A manual review process for a completed DARE task, comparing its written specification with the actual code. DARE is the task-management method used by this workflow.

Use it before marking a task done or when a task needs a detailed implementation review.

It can reveal unfinished placeholders, test-only code used in production, empty functions, TODOs, and requirements the code does not meet.

dare-review — Skill for Claude Code and Codex by dewtech-technologies

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 dewtech-technologies/dare-method --skill dare-review

Clone the repo

git clone --depth 1 https://github.com/dewtech-technologies/dare-method

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/dewtech-technologies/dare-method/dare-review/github.svg)](https://agentmods.dev/skills/dewtech-technologies/dare-method/dare-review)

Your own site

<a href="https://agentmods.dev/skills/dewtech-technologies/dare-method/dare-review"><img src="https://agentmods.dev/badge/skills/dewtech-technologies/dare-method/dare-review/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/dewtech-technologies/dare-method/dare-review"><img src="https://agentmods.dev/badge/skills/dewtech-technologies/dare-method/dare-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,073 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	$0.00092	$0.01073
Opus 5.5	$0.00037	$0.00429
Sonnet 5.5	$0.00018	$0.00215
Haiku 4.5	$0.00009	$0.00107

Measured 1mo ago against content hash 8870b6ab7fa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dare-review 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 1mo 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.

implementations/antigravity/.agents/skills/dare-review/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DARE Review Skill

Equivalente no terminal: dare review <task-id> --ai

Você é o auditor de qualidade do método DARE. Seu papel é verificar se uma task implementada realmente entrega o que a spec promete — sem stubs, sem mocks em produção, sem funções vazias, sem TODOs pendentes.

Quando usar esta skill

Antes de marcar uma task como DONE (gate obrigatório no Definition of Done)
Quando dare review <id> estático passa mas precisa validação semântica
Quando o dev pede revisão manual: "revise a task-034"

Camada estática vs semântica

O CLI dare review <id> já faz a camada estática: regex sobre os arquivos detecta TODO/FIXME/stubs/mocks/funções vazias. Esta skill faz a camada semântica: critério-a-critério da spec contra a implementação real.

Como executar

Passo 1: Rodar a camada estática

dare review <task-id> --format json > .dare/review-static-<task-id>.json

Leia o JSON. Se houver erros estáticos, reporte-os primeiro. Geralmente não vale prosseguir com semântica se a estática falhou.

Passo 2: Carregar contexto

DARE/EXECUTION/<task-id>.md — spec da task
Cada arquivo listado na seção 3 ("ARQUIVOS A CRIAR / MODIFICAR")
DARE/BLUEPRINT.md — contratos de API / modelos

Passo 3: Auditoria critério-a-critério

Para cada item das seções abaixo, marque ✅ / ❌ com evidência (arquivo + linha):

3.1 Objetivo (seção 1 da spec)

A implementação atinge o estado observável prometido? Encontre evidência concreta.

3.2 Arquivos (seção 3)

Todos existem com conteúdo descrito?
Arquivos extras suspeitos?

3.3 Implementação (seção 4)

Cada passo numerado foi executado?
Assinaturas exatas correspondem?
Validações têm regras concretas (não "valida email" — a regex específica)?

3.4 Testes (seção 4 — subitem testes)

Cada teste listado existe?
Tem assertions reais (não assertTrue(true))?
Edge cases enumerados cobertos?

3.5 Segurança (seção 5)

Input validation conforme spec?
Não há secrets/tokens hardcoded?
SQL/Command injection mitigado?

Read the full file on GitHub · 115 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.

1mo ago First seen · 115 lines · 92 tokens per session scan A 8870b6ab7fa0

Subscribe to this mod's changes

dare-review is a skill published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 3mo ago), licensed MIT. It adds 92 tokens to every session and 1,073 once invoked, about $0.0004 per session on Opus 5.5. 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.

Code review agentic-engineering ai-agents ai-assisted-development ai-coding anthropic claude

dare-review