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.
npx agentmods add commands/romilly/claude-code-helpers/hexagonalgit clone --depth 1 https://github.com/romilly/claude-code-helpersWhat 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 | $0.00000 | $0.00319 |
| Opus 5 | $0.00000 | $0.00160 |
| Sonnet 5 | $0.00000 | $0.00064 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
hexagonal 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 yesterday.
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
Hexagonal Architecture and Walking Skeleton
Architecture Principles
Use hexagonal (ports and adapters) architecture:
- Domain logic: Completely independent of I/O, persistence, external systems
- Ports: Abstract interfaces (Python ABCs) defining boundaries
- Adapters: Implement ports for specific technologies
- Dependencies flow inward: adapters depend on ports, never reverse
Structure:
src/project_name/
├── domain/ # Pure business logic, no I/O
├── ports/ # Abstract interfaces (ABCs)
└── adapters/ # Implementations (fake, real)
Walking Skeleton
- Define the use case (Cockburn style: system, actor, goal, main scenario, extensions)
- Build minimal end-to-end with fake adapters returning hardcoded results
- Verify with end-to-end tests in clean environment
- Iterate with TDD, replacing fakes incrementally
The skeleton proves the architecture works before investing in real functionality.
Testing: Fake Adapters, Not Monkeypatching
Never monkeypatch (pyfakefs, unittest.mock.patch for dependencies):
- Creates invisible dependencies
- Tests can pass without verifying anything meaningful
- "Action at a distance" — setup disconnected from calls
Use explicit dependency injection:
- Ports as ABCs with explicit signatures
- Fake adapters implementing the port interface
- Constructor injection so dependencies are visible
- Contract tests verifying fakes and real adapters both satisfy ports
Fake adapters must be fully functional, just using in-memory storage.
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.
- yesterday First seen · 43 lines · 0 tokens per session scan A cf76ded05a43
hexagonal is a command published in the GitHub repository romilly/claude-code-helpers (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 319 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.