silent-failure-hunter

silent-failure-hunter is an agent for Claude Code from felvieira/claude-skills-fv. It costs 79 tokens per session (1,252 once invoked), scanned A, original, Apache-2.0.

A review-only agent that searches for errors which code catches, hides, or replaces with misleading fallback values.

In plain words
What is it for?
Use it after adding error handling, before a release, or when a bug seems to disappear. It checks empty catch blocks, swallowed promises, unsafe defaults, lost stack traces, and missing rollback handling.
Why use it?
Hidden failures can turn into undiagnosed bugs, corrupted data, or confusing user behavior because the original problem never surfaces.

Agent for Claude Code

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

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

Good fit Use it after adding error handling, before a release, or when a bug seems to disappear. It checks empty catch blocks, swallowed promises, unsafe defaults, lost stack traces, and missing rollback handling.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/felvieira/claude-skills-fv/silent-failure-hunter
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 silent-failure-hunter

README.md
[![agentmods](https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/silent-failure-hunter/github.svg)](https://agentmods.dev/agents/felvieira/claude-skills-fv/silent-failure-hunter)
Your own site
<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.

agentmods 80×15 button for silent-failure-hunter

Your own site · 80×15
<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>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,252 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00079 $0.01252
Opus 5 $0.00039 $0.00626
Sonnet 5 $0.00016 $0.00250
Haiku 4.5 $0.00008 $0.00125

Measured 13d ago against content hash a03a85e102ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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
agents/silent-failure-hunter.md · 83 lines

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 amplo
  • security-auditor (subagent) → OWASP, auth, injecao, exposicao de dado
  • silent-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
  • catch sem 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

Read the full file on GitHub · 83 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. 13d ago First seen · 83 lines · 79 tokens per session scan A a03a85e102ee

Subscribe to this mod's changes

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.