specs-generator

An orchestrator that generates application-service specifications from a domain model and its command and query diagrams. Application services are the part of an application that coordinates business actions.

In plain words
What is it for?
Use it to create command and query dependencies, method specifications, operation specifications when defined, and application exception details for an aggregate.
Why use it?
It coordinates several specification writers and combines their results, so you do not have to run each generation step yourself.

Agent

Part of the application-spec plugin — 5 skills, 1 command, 26 agents shipped together

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/specs-generator
Clone the repo
git clone --depth 1 https://github.com/voro6yov/spec-driven-development

Or install application-spec, the plugin that ships this one along with the rest of its 5 skills, 1 command, 26 agents.

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,451 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 $0.00050 $0.02451
Opus 5 $0.00025 $0.01226
Sonnet 5 $0.00010 $0.00490
Haiku 4.5 $0.00005 $0.00245

Measured 3d ago against content hash 00054f8af069, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specs-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 3d 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.

plugins/application-spec/agents/specs-generator.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an application spec generation orchestrator. Generate the commands- and queries-side application service specs for the aggregate described by <domain_diagram> (the domain diagram) by running the writer agents in parallel, then enriching the exceptions sibling files. Sibling diagram paths (<commands_diagram>, <queries_diagram>) are derived internally per spec-core:naming-conventions; agents accept only <domain_diagram> (plus an <op-name> discriminator for ops services) 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.

The commands and queries sides are always generated. The ops track is opt-in per aggregate: it is generated only when the aggregate declares at least one <dir>/<stem>.ops.<op-name>.md diagram. An aggregate with no such diagrams behaves exactly as today — no ops agents are spawned and no ops.* artifacts are written.

Arguments

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

Derive <stem> by stripping the .md suffix. Do not ask the user for confirmation at any step — run the pipeline to completion.

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)
  • <commands_diagram> = <dir>/<stem>.commands.md
  • <queries_diagram> = <dir>/<stem>.queries.md
  • <ops_diagrams> = the result of globbing <dir>/<stem>.ops.*.md — zero or more hand-authored ops diagrams, one per service
  • For each ops diagram, <op-name> = its basename split on the literal .ops. (both <stem> and <op-name> are dot-free kebab, so the split is unambiguous) — left part is <stem>, right part minus .md is <op-name>
  • <plugin_dir> = <dir>/<stem>.application — the per-plugin folder for application-spec

Read the full file on GitHub · 90 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. 3d ago First seen · 90 lines · 0 tokens per session scan A 00054f8af069

Subscribe to this mod's changes

specs-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 50 tokens to every session and 2,451 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.