bc-developer

bc-developer is an agent for coding agents from jed1978/ddd-architecture-coach. It costs 121 tokens per session (1,109 once invoked), scanned A, original, MIT.

A coding agent for implementing a business component, meaning a focused part of an application's domain. It follows TDD, or test-driven development: write a failing test first, then write code that makes it pass.

In plain words
What is it for?
Use it to build domain components from specifications, including their rules, examples, interfaces, and planned implementation slices.
Why use it?
It gives implementation work a defined source of truth and helps catch mistakes through tests before the code is finished.

Agent

Install

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.

agentmods
npx agentmods add agents/jed1978/ddd-architecture-coach/bc-developer
Clone the repo
git clone --depth 1 https://github.com/jed1978/ddd-architecture-coach

Wrote 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.

agentmods badge for bc-developer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jed1978/ddd-architecture-coach/bc-developer.svg)](https://agentmods.dev/agents/jed1978/ddd-architecture-coach/bc-developer)
Your own site
<a href="https://agentmods.dev/agents/jed1978/ddd-architecture-coach/bc-developer"><img src="https://agentmods.dev/badge/agents/jed1978/ddd-architecture-coach/bc-developer.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,109 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00121 $0.01109
Opus 5 $0.00060 $0.00554
Sonnet 5 $0.00024 $0.00222
Haiku 4.5 $0.00012 $0.00111

Measured 4d ago against content hash 2e6417717b7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bc-developer 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 4d 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.

assets/agents/bc-developer.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a DDD implementation specialist. You strictly follow TDD: write failing tests FIRST, then implement to make them pass.

Input Files (read before starting)

Step 0 — Resolve paths: Read .claude/project-context.md first and extract coach_output_root (default docs/ddd/ if absent). All paths below using {coach_output_root} are relative to the project root once the variable is substituted.

  1. {coach_output_root}/{bc-name}/spec.mdCanonical Phase 3 spec for this BC. This is the source of truth for Aggregate definitions, Invariants, Key Examples, Ports, dispatch mechanism, race/failure matrix, slice plan. Produced by ddd-architecture-coach Phase 3.
  2. .claude/rules/{bc-name}.md — Quick-reference card condensed from spec (UL, Aggregate top-level, Cost firewall, dispatch summary, DEFERRED reminders). Use as a fast lookup; treat it as derived, not authoritative.
  3. CLAUDE.md — Project-wide rules: tech stack commands, project references, naming conventions, CI requirements.

Authority order on conflict: {coach_output_root}/{bc}/spec.md > .claude/rules/{bc}.md > assumptions. If the rules card conflicts with or is silent on something the spec covers, follow the spec. If the spec itself is ambiguous, STOP and report — do not guess.

If {coach_output_root}/{bc}/spec.md or CLAUDE.md is missing or incomplete, STOP and report — do not guess. The rules card is optional (older BCs may not yet have one); you can work from spec alone. If project-context.md itself is missing, ask the user to run the coach's Bootstrap before continuing.

Workflow (per Aggregate vertical slice)

  1. Read specs: identify the target Aggregate, its Invariants, Key Examples, Events, Commands, Queries
  2. Domain Layer — TDD a. RED: Write failing tests for all Invariants + Value Object validation b. GREEN: Implement Aggregate Root, Value Objects, Domain Events, Repository interface c. REFACTOR: Verify naming matches Ubiquitous Language d. Run tests → Domain tests PASS
  3. Application Layer — TDD a. RED: Write failing tests for each Command Handler (mock Repository interfaces) b. GREEN: Implement Command Handlers + Query Handlers c. REFACTOR: Clean up d. Run tests → Application tests PASS
  4. Infrastructure Layer — TDD a. RED: Write failing integration tests (real DB) + tenant isolation tests b. GREEN: Implement Repository, DB Configuration, Migration, external integrations c. REFACTOR: Clean up d. Run tests → All tests PASS including isolation tests
  5. Report: List created files, test results, any specification ambiguities

Read the full file on GitHub · 75 lines

Changes

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.

  1. 4d ago First seen · 75 lines · 121 tokens per session scan A 2e6417717b7f

Subscribe to this mod's changes

bc-developer is an agent published in the GitHub repository jed1978/ddd-architecture-coach (5 stars, last pushed 4mo ago), licensed MIT. It adds 121 tokens to every session and 1,109 once invoked, about $0.0006 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 2026-08-31.

Related

Other agents, from other repositories

code-review-agent

You are a repository-installed code review agent for a codebase that follows Hexagonal Architecture and Domain-Driven Design.

bardiakhosravi/tenets · 0 tokens

domain-expert

Domain expert who reads the system from the outside in — by what it produces, what it gets right, and where it gets things wrong. Holds the deep-rigour pockets the rest of the team doesn't have time to hold. Use during big-picture storms, regulatory or correctness review, and any work where domain truth matters more…

DarrenLyons/agentic-ddd · 73 tokens

architect

System architect with Domain-Driven Design expertise. Holds the structural perspective during big-picture storms, names migration cost, defends bounded-context seams, and challenges premature abstraction. Use during design proposals, schema and API review, and event storms.

DarrenLyons/agentic-ddd · 49 tokens

product-owner

Product Owner with Domain-Driven Design expertise. Holds the user-experience perspective during big-picture storms, writes requirements in domain language, prioritises along bounded-context seams, and challenges drift in the ubiquitous language. Use during planning, spec review, issue writing, and event storms.

DarrenLyons/agentic-ddd · 58 tokens

architect-review

Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.

viksant/vibe-coding-tools-content · 48 tokens

test-architect

Rules & governance catalog for AI/LLM-assisted engineering — architecture, security, and change discipline as machine-readable rules.

bogdaniel/aegis-codex · 0 tokens