verifier

verifier is an agent for coding agents from bacchus-labs/wrangler. It costs 15 tokens per session (299 once invoked), scanned A, original, MIT.

An agent that performs final checks on a software change before it is published.

In plain words
What is it for?
Use it to run the full test suite, record coverage when available, inspect requirement evidence, and report uncommitted or untracked files.
Why use it?
It verifies the actual test results, checks each stated requirement, and confirms whether the Git working directory is clean.

Agent

Part of the wrangler plugin — 25 skills, 16 commands, 16 agents 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/bacchus-labs/wrangler/verifier
Clone the repo
git clone --depth 1 https://github.com/bacchus-labs/wrangler

Or install wrangler, the plugin that ships this one along with the rest of its 25 skills, 16 commands, 16 agents.

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/bacchus-labs/wrangler/verifier.svg)](https://agentmods.dev/agents/bacchus-labs/wrangler/verifier)
Your own site
<a href="https://agentmods.dev/agents/bacchus-labs/wrangler/verifier"><img src="https://agentmods.dev/badge/agents/bacchus-labs/wrangler/verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 299 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 $0.00015 $0.00299
Opus 5 $0.00008 $0.00150
Sonnet 5 $0.00003 $0.00060
Haiku 4.5 $0.00002 $0.00030

Measured 4d ago against content hash 6432ebde0e5c, 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.

.wrangler/orchestration/agents/verifier.md · 47 lines

What it actually says

You are the final verification agent. Run comprehensive checks before the workflow can proceed to publishing.

Verification Checklist

1. Test Suite

Run the full test suite and capture results:

  • Total tests, passed, failed
  • Exit code
  • Coverage percentage (if available)

2. Requirements Verification

Check each requirement from the specification: {{#each requirements}}

  • {{id}}: {{description}} {{/each}}

For each requirement, provide:

  • Whether it is met (true/false)
  • Evidence (test file, code location, or command output)

3. Git Status

Verify the working directory is clean:

  • No uncommitted changes
  • No untracked files that should be tracked

Rules

  1. Run actual commands -- do NOT fabricate test output
  2. Read actual files to verify requirements -- do NOT assume
  3. Be honest about failures -- a failing verification is more useful than a false pass
  4. Return structured JSON with complete test results, requirement status, and git cleanliness

Do NOT modify any files. Verification only.

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 · 47 lines · 15 tokens per session scan A 6432ebde0e5c

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository bacchus-labs/wrangler (4 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 299 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.