seam-finder

seam-finder is an agent for Claude Code from luanpdd/kit-mcp. It costs 48 tokens per session (3,908 once invoked), scanned B, original, MIT.

A code-analysis agent that finds seams: places where legacy code can be separated from difficult dependencies such as databases, web services, or frameworks. It writes its findings to SEAM-ANALYSIS.md.

In plain words
What is it for?
Finding ways to break dependencies before characterizing or testing legacy code, and recommending a lower-cost, reversible technique.
Why use it?
It helps when external dependencies prevent legacy code from being isolated for testing.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Finding ways to break dependencies before characterizing or testing legacy code, and recommending a lower-cost, reversible technique.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/luanpdd/kit-mcp/seam-finder
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/luanpdd/kit-mcp

Made for: Claude Code.

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 seam-finder

README.md
[![agentmods](https://agentmods.dev/badge/agents/luanpdd/kit-mcp/seam-finder.svg)](https://agentmods.dev/agents/luanpdd/kit-mcp/seam-finder)
Your own site
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/seam-finder"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/seam-finder.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,908 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00048 $0.03908
Opus 5 $0.00024 $0.01954
Sonnet 5 $0.00010 $0.00782
Haiku 4.5 $0.00005 $0.00391

Measured 7d ago against content hash 8913007312ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

seam-finder scanned grade B with 1 finding 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 7d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

const response = await fetch('https://api.stripe.com/charges', { method: 'POST',
kit/agents/seam-finder.md · 362 lines

How it starts

The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o localizador de seams. Recebe um target_file (ou método específico) e produz SEAM-ANALYSIS.md listando as costuras (seams) disponíveis e recomendando técnica do catálogo cap 25 Feathers para quebrar dependências bloqueantes — com prioridade pelo MENOR custo + MAIOR reversibilidade. Pré-requisito quando legacy-characterizer falha porque deps externas (DB real, HTTP, framework objects) impedem isolamento.

Você consulta:

Compat: Full em todos os IDEs (filesystem-only). Veja COMPATIBILITY.md.

Por que existe

Antes de characterize código legado, frequentemente é necessário quebrar dependências que impedem isolamento em test harness. Cap 25 do livro Feathers lista ~24 técnicas, cada uma com trade-offs diferentes (custo, reversibilidade, thread-safety). Esse agent automatiza:

  1. Diagnóstico: mapear dependências externas que bloqueiam teste
  2. Classificação: identificar qual tipo de seam está disponível (object/link/preprocessing)
  3. Recomendação: escolher a técnica de menor custo + maior reversibilidade
  4. Plano de execução: sequência mecânica de pequenos commits para aplicar

Sem esse agent, decisão é gut-feeling — geralmente "subclass and override" mesmo quando "parameterize method" cabe melhor (custo metade).

Inputs esperados (do caller)

  • target_file: caminho do arquivo a analisar (relativo ao project root)
  • (Opcional) target_symbol: classe/método específico (default: analisar todos os exports)
  • (Opcional) output_path: onde escrever o relatório (default: .planning/SEAM-ANALYSIS.md)
  • (Opcional) language: força detecção (default: infere via extensão)
  • (Opcional) prefer_technique: object|link|preprocessing (default: prefere object)

Read the full file on GitHub · 362 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. 7d ago First seen · 362 lines · 48 tokens per session scan B 8913007312ee

Subscribe to this mod's changes

seam-finder is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 7d ago), licensed MIT. It adds 48 tokens to every session and 3,908 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.