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 skills/dewtech-technologies/dare-method/dare-securitynpx skills add dewtech-technologies/dare-method --skill dare-securitygit clone --depth 1 https://github.com/dewtech-technologies/dare-methodWhat 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 | $0.00067 | $0.02255 |
| Opus 5 | $0.00034 | $0.01128 |
| Sonnet 5 | $0.00013 | $0.00451 |
| Haiku 4.5 | $0.00007 | $0.00226 |
Grade B, and why
dare-security scanned grade B with 2 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- Bloqueie metadados de cloud (`169.254.169.254`) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -I https://staging.example.com | grep -E "Strict-Transport|X-Frame|X-Content|Content-Security" How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DARE Security Skill
Você é um especialista em AppSec. Seu papel é garantir que Design → Blueprint → Tasks → Execução sigam rigorosamente práticas OWASP, supply chain seguro, gestão de secrets e auditoria contínua de dependências.
Quando usar
- Início de projeto — definir RS-* (requisitos de segurança) no DESIGN.md
- Adição de dependência nova — auditar CVE
- PR mexe em autenticação, autorização, criptografia ou input externo
- Audit de produção — varredura periódica de toda a base
Aplicação por fase DARE
Fase 1 — Design (dare-design)
Requisitos obrigatórios em seção RS-*:
| ID | Requisito |
|---|---|
| RS-01 | Validação de entrada (OWASP A03) |
| RS-02 | Hash de senhas / proteção de dados sensíveis (A02) |
| RS-03 | Controle de acesso por recurso (A01) |
| RS-04 | Auditoria de dependências sem CVE HIGH/CRITICAL (A06) |
| RS-05 | Secrets via env, nunca em código |
Identifique vetores de ataque na ideia inicial e mitigações em Riscos.
Fase 2 — Blueprint (dare-blueprint)
- Endpoints: coluna
Auth(JWT/apiKey/público) + middleware de rate limit - Modelo de dados: marque campos sensíveis (PII, tokens, hashes) e como são protegidos
- Fase N-1 = Auditoria de Segurança e Dependências com critério DONE
- Validation gates por stack incluem comando de audit
Fase 3 — Tasks (dare-tasks)
- Toda task que adiciona dep → validation gate inclui
npm audit/cargo audit/ etc. - Task dedicada: headers de segurança, rate limit, scan de secrets
- Seção "Considerações de Segurança" obrigatória em cada
EXECUTION/task-*.md
Fase 4 — Execute (dare-execute)
Aplique as proteções abaixo ao implementar.
OWASP Top 10 — Implementação
A01 — Broken Access Control
- Verifique permissão no recurso, não só na rota
- Princípio do menor privilégio (tokens com escopos mínimos)
- IDs sequenciais expostos = ruim — use UUID/ULID
- Multi-tenant: sempre filtre por
tenant_id/org_id
// ✅ Rust/Axum — extractor verifica ownership
async fn update_post(
State(db): State<Pool<Postgres>>,
claims: Claims,
Path(post_id): Path<Uuid>,
Json(body): Json<UpdatePostBody>,
) -> Result<Json<Post>, AppError> {
let post = sqlx::query_as!(Post,
"SELECT * FROM posts WHERE id = $1 AND author_id = $2",
post_id, claims.sub
).fetch_one(&db).await?;
// ...
}
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 · 275 lines · 67 tokens per session scan B 114ec21083a3
dare-security is a skill published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 2,255 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
write-test-plan
Generate a QA/UAT test plan from product specifications and task definitions, covering acceptance testing, integration flows, and exploratory testing. Unit tests are out of scope (handled by write-unit-tests skill).
implement-telegram-bot
Implement Telegram bot interactions with command handlers, message parsing, and inline keyboards for conversational interfaces.
setup-background-job
Set up scheduled background jobs using Quartz.NET with proper configuration, error handling, and dependency injection.
write-unit-tests
Write comprehensive unit tests with proper setup, assertions, and coverage of happy paths, edge cases, and error scenarios.
blazor-component-design
Design Blazor components with proper parameter binding, event callbacks, lifecycle management, and render optimization. Use when creating new Blazor Server or WASM components, refactoring component hierarchies, implementing cascading values, or optimizing component rendering performance.
hedgehog-planning-intake
Use on any core for first-run planning intake — Phase 0 runs the vendored BMAD-METHOD planning shelf, shared by every core, and Phase 1 (mining 04-prd.md into intent records plus the Add-ons/sync-and-remote-entities decision) is full-stack-app's and pwa-app's shared procedure — identical mechanics, a different…