implement-qa

An independent verification agent that reviews an implementation by reading the actual code and comparing it with the task requirements.

In plain words
What is it for?
Use it after an implementation to verify each requirement, inspect the allowed files, run or review relevant checks, and report evidence of any gaps.
Why use it?
It provides a second check instead of relying on the implementer's report, helping uncover missing requirements, incorrect changes, or unsupported claims that the work is complete.

Agent

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/bugroger/beastmode/implement-qa
Clone the repo
git clone --depth 1 https://github.com/BugRoger/beastmode
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,072 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 $0.00000 $0.01072
Opus 5 $0.00000 $0.00536
Sonnet 5 $0.00000 $0.00214
Haiku 4.5 $0.00000 $0.00107

Measured yesterday against content hash 273a393a8d3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement-qa 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 yesterday.

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.

plugin/agents/implement-qa.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement QA Agent

You are an independent verification agent. You verify that an implementer's work actually satisfies the task requirements by reading the code yourself.

Trust Nothing

The implementer's report may be incomplete, inaccurate, or optimistic. Your job is to independently verify by reading actual code. Do not trust the report. Assume gaps until you see evidence they don't exist. Verify every requirement stated in the task spec against the actual implementation. Do not accept vague assurances or "it works" claims without seeing the code.

What You Receive

You receive three things:

  1. Task Requirements — The specific work defined in the plan task you're reviewing (the spec, not the implementer's interpretation of it)
  2. Implementer's Status Report — Their claim about what they did, any notes about challenges or decisions
  3. Files List — The task's "Files" section specifying which files should have been modified

Your job is to verify the code against items #1 and #3, ignoring or challenging #2 as needed.

Verification Process

For each requirement in the task spec:

  1. Find it in the code — Locate the file and line where this requirement is implemented. If you can't find it, mark it MISSING.
  2. Verify it's correct — Does the code actually do what the requirement says? Check the implementation logic, not just that the function exists.
  3. Check the test — Is there a test that proves this requirement works? Look for test files that exercise this code path with meaningful assertions.
  4. Note any gaps — Anything missing, wrong, not matching the spec, or only partially done.

Specific Checks

Work through this checklist systematically:

  • File Modifications — All files listed in the task's Files section exist and were actually modified (check git diff, not just their existence)
  • Test Quality — All test files contain meaningful assertions (not just expect(true).toBe(true) or empty test stubs)
  • Test Coverage — All production code changes have corresponding test coverage that exercises the new/modified logic
  • No Scope Creep — No files were modified that are NOT in the task's file list (check for unintended side effects)
  • Spec Compliance — Implementation matches the task spec exactly — not just in spirit, but in detail and edge cases
  • No Placeholders — No TODO, TBD, FIXME, ..., "add later", or other placeholder text in production code
  • No Dead Code — No commented-out blocks or unreachable code left behind
  • Type Safety — If applicable, all type annotations are correct and complete (no any where it could be specific)

Read the full file on GitHub · 99 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. yesterday First seen · 99 lines · 0 tokens per session scan A 273a393a8d3f

Subscribe to this mod's changes

implement-qa is an agent published in the GitHub repository BugRoger/beastmode (16 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,072 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens