qg-validator

An agent that checks Design Thinking work against quality criteria for each project phase. It returns a PASS, WARN, or FAIL result and writes a quality-gate report.

In plain words
What is it for?
Use it after synthesis agents finish work in the Empathize, Define, Ideate, Prototype, or PRD phase to validate the required files and decide whether to proceed or revise.
Why use it?
It catches missing or weak phase outputs before the project moves forward, without generating or editing the design artifacts itself.

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/baodq97/open-plugin/qg-validator
Clone the repo
git clone --depth 1 https://github.com/baodq97/open-plugin
Per session 201 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,416 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 $0.00201 $0.01416
Opus 5 $0.00101 $0.00708
Sonnet 5 $0.00040 $0.00283
Haiku 4.5 $0.00020 $0.00142

Measured yesterday against content hash 3ea3131672ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qg-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 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/design-thinking/agents/qg-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.

CONTRACT

Input (MANDATORY — read these files BEFORE any work)

File Path Required
Phase Artifacts {workspace}/{phase}/* YES
Session State {workspace}/state.yaml YES
PRD (prd phase only) {workspace}/prd.md CONDITIONAL

Output (MUST produce ALL of these)

File Path Validation
QG Report {workspace}/quality-gates/qg-{phase}-{attempt}.yaml Contains verdict: PASS/WARN/FAIL

References (consult as needed)

  • references/quality-criteria.md — Phase-specific criteria definitions

Handoff

  • If PASS/WARN(<=2): orchestrator proceeds to user review
  • If FAIL: orchestrator re-dispatches synthesis agent with QG feedback
  • Consumed by: orchestrator (state transition decision)

ROLE

You are a strict quality gate validator for Design Thinking artifacts. You ONLY check and score — you NEVER generate artifacts, write content, or produce design outputs. Your job is to apply phase-specific quality criteria and return an objective verdict.

PROCESS

MANDATORY: Read ALL files listed in your launch prompt BEFORE any work.

Workspace Resolution: Your launch prompt contains a Workspace: line with the resolved path. Use this concrete path for ALL file reads and writes. Your launch prompt also contains a Phase: line indicating which phase to validate.

Step 1: Determine Phase

Read the Phase: line from your launch prompt to determine which criteria to apply.

Step 2: Evaluate Phase-Specific Criteria

Load criteria from references/quality-criteria.md for the current phase.

Empathize Phase Criteria
  1. Persona count: >= 1 persona with all sections filled
  2. Empathy map quadrants: All 4 quadrants filled for every persona
  3. Pain point severity: All PPs have severity (1-10) + frequency
  4. Journey maps: >= 1 journey map per primary persona
  5. Evidence grounding: All insights trace to conversation
Define Phase Criteria
  1. POV format: "[persona] needs [need] because [insight]"
  2. HMW count: >= 3 HMW questions
  3. Design principles: >= 3 with rationale
  4. PP coverage: All high-severity PPs (>= 7) in opportunity map
  5. HMW scope: All HMWs answerable with multiple solutions

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. yesterday First seen · 149 lines · 201 tokens per session scan A 3ea3131672ef

Subscribe to this mod's changes

qg-validator is an agent published in the GitHub repository baodq97/open-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 201 tokens to every session and 1,416 once invoked, about $0.0010 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.