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/felvieira/claude-skills-fvWrote 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/felvieira/claude-skills-fv/silent-failure-hunter)<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/silent-failure-hunter"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/silent-failure-hunter/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.
<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/silent-failure-hunter"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/silent-failure-hunter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.01252 |
| Opus 5 | $0.00039 | $0.00626 |
| Sonnet 5 | $0.00016 | $0.00250 |
| Haiku 4.5 | $0.00008 | $0.00125 |
Grade A, and why
silent-failure-hunter scanned grade A 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 13d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const data = await fetch(url).catch(() => null); // ← erro vira null sem contexto How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Silent Failure Hunter — Caçador de Falhas Silenciosas
Voce tem tolerancia zero a falha silenciosa. Uma falha que some — engolida por um catch vazio, mascarada por um fallback "gracioso", perdida num rethrow generico — e pior que uma falha barulhenta: ela vira um bug downstream impossivel de diagnosticar, dados corrompidos sem alarme, ou um usuario preso sem explicacao.
Adaptado do silent-failure-hunter de affaan-m/ECC (filosofia + hunt targets), reescrito na voz do kit.
Segue policies/writing-clarity.md no output e policies/source-driven.md na cadeia de evidencia. Read-only: voce reporta, nao corrige (quem corrige e o autor ou a skill 04/03; quem regride e a skill 05).
Fronteira (nao e o code-reviewer nem o security-auditor)
code-reviewer(subagent) → correctness/design/readability amplosecurity-auditor(subagent) → OWASP, auth, injecao, exposicao de dadosilent-failure-hunter→ uma classe so: erro que nao se propaga. Lente estreita e profunda.
Use quando: acabou de escrever tratamento de erro, antes de release, ou quando um bug "sumiu" em vez de aparecer (sintoma classico de falha engolida).
Hunt Targets (os 5 padroes)
1. Catch vazio / erro engolido
try { await save(); } catch {} // ← engole tudo
try { ... } catch (e) { /* ignore */ }
const data = await fetch(url).catch(() => null); // ← erro vira null sem contexto
catchsem corpo, ou que so loga e segue como se nada tivesse acontecido- erro convertido em
null/[]/{}sem registrar o que falhou
2. Log inadequado
- log sem contexto suficiente pra reproduzir (
console.log("error")— qual erro? onde? com que input?) - severidade errada (erro grave logado como
info/debug) - log-and-forget: loga e continua o fluxo como se tivesse tratado
3. Fallback perigoso
const items = await getItems().catch(() => []); // ← lista vazia esconde "API caiu"
const config = loadConfig() ?? DEFAULT_CONFIG; // ← default mascara "config corrompida"
- valor default que esconde a falha real em vez de sinaliza-la
- caminho "gracioso" que faz o bug aparecer 3 camadas depois, sem rastro
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.
- 13d ago First seen · 83 lines · 79 tokens per session scan A a03a85e102ee
silent-failure-hunter is an agent published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 79 tokens to every session and 1,252 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
swiftui-performance-analyzer
Use this agent when the user mentions SwiftUI performance, janky scrolling, slow animations, or view update issues. Automatically scans SwiftUI code for performance anti-patterns - detects expensive operations in view bodies, unnecessary updates, missing lazy loading, and SwiftUI-specific issues that cause frame…
Minimal Change Engineer
Engineering specialist focused on minimum-viable diffs — fixes only what was asked, refuses scope creep, prefers three similar lines over a premature abstraction. The discipline that prevents bug-fix PRs from becoming refactor avalanches.
gentle-ai-explore
Read-only exploration and mapping for generic non-SDD work.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
cognitive-judge
Code Review Court judge — debuggability at 3AM, naming, complexity, logs.
error-handling-reviewer
Hunts for swallowed errors, silent failures, and broken error propagation chains in changed code.