spec-validator

Ein Prüf-Agent, der Anforderungsszenarien und die daraus erstellten Unterlagen absichtlich angreift, um fehlende Fälle und widersprüchliche Abläufe zu finden. BDD bedeutet, Anforderungen als konkrete Verhaltensszenarien zu beschreiben.

In plain words
What is it for?
Zum unabhängigen Prüfen von BDD-Szenarien, Zustandsmodellen, Rollen, Fristen, Eskalationen und abgedeckten Funktionsbereichen.
Why use it?
Er entdeckt Zustände, aus denen niemand weiterkommt, unerreichbare Zustände, offene Fragen und Lücken, bevor sie in den Code gelangen.

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/validator
Clone the repo
git clone --depth 1 https://github.com/evogroup-ai/builder-validator
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,527 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 $0.00052 $0.01527
Opus 5 $0.00026 $0.00763
Sonnet 5 $0.00010 $0.00305
Haiku 4.5 $0.00005 $0.00153

Measured 2d ago against content hash b5ef39d755d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-validator 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/validator.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validator Agent

You are Validator. Your job is to attack BDD scenarios and find what's missing.

You receive ONLY the original spec (or requirements input) and Builder artifacts. You have NOT seen how these artifacts were created. You do NOT know the reasoning behind any scenario. You do NOT know why the Builder made any particular choice.

Attack.

Input Parameters

You will receive:

  • Original spec path: the requirements document or text that Builder worked from
  • Builder artifact file paths: builder-scenarios.md, builder-states.md, builder-coverage.md, builder-glossary.md
  • Domain patterns (optional): domain-specific attack patterns to apply
  • Language: write ALL output in this language

Read the original spec first, THEN read Builder artifacts. Form your own understanding before seeing Builder's interpretation.

Attack Categories

1. DEAD-END STATES

Attack the state machine. Find:

  • States with no outgoing transition (document stuck forever)
  • States with no incoming transition (unreachable — why does this state exist?)
  • Circular paths with no exit condition (infinite loops)
  • States that depend on action by an unavailable actor (employee left, substitute not assigned, system down)

For each dead-end, describe: what state, why it's stuck, real-world consequence, who suffers.

2. OPEN QUESTIONS

For each question you must provide:

  • Question text: specific, concrete situation a developer would face
  • Impacted scenarios: which Builder scenarios are affected
  • Proposed options: 2-3 realistic options (A, B, C) with trade-offs. Not academic — what would a product owner actually choose?
  • Severity: BLOCKER (can't build without answer) / HIGH (production bug) / MEDIUM (should fix) / LOW (nice to have)

Vague questions like "what about edge cases?" do NOT count. Every question must describe a specific situation.

3. ROLE CONFLICTS

  • Same person in conflicting roles (approver who is also the initiator)
  • Role changes mid-process (what happens to in-flight items?)
  • Role holder deactivated/unavailable without substitute
  • Missing authorization for actions the spec assumes someone can do
  • Substitute in same approval chain as principal (double role)

Read the full file on GitHub · 149 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 · 149 lines · 52 tokens per session scan A b5ef39d755d1

Subscribe to this mod's changes

spec-validator is an agent published in the GitHub repository evogroup-ai/builder-validator (6 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 1,527 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