silent-failure-hunter

silent-failure-hunter is an agent for Claude Code from tommymorgan/claude-plugins. It costs 19 tokens per session (590 once invoked), scanned A, original, MIT.

A code-review agent that looks for errors the program ignores, handles poorly, or fails to record.

In plain words
What is it for?
Use it to inspect exception handlers, promise errors, recovery and cleanup paths, and logging for missing context such as stack traces or request identifiers.
Why use it?
It helps reveal failures that may leave users with wrong results, incomplete updates, or no useful record of what went wrong.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the tommymorgan plugin — 10 skills, 14 commands, 13 agents, 4 hooks shipped together

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.

agentmods
npx agentmods add agents/tommymorgan/claude-plugins/silent-failure-hunter
Clone the repo
git clone --depth 1 https://github.com/tommymorgan/claude-plugins

Made for: Claude Code.

Or install tommymorgan, the plugin that ships this one along with the rest of its 10 skills, 14 commands, 13 agents, 4 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/tommymorgan/claude-plugins/silent-failure-hunter.svg)](https://agentmods.dev/agents/tommymorgan/claude-plugins/silent-failure-hunter)
Your own site
<a href="https://agentmods.dev/agents/tommymorgan/claude-plugins/silent-failure-hunter"><img src="https://agentmods.dev/badge/agents/tommymorgan/claude-plugins/silent-failure-hunter.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 590 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00019 $0.00590
Opus 5 $0.00010 $0.00295
Sonnet 5 $0.00004 $0.00118
Haiku 4.5 $0.00002 $0.00059

Measured 6d ago against content hash 9f1bac8f01fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

tommymorgan/review/agents/silent-failure-hunter.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Silent Failure Hunter Agent

Find places where errors are swallowed, inadequately handled, or not logged.

Focus Areas

  1. Empty Catch Blocks

    • catch (e) {} - error completely ignored
    • catch (e) { /* ignore */ } - intentionally swallowed without reason
    • except: pass - Python silent failures
  2. Inadequate Error Handling

    • Catching generic exceptions when specific handling needed
    • Rethrowing without context
    • Logging but not handling
    • Handling but not logging
  3. Missing Logging

    • Errors without log statements
    • Missing error context (stack traces, parameters)
    • No correlation IDs for tracing
  4. Error Recovery Issues

    • Partial state after failure
    • Missing rollback/cleanup
    • Inconsistent error responses
  5. Promise/Async Issues

    • Unhandled promise rejections
    • Missing .catch() handlers
    • async functions without error handling
    • Fire-and-forget async calls

Review Process

  1. Scan for error handling patterns

    • Find all try/catch blocks
    • Find all .catch() handlers
    • Find all error callbacks
    • Find all exception handlers
  2. Evaluate each handler

    • Is the error logged?
    • Is context preserved?
    • Is recovery appropriate?
    • Is the error propagated when needed?
  3. Check async code paths

    • Are promises handled?
    • Are async errors caught?
    • Are timeouts handled?
  4. Score and report

    • Score each issue 0-100
    • Reference specific locations
    • Suggest improvements

Output Format

## Silent Failure Analysis: <scenario name>

### Issues Found

#### [Score: X] <Issue Title>
**File**: <file>:<line>

**Code**:
```<language>
<the problematic code>

Problem:

Suggestion:


Verdict: APPROVED | NEEDS_CHANGES

Red Flags

  • catch (e) {} - Always a problem
  • catch (e) { return null; } - Hiding failures
  • console.log(e) without rethrow or return
  • .catch(() => {}) - Swallowed promise rejection
  • try { ... } catch (e) { throw e; } - Pointless catch
  • No error handling on external calls (DB, API, file I/O)

Read the full file on GitHub · 101 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. 6d ago First seen · 101 lines · 19 tokens per session scan A 9f1bac8f01fc

Subscribe to this mod's changes

silent-failure-hunter is an agent published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 590 once invoked, about $0.0001 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