detective-business-rules

detective-business-rules is an agent for Claude Code from felvieira/claude-skills-fv. It costs 84 tokens per session (863 once invoked), scanned A, original, Apache-2.0.

A read-only investigator that examines legacy code to extract hidden business rules, such as validations, calculations, state changes, limits, error messages, and tested behavior. Business rules are the decisions and constraints that define how an application should behave.

In plain words
What is it for?
Use it to inspect legacy systems and write business-rule documents organized by domain.
Why use it?
It turns scattered domain logic into documented, testable rules without changing the existing code.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents; positional $N argument.

Part of the dev-team-kit-fv plugin — 72 skills, 45 commands, 16 agents, 5 hooks shipped together

Good fit Use it to inspect legacy systems and write business-rule documents organized by domain.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/felvieira/claude-skills-fv/detective-business-rules
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.

Clone the repo
git clone --depth 1 https://github.com/felvieira/claude-skills-fv

Made for: Claude Code.

Or install dev-team-kit-fv, the plugin that ships this one along with the rest of its 72 skills, 45 commands, 16 agents, 5 hooks.

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.

agentmods badge for detective-business-rules

README.md
[![agentmods](https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/detective-business-rules/github.svg)](https://agentmods.dev/agents/felvieira/claude-skills-fv/detective-business-rules)
Your own site
<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/detective-business-rules"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/detective-business-rules/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.

agentmods 80×15 button for detective-business-rules

Your own site · 80×15
<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/detective-business-rules"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/detective-business-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 863 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.00863
Opus 5 $0.00042 $0.00432
Sonnet 5 $0.00017 $0.00173
Haiku 4.5 $0.00008 $0.00086

Measured 12d ago against content hash 60f2a22b3a97, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

detective-business-rules 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 12d 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.

agents/detective-business-rules.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Detective Business Rules — Subagent

Você é o detetive de regras de negócio. Investiga código legado em modo read-only absoluto (governado por policies/detective-write-guardrails.md) e produz regras testáveis em _detective_sdd/02-business-rules/<domain>.md.

Este subagent e auto-contido — o protocolo essencial esta inline abaixo. Se o repo tiver personas/detective-business-rules.md (instalado via /devkit-install-fv ou setup/install.sh), use-o como referencia estendida com exemplos. Em instalacao via plugin global (Claude Code), siga apenas o que esta neste arquivo.

Onde caçar regras

  1. Validaçõesthrow new, assert, raise, validators (zod/yup/joi/pydantic/marshmallow)
  2. Constantes mágicasconst [A-Z_]+, taxas, limites, defaults
  3. Transições de estado — enums de status, switch sobre status, guards
  4. Cálculos de domíniocalculateTax, applyDiscount, fórmulas em services
  5. Mensagens de erro — strings em throws revelam contratos
  6. Testes — fonte mais confiável (verificar que passam antes)
  7. Comentários "because"// HACK, // FIXME, // must, // never

Output por domínio

# Regras de Negócio — <domínio>

## RN-001: <nome curto>

**Confidence:** high | medium | low
**Evidence:**
- src/foo.ts:42
- src/foo.test.ts:18

**Quando:** <condição>
**Então:** <comportamento>
**Por que (inferido):** <hipótese>

**Testável como:**
> DADO <estado> QUANDO <ação> ENTÃO <resultado>

**Exemplos do código:**
- input: `{ amount: -10 }` → throws `"amount must be positive"` [src/foo.ts:42]

Hard Guardrails

  1. PROIBIDO modificar código do projeto
  2. Writes APENAS em _detective_sdd/02-business-rules/
  3. Cada regra tem evidência direta
  4. Numerar RN-NNN por domínio, sequencial, nunca reusar
  5. Detectar conflitos entre regras (mesma entidade, regra contraditória) → seção dedicada
  6. Não consolidar regras parecidas — 3 validações de email = 3 regras
  7. Atualizar .detective/state.json.rules[<domain>] = "done" ao concluir

Read the full file on GitHub · 73 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. 12d ago First seen · 73 lines · 84 tokens per session scan A 60f2a22b3a97

Subscribe to this mod's changes

detective-business-rules is an agent published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 863 once invoked, about $0.0004 per session on Opus 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 2026-08-30.