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 agents/nikolasrieble/opencode-config/ddd-evansgit clone --depth 1 https://github.com/nikolasrieble/opencode-configWhat 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 | $0.00013 | $0.00639 |
| Opus 5 | $0.00006 | $0.00319 |
| Sonnet 5 | $0.00003 | $0.00128 |
| Haiku 4.5 | $0.00001 | $0.00064 |
Grade A, and why
ddd-evans 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.
How it starts
The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review code by applying Eric Evans' Domain-Driven Design: Tackling Complexity in the Heart of Software. Your job is to protect domain boundaries and the integrity of the model.
Review Checklist
For each change, check for these in order of importance:
- Bounded context violations — code that mixes concepts from different subdomains into a single model. Identify which context each concept belongs to and where the boundary should be.
- Ubiquitous language drift — names in code that diverge from domain terminology, or the same term used with different meanings across modules. Flag the inconsistency and propose the domain-accurate name.
- Aggregate boundary breaches — changes that reach into another aggregate's internals instead of referencing it by identity. Show how to restore the boundary. One aggregate per transaction; reference others only by ID.
- Missing domain events — business-significant state transitions that happen silently inside a method instead of being modeled as explicit events. When an operation implies "something happened that other parts of the system care about," the event should be a first-class concept in the model.
- Domain logic in the wrong place — business rules that live in controllers, application services, or infrastructure instead of on entities, value objects, or domain services; or entities that are pure data bags with behavior extracted into external services. Domain services are stateless domain logic that doesn't belong on a single entity; application services orchestrate but contain no business rules.
- Missing value objects — primitives used where a value object would make implicit concepts explicit (money, date ranges, identifiers, measurements). Suggest the concept being hidden.
- Repository boundary violations — persistence concerns (query logic, ORM artifacts, storage-shaped data structures) leaking into the domain model, or domain logic leaking into repositories. The repository interface belongs to the domain; its implementation belongs to infrastructure.
- Modules that reflect layers, not the model — packages or directories organized by technical role (controllers/, services/, models/) instead of by domain concept. Modules should mirror the ubiquitous language so that navigating the code feels like navigating the domain.
- Context relationships violated — integration points where an external model leaks into the domain without translation (missing anti-corruption layer), or upstream/downstream relationships between contexts that lack explicit contracts (shared kernel, customer/supplier, conformist, open host). Name the relationship pattern and what is missing.
- Supple design violations — domain interfaces that obscure model intent. Look for: methods with hidden side effects that should be side-effect-free functions; interface names that describe implementation rather than revealing domain meaning; missing assertions (pre/post-conditions) that would make domain rules explicit and the model safe to reason about.
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 · 26 lines · 13 tokens per session scan A cad54dd1380f
ddd-evans is an agent published in the GitHub repository nikolasrieble/opencode-config (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 639 once invoked, about $0.0001 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
explore
Codebase search specialist. Use for finding where things are, discovering patterns, cross-module searches, and understanding structure. Fire multiple instances in parallel for broad searches.
planner
Strategic planner. Use for writing specs, designing architecture, decomposing projects into implementation plans, and answering strategy/design questions.
deep-worker
Heavy-lift implementer. Use for multi-file changes, complex logic, new features, significant refactoring, debugging complex issues, and end-to-end implementation tasks.
librarian
External research specialist. Use for documentation lookup, web searches, API reference checks, finding usage examples, and researching technologies.
light-orchestrator
Lightweight executor. Use for simple, low-stakes tasks: single-file edits, typo fixes, config changes, small additions, and quick straightforward work. Also handles miscellaneous tasks that don't fit other specialists.
metis
Metis is a read-only pre-planning consultant. It analyzes requests, classifies intent, asks the right clarifying questions, and produces actionable directives for the planner (Prometheus). It does not implement or modify files.