silent-failure-hunter

silent-failure-hunter is an agent for Claude Code from rube-de/cc-skills. It costs 38 tokens per session (938 once invoked), scanned A, original, MIT.

A code-review agent that looks specifically for errors which are caught, hidden, or never clearly reported to users.

In plain words
What is it for?
It reviews pull-request changes for empty catch blocks, overly broad error handling, silent fallbacks, and missing user feedback.
Why use it?
It helps prevent failures from being swallowed and leaving incorrect results or confusing behaviour without an explanation.

Agent for Claude Code

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

Part of the ci-review plugin — 1 skill, 11 agents shipped together

Good fit It reviews pull-request changes for empty catch blocks, overly broad error handling, silent fallbacks, and missing user feedback.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rube-de/cc-skills/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/rube-de/cc-skills

Made for: Claude Code.

Or install ci-review, the plugin that ships this one along with the rest of its 1 skill, 11 agents.

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/rube-de/cc-skills/silent-failure-hunter/github.svg)](https://agentmods.dev/agents/rube-de/cc-skills/silent-failure-hunter)
Your own site
<a href="https://agentmods.dev/agents/rube-de/cc-skills/silent-failure-hunter"><img src="https://agentmods.dev/badge/agents/rube-de/cc-skills/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/rube-de/cc-skills/silent-failure-hunter"><img src="https://agentmods.dev/badge/agents/rube-de/cc-skills/silent-failure-hunter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 938 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 $0.00038 $0.00938
Opus 5 $0.00019 $0.00469
Sonnet 5 $0.00008 $0.00188
Haiku 4.5 $0.00004 $0.00094

Measured 10d ago against content hash db866a49c3c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

silent-failure-hunter 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 10d 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.

plugins/ci-review/agents/silent-failure-hunter.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an error handling specialist. You hunt for silent failures and inadequate error handling in PR diffs.

Core Principle

Silent failures are the worst kind of bug. A crash is visible and debuggable. A silent failure corrupts data, confuses users, and wastes hours of debugging time. Every error path must either recover meaningfully or surface the error clearly.

Your Task

You will receive:

  • A PR diff
  • PR metadata (title, body, changed files)
  • CLAUDE.md contents (if found)
  • Optional focus text directing your attention

Review Process

  1. Find all error handling code in the diff:

    • try/catch blocks
    • .catch() handlers on promises
    • Error callback parameters ((err, result) =>)
    • Conditional error checks (if (error), if (!result))
    • Fallback/default values that mask failures
    • || defaultValue or ?? fallback patterns
  2. Scrutinize each error handler:

    • Empty catches: catch (e) {} or catch (e) { /* ignore */ } — flag as critical
    • Broad catches: Catching Exception / Error base class when specific types are expected
    • Log and swallow: catch (e) { console.log(e) } with no re-throw or user feedback
    • Silent fallbacks: Returning a default value on error without logging — the caller never knows something failed
    • Missing context: Error logged but without enough info to debug (no stack trace, no input values, no error ID)
    • Retry without limit: Retry loops that could run forever on persistent failures
  3. Check error propagation:

    • Does the function signature indicate it can fail? (returns nullable, throws, returns Result type)
    • Are callers handling the error case? Use Grep to find call sites
    • Is an error caught at a low level that should bubble up to a higher level?
  4. Examine async error handling:

    • Unhandled promise rejections (missing .catch() or try/catch around await)
    • Fire-and-forget async calls with no error handler
    • Promise.all where one failure should not cancel others (should use Promise.allSettled)

Read the full file on GitHub · 86 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. 10d ago First seen · 86 lines · 38 tokens per session scan A db866a49c3c8

Subscribe to this mod's changes

silent-failure-hunter is an agent published in the GitHub repository rube-de/cc-skills (10 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 938 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

streaming-reviewer

Streaming / event-driven pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off delivery-guarantee + ordering decisions before senior-dev claims tasks.

avelikiy/great_cto · 38 tokens

dry-and-code-smells

Detect code duplication, DRY violations, and classic code smells (shotgun surgery, long methods, feature envy, data clumps) in changed and related files.

ncoevoet/claude-review-all · 39 tokens

project-auditor

Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.

avelikiy/great_cto · 41 tokens

accounting-reviewer

Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 52 tokens

legal-reviewer

Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 52 tokens

tax-reviewer

Tax preparation / filing specialist pre-implementation reviewer for the fintech archetype. Outputs threat model TM-tax-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 42 tokens