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 skills add dewtech-technologies/dare-method --skill dare-refinegit 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/skills/dewtech-technologies/dare-method/dare-refine)<a href="https://agentmods.dev/skills/dewtech-technologies/dare-method/dare-refine"><img src="https://agentmods.dev/badge/skills/dewtech-technologies/dare-method/dare-refine/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.
<a href="https://agentmods.dev/skills/dewtech-technologies/dare-method/dare-refine"><img src="https://agentmods.dev/badge/skills/dewtech-technologies/dare-method/dare-refine.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00076 | $0.01045 |
| Opus 5.5 | $0.00030 | $0.00418 |
| Sonnet 5.5 | $0.00015 | $0.00209 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade A, and why
dare-refine 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.
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.
DARE Refine Skill
Equivalente no terminal:
dare refine <task-id> --split --ai
Você é o refinador de tasks do método DARE. Seu papel é garantir que cada task caiba em uma conversa única do agente — sem ficar tão grande que o agente "invente" stubs/mocks pra completar.
Quando usar
- Após
dare-tasksgerar o DAG, para cada task com complexity HIGH nodare-dag.yaml - Quando o dev pede: "refine task-034"
- Quando o BLUEPRINT mudou e uma task ficou grande demais
Camada determinística vs semântica
O CLI dare refine <id> já mede sinais objetivos: # arquivos, # funções, # testes, # dependências, keywords pesadas. Esta skill faz a camada semântica — você lê o conteúdo da spec e decide se faz sentido quebrar.
Como executar
Passo 1: Rodar a heurística determinística
dare refine <task-id> --split --format json > .dare/refine-<task-id>.json
JSON traz:
report.score,report.levelreport.signals— explica a pontuaçãoreport.recommendsSplit— true se HIGH/CRITICALproposal.subtasks— quebra inicial coarse
Passo 2: Decidir se quebra
Quebrar quando:
recommendsSplit: true(HIGH/CRITICAL)- Mais de 6 arquivos
- Mistura responsabilidades (modelo + controller + teste + migration)
- Inclui refactor + feature juntos
- Keyword "pesada" + score MED+
Manter inteira quando:
- LOW ou MED baixo
- Mesmo módulo
- Cabe em uma conversa (15–60 min)
Passo 3: Eixos de split
| Eixo | Quando |
|---|---|
| Por camada | Modelo / Controller / Service / Test separados |
| Por endpoint | 4 endpoints → 4 sub-tasks |
| Por feature | Auth = register + login → split por verbo |
| Refactor + feature | "1. refactor" + "2. feature em cima" |
| Migration + código | "1. migration" + "2. código novo" |
Cada sub-task:
subtask_promptauto-suficiente (Anti-Stub Contract!)- Spec própria em
DARE/EXECUTION/<sub-id>.md depends_onmínimo mas correto- Complexity honesta — se sub ainda for HIGH, quebrar de novo
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 · 118 lines · 76 tokens per session scan A a782b9cc8386
dare-refine is a skill published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 1,045 once invoked, about $0.0003 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.
Other skills, from other repositories
project-diagnosis
Structured gap analysis that identifies what a project is missing — not what's done poorly (that's /audit), but what's absent entirely. Checks for tests, CI, security basics, linting, type safety, deployment readiness, and dependency health. Each finding has a severity and a concrete fix action.
tech-debt-tracking
Track shortcuts with justifications, prevent debt accumulation, and surface outstanding debt at session start.
create-stories
Breaks one epic into implementable stories with acceptance criteria. Use when the user wants stories for an epic or the next batch of work to build. Not for turning the whole design into epics.
release-checklist
Pre-release checklist — build verification, certification requirements, store metadata, launch readiness.
retrospective
Sprint or milestone retrospective from completed work, velocity, blockers. Actionable insights for the next iteration.
bug-triage
Re-evaluate open bugs — priority vs severity, assign to sprints, surface systemic trends. Run when the count grows.