dare-ax

A project audit and setup tool focused on Agent Experience: the information and safeguards that help coding agents understand and operate a codebase. It checks or creates items such as `llms.txt`, API documentation, JSON output, environment examples, and basic protections.

In plain words
What is it for?
Use it to audit or prepare a project for coding agents, validate or create an OpenAPI description, and add JSON output to command-line tools where needed.
Why use it?
It reduces unnecessary code changes caused by agents missing project structure, commands, API details, or safety rules. It also highlights missing input validation, rate limits, and secret-handling practices.

Command for Claude Code

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.

agentmods
npx agentmods add commands/dewtech-technologies/dare-method/dare-ax
Clone the repo
git clone --depth 1 https://github.com/dewtech-technologies/dare-method

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,068 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01068
Opus 5 $0.00000 $0.00534
Sonnet 5 $0.00000 $0.00214
Haiku 4.5 $0.00000 $0.00107

Measured 2d ago against content hash 511c20dfb56d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dare-ax 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.

implementations/claude/.claude/commands/dare-ax.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dare-ax

Audita ou bootstrapa um projeto DARE com foco em Agent Experience (AX) — os sinais estruturados que agentes de código (Claude Code, Cursor, Antigravity) precisam para trabalhar sem refactor desnecessário.

Como usar

/dare-ax                          # audita projeto atual
/dare-ax init                     # cria llms.txt + .env.example + ajustes mínimos
/dare-ax openapi                  # valida ou gera openapi.json
/dare-ax cli                      # adiciona --json em comandos CLI faltantes

Os três planos AX

1. Discovery — agente acha o que precisa

  • llms.txt na raiz com descrição, comandos, endpoints
  • README.md com bootstrap em 5 minutos
  • Estrutura de pastas previsível (src/, tests/, docs/, DARE/)

2. Usage — agente consegue operar

  • openapi.json em /openapi.json (HTTP)
  • Flag --json em todos os CLIs
  • Dockerfile + docker-compose.yml validados
  • .env.example versionado

3. Defense — agente não quebra produção

  • Rate limit (rack-attack, express-rate-limit, tower-governor, slowapi)
  • Validação de input (FormRequests, Pydantic, Zod, serde+validator)
  • Secrets só via env
  • llms.txt sem credenciais (scan no CI)

Métricas obrigatórias

ID Métrica Como verificar
M-01 llms.txt existe e é válido (sem secrets, seções obrigatórias) grep + parse
M-02 openapi.json ou public/openapi.json existe test -f
M-03 CLI suporta --json cli --help | grep '\-\-json'
M-04 Rate limit configurado grep pelo middleware da stack

Falha em CI se M-01 ou M-04 falharem em produção.

O que fazer

Passo 1: Auditar o projeto

Confira na ordem:

  1. Existe llms.txt? Está atualizado?
  2. Existe openapi.json se o projeto expõe HTTP?
  3. Todos os CLIs aceitam --json?
  4. Existe rate limit em endpoints autenticados públicos?
  5. .env.example está versionado sem valores reais?

Passo 2: Gerar llms.txt se faltar

Use este template — preencha apenas com comandos e endpoints que existem de verdade:

Read the full file on GitHub · 132 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.

  1. 2d ago First seen · 132 lines · 0 tokens per session scan A 511c20dfb56d

Subscribe to this mod's changes

dare-ax 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 1,068 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 2026-08-31.