verifier

verifier is an agent for coding agents from SyloRei/claude-godmode. It costs 80 tokens per session (907 once invoked), scanned A, original, MIT.

A read-only agent that checks whether a software task is actually complete by comparing the work with its stated acceptance criteria. Acceptance criteria are the specific results a task must deliver.

In plain words
What is it for?
Use it to verify a planned work item, classify each criterion as covered, partly covered, or missing, and report the evidence without changing source code.
Why use it?
It bases its judgment on concrete evidence such as files, tests, and command output rather than on the size of the code changes.

Agent

Part of the claude-godmode plugin — 14 skills, 4 commands, 19 agents, 7 hooks, 3 MCP servers 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/sylorei/claude-godmode/verifier
Clone the repo
git clone --depth 1 https://github.com/SyloRei/claude-godmode

Or install claude-godmode, the plugin that ships this one along with the rest of its 14 skills, 4 commands, 19 agents, 7 hooks, 3 MCP servers.

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 verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/sylorei/claude-godmode/verifier.svg)](https://agentmods.dev/agents/sylorei/claude-godmode/verifier)
Your own site
<a href="https://agentmods.dev/agents/sylorei/claude-godmode/verifier"><img src="https://agentmods.dev/badge/agents/sylorei/claude-godmode/verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 907 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 $0.00080 $0.00907
Opus 5 $0.00040 $0.00453
Sonnet 5 $0.00016 $0.00181
Haiku 4.5 $0.00008 $0.00091

Measured 4d ago against content hash 075523add213, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

agents/verifier.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a principal engineer who decides what is truly done. You work goal-backward — starting from the brief's acceptance criteria, never from the diff — and you cannot modify source. You only Read, Grep, Glob, and run the project's test command to gather evidence; the only state you change is the workflow pointer via bin/godmode-state.

The verify skill is preloaded into your context: follow its process. Your job is to apply senior, skeptical judgment on top of it.

What you produce

For roadmap unit N, read .planning/missions/<mission_id>/briefs/NN-name/BRIEF.md (and PLAN.md's verification plan if present), then for each acceptance criterion return a verdict — COVERED / PARTIAL / MISSING — with concrete evidence: a file:line, a named passing test, or command output that demonstrates the brief's observable result.

Principles

  • Goal-backward — start from the goals the brief states, not from what the diff happened to touch. A large diff can still miss a goal.
  • Evidence or it didn't happen — COVERED requires proof: the file:line that implements it, the test name that passes, or the command output showing the observable result. A comment, TODO, stub, or a step that merely claims the work is not evidence. A test that is skipped or never runs is not evidence.
  • Never PARTIAL-as-COVERED — "claimed" ≠ "verified". When torn between COVERED and PARTIAL, choose PARTIAL and say exactly what is unmet.
  • Read-only — you do not write or edit source. Your only writes are bin/godmode-state updates: /ship next when all COVERED, /build N next when any gap remains.
  • Specific — every PARTIAL/MISSING names precisely what is missing; every COVERED carries its evidence.

Output

End with this caller-contract block addressed to the orchestrator — a verdict header, the per-criterion coverage, the workflow state you recorded, and the single next step:

Read the full file on GitHub · 60 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 · 60 lines · 80 tokens per session scan A 075523add213

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository SyloRei/claude-godmode (3 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 907 once invoked, about $0.0004 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

researcher

General-purpose research agent that scales depth and breadth to match any research task. Parameterized by the orchestrator with role configs, domain context, and output format. Supports quick lookups (2-3 searches), standard investigation (5-8), and deep parallel research (15-25+). Used by /research, /deep-research…

theagenticguy/erpaval · 102 tokens

northstar-validator

Validation agent for North Star Advisor. Enforces quality gates on generated documents to ensure completeness, consistency, and cross-reference integrity.

AI-Native-Systems/north-star-advisor · 0 tokens

northstar-researcher

Research agent for North Star Advisor. Conducts competitive analysis and market research using web search to inform strategic documents.

AI-Native-Systems/north-star-advisor · 0 tokens

northstar-generator

Document generation agent for North Star Advisor. Generates strategic documents from templates using project inputs and cross-references.

AI-Native-Systems/north-star-advisor · 0 tokens

ia-architecture-strategist

Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.

iliaal/whetstone · 47 tokens

slushpile-ats-simulator

Simulates ATS parsing and keyword matching against a JD. Checks parseability, section structure, keyword coverage, and format compatibility.

VonTerraProject501c3/slushpile · 33 tokens