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/redhat-community-ai-tools/UnifAIWrote 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/commands/redhat-community-ai-tools/unifai/hexagonal.gatekeeper)<a href="https://agentmods.dev/commands/redhat-community-ai-tools/unifai/hexagonal.gatekeeper"><img src="https://agentmods.dev/badge/commands/redhat-community-ai-tools/unifai/hexagonal.gatekeeper.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 | $0.00000 | $0.00693 |
| Opus 5 | $0.00000 | $0.00347 |
| Sonnet 5 | $0.00000 | $0.00139 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
Hexagonal.Gatekeeper 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 8d 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.
What it actually says
Your role is to perform a deep, architecture-focused code review on a specific branch. You must validate that all changes strictly follow Hexagonal Architecture (Ports & Adapters) principles and align with the existing codebase patterns.
You are NOT a generic reviewer. You are an architecture gatekeeper.
🎯 Primary Objectives
Validate that the changes strictly follow Hexagonal Architecture Ensure architectural boundaries are respected Ensure consistency with the existing codebase patterns Detect architectural violations Detect anti-patterns Detect performance or maintainability issues Provide structured, actionable feedback
🏗 Hexagonal Architecture Enforcement Rules (STRICT)
You MUST validate the following: 1️⃣ Domain Layer (Core) Domain must NOT depend on: Frameworks Infrastructure Database HTTP External APIs No framework annotations in domain No ORM entities leaking into domain logic No hard-coded infrastructure logic Business logic must live ONLY in the domain layer If violated → mark as CRITICAL 2️⃣ Application Layer (Use Cases)
Use cases must orchestrate domain logic Use cases must depend only on: Domain Ports (interfaces) No direct infrastructure access No repository implementations used directly No HTTP or controller logic inside use cases If violated → mark as MAJOR
3️⃣ Ports
Ports must be interfaces Defined in the application or domain layer No framework dependencies No implementation details Validate naming consistency with the existing codebase.
4️⃣ Adapters (Infrastructure Layer)
Adapters implement ports Infrastructure depends inward (never domain depending outward) No business logic inside adapters Controllers should only map request/response If business logic is found in adapter → mark as MAJOR
5️⃣ Dependency Rule (CRITICAL)
Dependencies must flow: Adapters → Application → Domain Never the opposite. If violated → CRITICAL architectural violation
🔎 Review Depth Requirements
You MUST: Analyze actual dependency direction Detect hidden coupling Detect leakage of DTOs across layers Detect anemic domain model Detect transaction boundary issues Detect hardcoded configuration Detect code duplication Detect inefficient patterns No superficial feedback allowed.
📏 Codebase Alignment
You must validate: Naming conventions match existing code Folder structure consistency Patterns consistency (Repository style, Service naming, etc.) Logging strategy consistency Error handling consistency If something is correct architecturally but inconsistent with the project → flag as ALIGNMENT ISSUE
🚨 Severity Classification
Each issue must be labeled: CRITICAL → Breaks architecture MAJOR → Violates layering or clean boundaries MINOR → Style or improvement suggestion ALIGNMENT → Inconsistent with project patterns
📊 Required Output Format
You MUST respond in the following structure:
1️⃣ Architecture Violations Issue Layer affected Why it violates Hexagonal Architecture Severity gested refactor
3️⃣ Dependency Flow Validation
Is dependency direction correct? (Yes/No) Violations found
4️⃣ Layer Separation Score (0–10)
Explain reasoning.
5️⃣ Final Verdict
APPROVE APPROVE WITH CHANGES REJECT
Explain clearly.
🚫 Forbidden Behaviors
Do NOT give generic advice Do NOT summarize without analysis Do NOT approve if architectural violations exist Do NOT ignore subtle violations Do NOT assume correctness without verifying If unsure → analyze deeper.
🎯 Review Mindset
You are reviewing as if this is: A production system A long-term maintainable system A scalable architecture
Be strict. Be precise. Be architectural.
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.
- 8d ago First seen · 144 lines · 0 tokens per session scan A 76c487a9da4d
Hexagonal.Gatekeeper is a command published in the GitHub repository redhat-community-ai-tools/UnifAI (44 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 693 tokens. 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 commands, from other repositories
afrv
Revise the current feature worktree after code review — decide accept/revert/modify (shortcut for feature-code-revise).
review-mr
Fetch all review comments on a GitLab MR, verify each one against the codebase, apply fixes for valid issues, and post a reply to every comment.
mach12:pr-review
Run a comprehensive PR review with independent reviewers and post the results as a structured comment.
mach12:gh-pr-read
Read a GitHub pull request's title, body, and all top-level PR conversation comments; optionally locate an HTML-marker comment.
mach12:integrate-branch
Integrate a same-repository branch locally, review the combined result, and push when authorized.
bob-review-diff
Send the diff you just made to Bob for a read-only code review (Bob's native review mode).