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.
npx agentmods add commands/dewtech-technologies/dare-method/dare-reviewgit clone --depth 1 https://github.com/dewtech-technologies/dare-methodWrote 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.
[](https://agentmods.dev/commands/dewtech-technologies/dare-method/dare-review)<a href="https://agentmods.dev/commands/dewtech-technologies/dare-method/dare-review"><img src="https://agentmods.dev/badge/commands/dewtech-technologies/dare-method/dare-review.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.01238 |
| Opus 5 | $0.00000 | $0.00619 |
| Sonnet 5 | $0.00000 | $0.00248 |
| Haiku 4.5 | $0.00000 | $0.00124 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comando: /dare-review
Equivalente no terminal:
dare review <task-id> --ai
Descrição
Audita uma task implementada cruzando a spec (DARE/EXECUTION/<id>.md) com os arquivos reais que ela tocou. Detecta stubs, mocks fora de testes, funções vazias, TODOs, retorno-fantasma — e valida critério-a-critério se a implementação satisfaz o que a spec prometeu.
Esta é a camada semântica do review. A camada estática (regex / patterns) já é feita automaticamente pelo CLI quando você roda dare review <task-id>. Este comando combina as duas: rode a estática via CLI, gere um verdito semântico aqui, e produza um relatório fundido.
Quando rodar
- Antes de marcar uma task como DONE (gate obrigatório no Definition of Done do TASK-SPEC)
- Quando o
dare review <id>estático passa mas você quer validação adicional contra a spec - Quando o dev pede revisão manual:
/dare-review task-034
Como executar
1. Validar argumento
$ARGUMENTS deve conter o task-id (ex.: task-034). Se vazio, peça.
2. Rodar a camada estática primeiro
dare review $ARGUMENTS --format json > .dare/review-static-$ARGUMENTS.json
Leia esse JSON. Se já houver erros estáticos, reporte-os primeiro e pergunte se quer prosseguir com a análise semântica mesmo assim (geralmente não vale — corrige os erros estáticos antes).
3. Carregar contexto
DARE/EXECUTION/$ARGUMENTS.md— spec da task- Cada arquivo listado na seção 3 da spec ("ARQUIVOS A CRIAR / MODIFICAR")
DARE/BLUEPRINT.md— contratos de API / modelos referenciados
4. Auditoria critério-a-critério
Para cada item nas seções abaixo da spec, marque ✅ / ❌:
4.1 Objetivo (seção 1)
A implementação atinge o estado observável que a seção 1 promete? Encontre evidência concreta (arquivo + linha) ou marque como não atendido.
4.2 Arquivos a criar / modificar (seção 3)
- Todos os arquivos da tabela existem com o conteúdo descrito?
- Há arquivos não listados que deveriam estar lá?
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.
- yesterday First seen · 117 lines · 0 tokens per session scan A cfdc010a6dbe
dare-review is a command published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,238 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 2026-09-03.
Other commands, from other repositories
consult
Use the "consult7" MCP server to request help from "openai/gpt-5", or the model explicitly specified, regarding the following request. Send it the following request, along with the relevant codebase, ALWAYS EXCLUDING all files and folders described in .claudeignore and .gitignore, as well as any file for which the…
health
Command "health" from Vimalk0703/shipworthy, covering part 1: plugin installation health and part 2: project health.
audit
Before executing this command, output.
start
SoDamAgentic 온보딩. 사용자가 /sodam-agentic:start 로 처음 시작할 때, "AI에게 제대로 일 시키는 4단계(계획→실행→검토→안전)"를 쉬운 한국어로 안내하고 안전 상태를 점검한다.
log
SoDamAgentic 안전 기록 조회(F6). 사용자가 /sodam-agentic:log 로 실행하면, 지금까지 안전장치가 막거나 확인받은 내역을 쉬운 한국어로 요약해 보여준다.
review
SoDamAgentic "변경점 검토". 사용자가 /sodam-agentic:review 로 직접 실행하거나, 파일 변경 직후 자동으로 발동해(skills/review) 무엇을·왜 바꿨고 위험은 없는지 쉬운 한국어로 요약한다.