What is reviewer-architect-adversarial?

A review method for testing an implementation plan before coding begins. It checks that referenced files and interfaces exist, that requirements are covered, and that hidden assumptions are exposed.

Reviewing architecture and implementation plans, acceptance criteria, file layouts, data flows, and planned tests before development starts.

It finds structural gaps and risky assumptions while changing the plan is still cheaper than rewriting code. This is a review of what will be built, not just what was built.

reviewer-architect-adversarial — Skill for Claude Code and Codex by nt

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.

Any agent

npx skills add ntorga/agent-starter-kit --skill reviewer-architect-adversarial

Clone the repo

git clone --depth 1 https://github.com/ntorga/agent-starter-kit

Made for: Claude Code, Codex.

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/skills/ntorga/agent-starter-kit/reviewer-architect-adversarial/github.svg)](https://agentmods.dev/skills/ntorga/agent-starter-kit/reviewer-architect-adversarial)

Your own site

<a href="https://agentmods.dev/skills/ntorga/agent-starter-kit/reviewer-architect-adversarial"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/reviewer-architect-adversarial/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ntorga/agent-starter-kit/reviewer-architect-adversarial"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/reviewer-architect-adversarial.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,393 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.

Model	Per session	Once invoked
Fable 5.1	$0.00026	$0.02393
Opus 5	$0.00013	$0.01196
Sonnet 5	$0.00005	$0.00479
Haiku 4.5	$0.00003	$0.00239

Measured 2d ago against content hash 26b2e4d1b525, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-14, from the pricing page.

Security

Grade A, and why

reviewer-architect-adversarial 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 2d 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/reviewer-architect-adversarial/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

A plan that survives adversarial scrutiny saves hours of rework. Code review catches bugs in what was built. This skill catches flaws in what will be built. It validates structural soundness of the grill artifacts (do referenced files and APIs exist? do the epics cover all acceptance criteria? are the epics coherent?) and attacks assumptions (where will this break? what does the plan take for granted?). Surface problems now, when the fix costs a plan revision, not a code rewrite.

Procedure

Read the artifacts end-to-end. Read tree.md, plan.md, arch.md, and impl.md in .memory/plan/<feature-slug>/. Understand the design tree, acceptance criteria, directory structure, epics, information flows, methods, and tests.

Initialize the progress file. Create .memory/reviews/review-architecture-<timestamp>.md and save it before proceeding:

# Architecture Review Progress

## Status
- Last updated: <timestamp>
- Overall: In Progress

## Phases
- [ ] 1. Completeness
- [ ] 2. Structural validation
- [ ] 3. Coverage
- [ ] 4. Assumptions
- [ ] 5. Standards
- [ ] 6. Scope

## Findings

Do not proceed until the file exists on disk.

Completeness. Answer each question with yes or no. A "no" is a Blocker. Write findings to the progress file under ## Findings with heading ### Completeness. Mark phase 1 as [x]. Save the file before proceeding.

tree.md:
- Does tree.md exist with a Path: line naming the selected path?
- Is every node in tree.md marked [settled]? Any [open] node is a Blocker — the grill terminated early.
- Does every fact in ## Facts carry a found answer? An open fact with no node depending on it is a Warning.
plan.md:
- Does plan.md contain a context section (2-3 sentences)?
- Does plan.md contain an acceptance criteria section with at least one numbered criterion?
- Is plan.md free of implementation mechanism (no file paths, function names, class names)? Technical terms that describe the product's domain are product language, not mechanism. Flag only terms that prescribe how to build, not terms that describe what the product is.
- Clean rewrite check. Does plan.md contain zero strikethrough markup, "Revised:" annotations, "no longer" phrasing, or diff-style markers? If any are present: Blocker.

Read the full file on GitHub · 118 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.

2d ago First seen · 118 lines · 26 tokens per session scan A 26b2e4d1b525

Subscribe to this mod's changes

reviewer-architect-adversarial is a skill published in the GitHub repository ntorga/agent-starter-kit (142 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 2,393 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 2026-09-13.

Code review Multi-Agent Planning agent-framework ai-agents coding-assistant llm-orchestration model-agnostic

pragma-code-review

A code-review guide written in Chinese. It reviews code across correctness, architectural boundaries, risk, and verification.

pqpo/pragma · 24 tokens

safe-refactor

Refactor checklist with guardrails.

eddmann/my-own-coding-agent · 10 tokens

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

build-and-test

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

microsoft/agent-framework · 26 tokens

python-feature-lifecycle

Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.

microsoft/agent-framework · 43 tokens