gsd-verifier

gsd-verifier is a skill for Claude Code, Codex from allgpt-co/QuickVoice. It costs 30 tokens per session (5,095 once invoked), scanned A, original, MIT.

A code-review helper that checks whether a project phase achieved its intended result, rather than only completing its listed tasks.

In plain words
What is it for?
Use it after a phase to verify that the promised behavior exists, is connected, and works as intended.
Why use it?
A task can be marked complete while the delivered feature is still a placeholder or disconnected. This checks the actual outcome in the codebase.

Skill for Claude CodeCodex

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 skills/allgpt-co/quickvoice/verifier
Any agent
npx skills add allgpt-co/QuickVoice --skill verifier
Clone the repo
git clone --depth 1 https://github.com/allgpt-co/QuickVoice

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for gsd-verifier

README.md
[![agentmods](https://agentmods.dev/badge/skills/allgpt-co/quickvoice/verifier.svg)](https://agentmods.dev/skills/allgpt-co/quickvoice/verifier)
Your own site
<a href="https://agentmods.dev/skills/allgpt-co/quickvoice/verifier"><img src="https://agentmods.dev/badge/skills/allgpt-co/quickvoice/verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,095 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 $0.00030 $0.05095
Opus 5 $0.00015 $0.02547
Sonnet 5 $0.00006 $0.01019
Haiku 4.5 $0.00003 $0.00509

Measured 4d ago against content hash 30253008be36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gsd-verifier 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 4d 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.

.claude/skills/gsd/agents/verifier/SKILL.md · 664 lines

How it starts

The opening of the file, as written. The whole thing — 664 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GSD Verifier

Verifies that a phase achieved its GOAL, not just completed its TASKS.

When to Use

Use this agent when:

  • A phase has been executed and needs verification
  • You need to confirm the phase goal was actually achieved
  • You are spawned by /gsd:verify-work command
  • You need to check that codebase delivers what was promised, not just that tasks were marked complete

Core Philosophy

Task Completion ≠ Goal Achievement

A task "create chat component" can be marked complete when the component is a placeholder. The task was done — a file was created — but the goal "working chat interface" was not achieved.

Goal-backward verification starts from outcome and works backwards:

  1. What must be TRUE for the goal to be achieved?
  2. What must EXIST for those truths to hold?
  3. What must be WIRED for those artifacts to function?

Then verify each level against actual codebase.

Verification Process

Step 0: Check for Previous Verification

Before starting fresh, check if a previous VERIFICATION.md exists:

cat "$PHASE_DIR"/*-VERIFICATION.md 2>/dev/null

If previous verification exists with gaps: section → RE-VERIFICATION MODE:

  1. Parse previous VERIFICATION.md frontmatter
  2. Extract must_haves (truths, artifacts, key_links)
  3. Extract gaps (items that failed)
  4. Set is_re_verification = true
  5. Skip to Step 3 (verify truths) with this optimization:
    • Failed items: Full 3-level verification (exists, substantive, wired)
    • Passed items: Quick regression check (existence + basic sanity only)

If no previous verification OR no gaps: section → INITIAL MODE:

Set is_re_verification = false, proceed with Step 1.

Step 1: Load Context (Initial Mode Only)

Gather all verification context from phase directory and project state:

# Phase directory (provided in prompt)
ls "$PHASE_DIR"/*-PLAN.md 2>/dev/null
ls "$PHASE_DIR"/*-SUMMARY.md 2>/dev/null

# Phase goal from roadmap
grep -A5 "Phase ${PHASE}:" .planning/ROADMAP.md

# Requirements mapped to this phase
grep -E "^| ${PHASE}" .planning/REQUIREMENTS.md 2>/dev/null

Read the full file on GitHub · 664 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. 4d ago First seen · 664 lines · 30 tokens per session scan A 30253008be36

Subscribe to this mod's changes

gsd-verifier is a skill published in the GitHub repository allgpt-co/QuickVoice (491 stars, last pushed 23d ago), licensed MIT. It adds 30 tokens to every session and 5,095 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

gsd-verifier

Verifies phase goal achievement through goal-backward analysis. Checks codebase delivers what phase promised, not just that tasks completed.

ctsstc/get-shit-done-skills · 30 tokens

Verification & Quality Assurance

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.

amangit1314/repo-rag · 36 tokens

Verification & Quality Assurance

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.

aegntic/cldcde · 36 tokens

lumina-frontend-ui

Build, refine, and debug the React/Vite frontend for Lumina. Use when editing files under client/src or client/package.json, changing chat UX, landing page content, auth flows, routing, theme behavior, markdown rendering, animations, responsive layout, or frontend API wiring.

hoangsonww/AI-RAG-Assistant-Chatbot · 62 tokens

lumina-agentic-mcp

Work on the Python multi-agent pipeline and MCP client in agenticai. Use when editing files under agenticai/, changing agent orchestration, configuration loading, MCP client connectivity, async execution flow, pipeline startup commands, or cloud deployment wrappers for the Python service.

hoangsonww/AI-RAG-Assistant-Chatbot · 60 tokens

lumina-backend-api

Implement and debug the Express and TypeScript backend for Lumina. Use when editing files under server/src or server/package.json, changing authentication, conversations, guest flows, chat routes, models, middleware, API contracts, or Gemini and Pinecone service wiring outside the dedicated knowledge-ingestion…

hoangsonww/AI-RAG-Assistant-Chatbot · 64 tokens