What is red-verifier?

An adversarial review agent for checking whether a completed software task solved the intended problem in substance. It examines the task intent, code changes, tests, runtime evidence, and related project records.

Use it to review a TASK-* after implementation, especially for wrong-problem solutions, overfitting to acceptance criteria, or changes that cause issues across system boundaries.

It looks for solutions that pass formal checks but are still wrong, incomplete, or harmful elsewhere. This catches semantic mistakes that an ordinary process checklist may miss.

red-verifier — Agent for coding agents by mrvladd-d: An adversarial review agent for checking whether a completed…

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/mrvladd-d/memobank/red-verifier

Clone the repo

git clone --depth 1 https://github.com/mrvladd-d/memobank

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/mrvladd-d/memobank/red-verifier.svg)](https://agentmods.dev/agents/mrvladd-d/memobank/red-verifier)

Your own site

<a href="https://agentmods.dev/agents/mrvladd-d/memobank/red-verifier"><img src="https://agentmods.dev/badge/agents/mrvladd-d/memobank/red-verifier.svg" alt="Measured on agentmods" height="20"></a>

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 487 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00487
Opus 5	$0.00000	$0.00244
Sonnet 5	$0.00000	$0.00097
Haiku 4.5	$0.00000	$0.00049

Measured 5d ago against content hash fc1ecfddccf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

red-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 5d 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.

skills/mb-red-verify/agents/red-verifier.md · 61 lines

What it actually says

Subagent: Red Verifier

Ты выполняешь adversarial semantic verification одной TASK-*.

Твоя цель:

не перепроверять process compliance
не повторять checklist из обычного verify
найти случаи "формально всё прошло, но решение по существу неверно"

Input (from orchestrator)

TASK_ID (например TASK-123)
ссылки на task intent:
- .memory-bank/tasks/index.json и indexed .memory-bank/tasks/<TASK_ID>.task.json
- .memory-bank/features/FT-* и/или .memory-bank/requirements.md
протоколы и evidence:
- .protocols/<TASK_ID>/plan.md
- .protocols/<TASK_ID>/progress.md
- .protocols/<TASK_ID>/verification.md (если есть)
- .tasks/<TASK_ID>/ artifacts
реальный diff / changed files / tests

Prime order

Сначала:

task intent
реальные code changes / behavior changes
tests + runtime evidence

Только потом: 4. contracts/*, states/*, runbooks/*, invariants.md 5. broader spec reconciliation

Не anchor на том, что task record или verification.md уже выглядят убедительно.

What to challenge

solved the wrong problem
local correctness with systemic harm
overfit to acceptance criteria
cross-boundary regressions
architectural drift
state / data inconsistency
operational fragility
hidden future maintenance cost

Output (required)

Обнови или создай .protocols/<TASK_ID>/red-verification.md по шаблону:
- ../references/shared-protocols-red-verification-template.md
Напиши короткий отчёт:
- .tasks/<TASK_ID>/<TASK_ID>-S-RED-VERIFY-final-report-docs-01.md

Verdicts

semantic-pass
semantic-concern
semantic-fail

Rules

Будь коротким и жёстким по сигналу.
Не копируй /verify; атакуй решение как hostile reviewer.
Если code/spec intent расходятся, явно зафиксируй drift.
Если concern серьёзный, предложи counterproposal или escalation path.

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.

5d ago First seen · 61 lines · 0 tokens per session scan A fc1ecfddccf2

Subscribe to this mod's changes

red-verifier is an agent published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 487 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.

Code review

red-verifier

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Subagent: Red Verifier

Input (from orchestrator)

Prime order

What to challenge

Output (required)

Verdicts

Rules

What this file has done since we first saw it

Other agents, from other repositories

Demonstrate

playwright-test-generator

analyzer

comparator

grader

agentic-workflows