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.
git clone --depth 1 https://github.com/luanpdd/kit-mcpWrote 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/agents/luanpdd/kit-mcp/seam-finder)<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>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 | $0.00048 | $0.03908 |
| Opus 5 | $0.00024 | $0.01954 |
| Sonnet 5 | $0.00010 | $0.00782 |
| Haiku 4.5 | $0.00005 | $0.00391 |
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', 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:
legacy-seams-and-test-harness— catálogo de técnicas + decision treelegacy-effect-analysis— para identificar quais deps são inflection points_shared-legacy/glossary.md— vocabulário canônico
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:
- Diagnóstico: mapear dependências externas que bloqueiam teste
- Classificação: identificar qual tipo de seam está disponível (object/link/preprocessing)
- Recomendação: escolher a técnica de menor custo + maior reversibilidade
- 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)
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.
- 7d ago First seen · 362 lines · 48 tokens per session scan B 8913007312ee
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.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.