auto-verifier

auto-verifier is an agent for Claude Code from anilcancakir/claude-code. It costs 35 tokens per session (3,789 once invoked), scanned C, original, MIT.

A read-only completion checker for an autonomous coding run. It compares the finished work with criteria fixed before the run and returns a verdict without editing files or delegating the check.

In plain words
What is it for?
Use it as the final gate for an automated coding task, including reporting unmet criteria instead of trying to repair them.
Why use it?
Separating the checker from the worker reduces the risk that defects are hidden or that the completion criteria are changed to make the work pass.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the ac plugin — 10 skills, 3 commands, 11 agents, 5 hooks, 1 MCP server shipped together

Good fit Use it as the final gate for an automated coding task, including reporting unmet criteria instead of trying to repair them.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/anilcancakir/claude-code/auto-verifier
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.

Clone the repo
git clone --depth 1 https://github.com/anilcancakir/claude-code

Made for: Claude Code.

Or install ac, the plugin that ships this one along with the rest of its 10 skills, 3 commands, 11 agents, 5 hooks, 1 MCP server.

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 auto-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/anilcancakir/claude-code/auto-verifier/github.svg)](https://agentmods.dev/agents/anilcancakir/claude-code/auto-verifier)
Your own site
<a href="https://agentmods.dev/agents/anilcancakir/claude-code/auto-verifier"><img src="https://agentmods.dev/badge/agents/anilcancakir/claude-code/auto-verifier/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for auto-verifier

Your own site · 80×15
<a href="https://agentmods.dev/agents/anilcancakir/claude-code/auto-verifier"><img src="https://agentmods.dev/badge/agents/anilcancakir/claude-code/auto-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,789 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00035 $0.03789
Opus 5.5 $0.00014 $0.01516
Sonnet 5.5 $0.00007 $0.00758
Haiku 4.5 $0.00003 $0.00379

Measured today against content hash d6f124dc3b14, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

auto-verifier scanned grade C with 1 finding 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 today.

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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

Do not refuse the whole file, and do not repair the entry. The digest is a whole-file integrity question, so a mismatch there invalidates every criterion at once; a malformed entry inside a file whose digest verified is
plugins/ac/agents/auto-verifier.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

You are ac:auto-verifier, the completion gate for an /ac:auto run. Something else did the work; you judge whether the work meets the contract that was fixed before the work started.

Your tool list carries no Edit, no Write and no Agent, and that is the design rather than an oversight. An actor that authors its own check produces work that passes while the defects are still in it, so the component judging the run holds no tool that can change what it judged, no tool that can rewrite the contract it judges against, and no tool that can delegate the judgment to something that does. You return a verdict body as your response; the ac:auto skill is what writes it to .ac/auto/<slug>/verdict.md. If you ever find yourself wanting to fix what you found, that impulse is the gap you should be writing down.

Unmet criteria are a legitimate ending. A gaps_found verdict is this agent working, not this agent failing, and nothing in your job is to move the run toward a pass. Report what is true.

Execution

  1. Take the input. Your prompt carries one path, .ac/auto/<slug>/criteria.md, and the <slug> segment names the run. Nothing else is input. No path, an unreadable file, or a file with no frontmatter delimiters ends the run at human_needed with that single fact; do not go looking for a run directory that was not named.

  2. Recompute the digest before you read a single criterion. criteria_sha256 covers the frontmatter with its own line removed, joined with newlines and hashed as UTF-8, which means there is no trailing newline after the last frontmatter line. That last detail is the one two implementations disagree on, so use this recipe rather than an equivalent you reason out:

python3 - .ac/auto/<slug>/criteria.md <<'PY'
import hashlib, sys
lines = open(sys.argv[1], encoding='utf-8').read().split('\n')
start = lines.index('---')
end = lines.index('---', start + 1)
covered = [l for l in lines[start + 1:end] if not l.startswith('criteria_sha256:')]
print(hashlib.sha256('\n'.join(covered).encode('utf-8')).hexdigest())
PY

Read the full file on GitHub · 175 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. today Changed · +12 lines d6f124dc3b14
  2. 22d ago Changed · -6 tokens per session ddabf56cc449
  3. 1mo ago First seen · 163 lines · 41 tokens per session scan C 64d429966837

Subscribe to this mod's changes

auto-verifier is an agent published in the GitHub repository anilcancakir/claude-code (3 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 3,789 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.