Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Intense-Visions/harness-engineeringnpx agentmods add agents/intense-visions/harness-engineering/harness-architecture-enforcerWrote 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/agents/intense-visions/harness-engineering/harness-architecture-enforcer)<a href="https://agentmods.dev/agents/intense-visions/harness-engineering/harness-architecture-enforcer"><img src="https://agentmods.dev/badge/agents/intense-visions/harness-engineering/harness-architecture-enforcer/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/agents/intense-visions/harness-engineering/harness-architecture-enforcer"><img src="https://agentmods.dev/badge/agents/intense-visions/harness-engineering/harness-architecture-enforcer.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 | $0.00030 | $0.08377 |
| Opus 5 | $0.00015 | $0.04189 |
| Sonnet 5 | $0.00006 | $0.01675 |
| Haiku 4.5 | $0.00003 | $0.00838 |
Grade A, and why
harness-architecture-enforcer 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 9d 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 — 730 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Enforce layer boundaries, detect circular dependencies, block forbidden imports
Skills
- enforce-architecture
- check-mechanical-constraints
- harness-dependency-health
Steps
- Run
harness check-deps(always) - Run
harness validate(always)
Methodology
Enforce Architecture
Validate architectural layer boundaries and detect dependency violations. No code may violate layer constraints — this is a hard gate, not a suggestion.
When to Use
- Before approving any pull request or merge
- After writing new imports or module references
- When adding a new module or package to the project
- When
on_pre_commitoron_architecture_checktriggers fire - After refactoring that moves code between layers or modules
- NOT when editing documentation, configuration, or non-code files
- NOT when the violation is intentional and requires a constraint update (escalate instead)
Process
Phase 1: Load Constraints
- Read
harness.config.jsonto understand the project's architectural constraints. The config defines:- Layers — ordered list of architectural layers (e.g.,
ui -> service -> repository -> domain) - Dependency rules — which layers may import from which (typically: layers may only import from layers below them)
- Forbidden imports — specific import paths that are never allowed in certain contexts
- Boundary definitions — which directories/packages belong to which layer
- Layers — ordered list of architectural layers (e.g.,
- Design constraints — when
designconfig exists, also load design constraint rules:- Token compliance — components must reference design tokens, not hardcoded values
- Accessibility compliance — color pairs must meet WCAG contrast ratios
- Anti-pattern enforcement — project-specific anti-patterns from
design-system/DESIGN.md - Platform binding — tokens must have appropriate platform bindings for enabled platforms
- Understand the layer model. In a typical layered architecture:
- Higher layers depend on lower layers (UI depends on Service, Service depends on Repository)
- Lower layers NEVER depend on higher layers (Repository must not import from UI)
- Same-layer imports may or may not be allowed depending on project config
- Cross-cutting concerns (logging, config) have their own rules
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.
- 9d ago First seen · 730 lines · 30 tokens per session scan A c28a00c82cc7
harness-architecture-enforcer is an agent published in the GitHub repository Intense-Visions/harness-engineering (20 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 8,377 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.