recorded? - If the rationale is unclear, ask the human before refactoring around it.
- If the constraint genuinely doesn't fit the new code, propose changing it explicitly (with a code change to
harness.config.json), not bypassing it.
What you must not do
- Never add
// eslint-disable-next-lineor// harness-ignoreto suppress a layer violation. If the violation is intentional, change the constraint. If it's a bug, refactor. - Never assume "it's just one import, fix it later." Architectural drift compounds.
- Never refactor existing layer rules without confirming with the human first.
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 · 460 tokens per session scan A c3c481de8a41
respect-architecture is a cursor rule published in the GitHub repository Intense-Visions/harness-engineering (20 stars, last pushed yesterday), licensed MIT. It adds 460 tokens to every session, about $0.0023 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 2026-09-03.
Other cursor rules, from other repositories
clean-code-reviewer
Eliminates technical debt using SOLID, DRY, YAGNI, and Addy Osmani production-grade engineering principles. / TR: SOLID, DRY, YAGNI ve Addy Osmani üretim seviyesi mühendislik ilkeleri ile kod kalitesini denetleyen yetenek.
sweep-benchmarks
Audit xrspatial modules for asv benchmark coverage gaps: missing benchmarks, backend parameterization gaps, unrepresentative inputs, broken or silently-skipped benchmarks.
code-review
BMAD BMM Agent: code-review.
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.