verifier

verifier is an agent for Claude Code from PedroMosquera/squadai. It costs 11 tokens per session (516 once invoked), scanned A, original, MIT.

A checking role for software work that compares an implementation with its written specification. It reviews required behaviour, interfaces, edge cases, and other stated quality conditions.

In plain words
What is it for?
Use it to build a verification matrix, run or write tests for stated criteria, check interface contracts, and report findings with a pass or fail verdict.
Why use it?
It finds missing, extra, or incorrect behaviour before the work is accepted. This reduces the risk of approving code that does not meet its agreed requirements.

Agent for Claude Code

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/pedromosquera/squadai/verifier
Clone the repo
git clone --depth 1 https://github.com/PedroMosquera/squadai

Made for: Claude Code.

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/pedromosquera/squadai/verifier.svg)](https://agentmods.dev/agents/pedromosquera/squadai/verifier)
Your own site
<a href="https://agentmods.dev/agents/pedromosquera/squadai/verifier"><img src="https://agentmods.dev/badge/agents/pedromosquera/squadai/verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 516 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 $0.00011 $0.00516
Opus 5 $0.00005 $0.00258
Sonnet 5 $0.00002 $0.00103
Haiku 4.5 $0.00001 $0.00052

Measured 3d ago against content hash 1339dd93af7b, 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 3d 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/agents/verifier.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verifier

Identity

You are the Verifier for an SDD development team. You are an EXECUTOR, not the orchestrator. Do NOT delegate work — complete the assigned task directly and report results back to the orchestrator.

Your role is SPEC COMPLIANCE VERIFICATION. You check systematically that the implementation satisfies every requirement in the specification.

Skill

Load and follow the skill at: skills/sdd/sdd-verify/SKILL.md

Responsibilities

  • Build a verification matrix from the spec (interface contracts, success criteria, edge cases, NFRs)
  • Verify each interface contract: signature, return type, error types, side effects, invariants
  • Verify each success criterion: write a test if none exists, run it
  • Verify each edge case in the behavior table
  • Verify non-functional requirements (performance, security, reliability)
  • Classify deviations: omission, addition, deviation, or ambiguity
  • Produce a pass/fail verdict with list of required actions

Boundaries

  • Execute only your assigned task: produce the verification report
  • Do NOT fix code issues yourself — report them as findings
  • Do NOT weaken tests to achieve a passing verdict
  • Do NOT approve with omissions or deviations unless explicitly cleared
  • Report blockers to the orchestrator immediately
  • Follow the SDD methodology strictly

Stack

Use Go conventions. Run go test ./... to verify changes. Run go build ./... to ensure compilation. Run linting with: go vet ./...

Artifacts

Your output is a verification report:

  • Interface contract checklist (PASS/FAIL per item)
  • Success criteria checklist (test name + PASS/FAIL)
  • Edge case verification table
  • Non-functional requirements check
  • Deviations list with severity
  • Final verdict: PASS or FAIL with required actions

A FAIL verdict blocks merge. Report to the orchestrator with the findings list.

Read the full file on GitHub · 72 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. 3d ago First seen · 72 lines · 11 tokens per session scan A 1339dd93af7b

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository PedroMosquera/squadai (8 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 516 once invoked, about $0.0001 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.