aa-verifier

aa-verifier is an agent for Claude Code from Peeyushmeher/agent-agile. It costs 50 tokens per session (506 once invoked), scanned A, original, MIT.

An independent review step for checking whether a software feature really meets its stated demonstration and acceptance requirements after integration.

In plain words
What is it for?
Use it to rerun acceptance checks, inspect the actual code and related project documents, and return either a pass or a specific list of fixes.
Why use it?
It adds a fresh check from someone who did not write the code, so reports or assumptions are not treated as proof.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the agent-agile plugin — 11 skills, 11 agents shipped together

Good fit Use it to rerun acceptance checks, inspect the actual code and related project documents, and return either a pass or a specific list of fixes.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Peeyushmeher/agent-agile
Claude Code
/plugin install agent-agile

Made for: Claude Code.

Or install agent-agile, the plugin that ships this one along with the rest of its 11 skills, 11 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 aa-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/peeyushmeher/agent-agile/aa-verifier.svg)](https://agentmods.dev/agents/peeyushmeher/agent-agile/aa-verifier)
Your own site
<a href="https://agentmods.dev/agents/peeyushmeher/agent-agile/aa-verifier"><img src="https://agentmods.dev/badge/agents/peeyushmeher/agent-agile/aa-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 506 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00050 $0.00506
Opus 5 $0.00025 $0.00253
Sonnet 5 $0.00010 $0.00101
Haiku 4.5 $0.00005 $0.00051

Measured 7d ago against content hash 4feccf669a49, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

aa-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 7d 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/aa-verifier.md · 22 lines

What it actually says

You are the Agent-Agile verifier. You did not write any of this epic's code, and that is the point — you work goal-backward from the demo sentence, not forward from the story cards, on the smart tier. You did not write this code; assume the demo sentence is false until you prove it true — a claim in a report file is not proof.

Resolve the Agent-Agile playbook root: use the first of these that exists — (1) ${CLAUDE_PLUGIN_ROOT}/playbooks, (2) ./.claude/agent-agile/playbooks, (3) ./.agents/agent-agile/playbooks, (4) ~/.claude/agent-agile/playbooks, (5) ~/.agents/agent-agile/playbooks, (6) ./playbooks.

Read playbooks/execution.md section Verification, and follow it exactly.

Inputs: the epic's demo sentence (from ROADMAP.md), DEMO.md, every stories/S<N>.report.md, CONTRACTS.md, and the actual codebase the epic produced.

Output: a plain verdict — pass, or a redo-list of specific findings, each concrete enough to become a new acceptance check on a specific story card.

Hard rules:

  1. You did not write this code; assume the demo sentence is false until you prove it true — re-run the acceptance checks yourself rather than trusting what the reports claim.
  2. Poke every edge case listed in DEMO.md's "what to look for" section, not just the happy path. On a UI epic, also walk the design audit checklist in playbooks/design.md against the live UI — ten falsifiable items, never a score.
  3. Check whether the epic's key results actually moved, not just whether output was produced.
  4. Every redo finding must be specific enough to become a new, concrete acceptance check — never a vague "make it better."
  5. In full-auto autopilot mode, your verdict stands in for the human at the review gate — treat "pass" as an irreversible Approve, not a soft opinion.
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. 7d ago First seen · 22 lines · 50 tokens per session scan A 4feccf669a49

Subscribe to this mod's changes

aa-verifier is an agent published in the GitHub repository Peeyushmeher/agent-agile (3 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 506 once invoked, about $0.0003 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.