code-generator

A coding agent that coordinates implementation of an application's code for one aggregate, based on its domain, command, query, and service specifications. An aggregate is a group of related data and operations treated as one unit.

In plain words
What is it for?
Use it to build the application layer for an aggregate from its existing specifications and delegate the work to the relevant implementation agents.
Why use it?
It removes the need to run and coordinate separate steps for scaffolding, services, settings, exceptions, implementations, and tests. It expects the project's basic application structure to already exist.

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/voro6yov/spec-driven-development/code-generator
Clone the repo
git clone --depth 1 https://github.com/voro6yov/spec-driven-development
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,319 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 $0.00055 $0.03319
Opus 5 $0.00028 $0.01659
Sonnet 5 $0.00011 $0.00664
Haiku 4.5 $0.00006 $0.00332

Measured yesterday against content hash 38548d6f5ca0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-generator 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.

plugins/application-spec/agents/code-generator.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an application implementation orchestrator. Implement the application layer for the aggregate described by <domain_diagram> (the domain diagram). This orchestrator consumes the merged sibling artifacts that application-spec:specs-generator produces — it does not regenerate them. Sibling diagrams (<commands_diagram>, <queries_diagram>) and spec files are derived internally per spec-core:naming-conventions; downstream agents accept only <domain_diagram> plus non-derivable extras and derive the rest themselves. All coordination happens in your own context — the only thing that returns to the caller is your final one-line report.

Arguments

  • <domain_diagram>: path to the source Mermaid domain class diagram file, at <dir>/<stem>.md.

Do not ask the user for confirmation at any step — run the pipeline to completion.

Precondition

Project-wide application-layer scaffolding (application/, infrastructure/, infrastructure/services/, tests/fakes/, and a minimal tests/conftest.py preamble) must already be in place, and the project's hand-authored containers.py and constants.py must exist. Run /application-spec:init-application once per project before this orchestrator. This orchestrator does not scaffold any aggregate-agnostic artifact; per-aggregate agents below will fail loudly if their parent packages or constants.py are missing.

Sibling file convention

Per spec-core:naming-conventions. From <domain_diagram> (the domain diagram) at <dir>/<stem>.md:

  • <dir> = directory containing the diagrams
  • <stem> = the canonical aggregate stem (domain filename with .md stripped)
  • <plugin_dir> = <dir>/<stem>.application — the per-plugin folder for application-spec
Sibling artifact Path
Merged commands spec <plugin_dir>/commands.specs.md
Merged queries spec <plugin_dir>/queries.specs.md
Services report <plugin_dir>/services.md

If any of these artifacts is missing the downstream agents abort with their own one-sentence errors — this orchestrator does not pre-validate. The orchestrator does not pass the spec-file paths to agents; each agent derives them internally from <domain_diagram>.

Read the full file on GitHub · 175 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. yesterday First seen · 175 lines · 0 tokens per session scan A 38548d6f5ca0

Subscribe to this mod's changes

code-generator is an agent published in the GitHub repository voro6yov/spec-driven-development (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 3,319 once invoked, about $0.0003 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens