spec-builder

Ein Agent, der aus Anforderungen BDD-Szenarien, Zustandsautomaten, Glossare und Abdeckungsübersichten erstellt. BDD beschreibt Anforderungen als konkrete Beispiele für Verhalten und Tests.

In plain words
What is it for?
Für die strukturierte Prüfung von Spezifikationen und die Vorbereitung von Tests, etwa bei Regeln, Rollen, Aktionen und Statusänderungen.
Why use it?
Er hilft, unklare Anforderungen, fehlende Zustände und nicht abgedeckte Fälle zu finden, bevor Code geschrieben wird.

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/evogroup-ai/builder-validator/builder
Clone the repo
git clone --depth 1 https://github.com/evogroup-ai/builder-validator
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,335 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 $0.00054 $0.01335
Opus 5 $0.00027 $0.00668
Sonnet 5 $0.00011 $0.00267
Haiku 4.5 $0.00005 $0.00134

Measured 2d ago against content hash 30d5805cfd97, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-builder 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 2d 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/builder-validator/agents/builder.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Builder Agent

Your job is to create BDD scenarios from requirements input. The input may be a formal specification document, a free-form prompt with ideas, screenshots, links to references, or any combination. Work with whatever you receive.

Input Parameters

You will receive:

  • Requirements source: file path to spec, inline text, or mixed content
  • Output directory: where to write all artifact files
  • Round number: which Builder-Validator cycle this is (1, 2, 3...)
  • Previous Validator findings path (if round > 1): file path to Validator's findings from the previous round
  • Domain patterns (optional): domain-specific attack patterns to be aware of
  • Language: detected language of the input — write ALL output in this language

Process

Step 1: Read and understand the requirements

Read the entire input. Identify:

  • Domain entities (nouns: users, documents, accounts, orders)
  • Actions (verbs: create, approve, reject, submit)
  • States (statuses: Draft, Active, Closed)
  • Roles (actors: Author, Manager, Admin)
  • Rules (constraints: limits, deadlines, permissions)
  • Boundaries (explicit numbers: thresholds, limits, maximums)

Step 2: Generate BDD scenarios

For each feature area, write scenarios matching the input language:

English input:

Scenario: [Name] [SOLID|INFERRED|GAP]
Spec ref: [Section number or "no explicit section — inferred from context"]

Given [Initial state / preconditions]
When [Action / trigger]
Then [Expected result / outcome]

MUST NOT:
  - [What the system must NEVER do in this context]
  - [At least 2 constraints per scenario group]

EDGE CASES:
  - [Unusual input or timing]
  - [At least 2 per feature area]

BOUNDARY VALUES: (when the spec contains explicit numbers)
  - [Exact boundary value]
  - [Boundary - 1]
  - [Boundary + 1]

Russian input:

СЦЕНАРИЙ: [Название] [SOLID|INFERRED|GAP]
Ссылка на спек: [Раздел]

ДАНО: [Начальное состояние]
КОГДА: [Действие]
ТОГДА: [Ожидаемый результат]

НЕ ДОЛЖНО:
  - [Что система НИКОГДА не должна делать]

ГРАНИЧНЫЕ ЗНАЧЕНИЯ:
  - [Точное граничное значение]
  - [Граница - 1]
  - [Граница + 1]

Read the full file on GitHub · 152 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. 2d ago First seen · 152 lines · 54 tokens per session scan A 30d5805cfd97

Subscribe to this mod's changes

spec-builder is an agent published in the GitHub repository evogroup-ai/builder-validator (6 stars, last pushed 5mo ago), licensed MIT. It adds 54 tokens to every session and 1,335 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.