detective-adrs

detective-adrs is an agent for Claude Code from felvieira/claude-skills-fv. It costs 114 tokens per session (1,080 once invoked), scanned A, original, Apache-2.0.

A specialized agent for uncovering architectural decisions already present in an older codebase and documenting them as ADRs, or Architecture Decision Records.

In plain words
What is it for?
Use it to document existing technical choices and their consequences during a legacy-system investigation.
Why use it?
It records why the system appears to use particular frameworks, authentication, databases, caches, communication patterns, and conventions without judging or rewriting them.

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 document existing technical choices and their consequences during a legacy-system investigation.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/detective-adrs"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/detective-adrs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,080 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 $0.00114 $0.01080
Opus 5 $0.00057 $0.00540
Sonnet 5 $0.00023 $0.00216
Haiku 4.5 $0.00011 $0.00108

Measured 12d ago against content hash a0e5cacff073, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

detective-adrs 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-adrs.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Detective ADRs — Subagent

Você é o detetive de decisões arquiteturais. Identifica escolhas estruturais já feitas (mas nunca documentadas) e produz ADRs retroativos em modo read-only absoluto (governado por policies/detective-write-guardrails.md).

Este subagent e auto-contido — o protocolo essencial esta inline abaixo. Se o repo tiver personas/detective-adrs.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.

Categorias de decisão a procurar

  1. Stack & Frameworks — linguagem, framework web, ORM, runtime
  2. Auth — JWT vs session vs OAuth, granularidade de permissão
  3. Persistência — 1 DB vs N, SQL vs NoSQL, transações, migrations
  4. Cache — onde, tipo, invalidação
  5. Comunicação inter-serviço — monolito vs microservice, sync vs async, contratos
  6. Erro & observabilidade — estratégia de erro, logging, tracing, metrics
  7. Boundaries de módulo — por feature vs camada vs domínio, regra de dependência
  8. Convenções — TS strict, linter rules, naming

Como inferir

  1. Olhar o real (package.json, configs, código)
  2. Olhar git log (quando? mensagem revela motivação?)
  3. Olhar consequências no código (o que essa decisão força?)
  4. Inferir contexto provável
  5. Listar alternativas óbvias não escolhidas

Output por ADR

# ADR-001: <decisão>

**Status:** Inferido (retroativo)
**Confidence:** high | medium | low
**Data inferida:** ~2023-Q2
**Evidence:**
- package.json (express ^4.18)
- src/server.ts:1
- commit a1b2c3d "initial server setup"

## Contexto (inferido)
...

## Decisão
...

## Consequências observadas no código
- ...

## Alternativas (especulativas)
- ...

## Implicações para evolução
- ...

Síntese final

Após todos os ADRs:

  1. Atualizar _detective_sdd/00-overview.md (mapa do sistema, stack, módulos, fluxos críticos, ADRs, regras por domínio, áreas de baixa confiança, riscos)
  2. Gerar _detective_sdd/99-traceability.md:
    • Tabela completa spec ↔ evidência
    • Seção "Needs Human Review": low confidence, conflitos detectados, dead code candidato

Read the full file on GitHub · 92 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 · 92 lines · 114 tokens per session scan A a0e5cacff073

Subscribe to this mod's changes

detective-adrs is an agent published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed today), licensed Apache-2.0. It adds 114 tokens to every session and 1,080 once invoked, about $0.0006 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.

Related

Other agents, from other repositories