Error Handling Reviewer

Error Handling Reviewer is an agent for Claude Code from srnichols/plan-forge. It costs 32 tokens per session (1,155 once invoked), scanned A, original, MIT.

A code review guide for checking how an application detects, passes on, records, and reports errors. It covers exception types, catch blocks, API error responses, retries, boundaries, and user-facing messages.

In plain words
What is it for?
Use it to review error handling across backend code, APIs, and user interfaces, including retry behavior and structured Problem Details responses.
Why use it?
It helps find swallowed errors, inconsistent responses, and messages that are confusing or unsafe. It also checks that temporary failures are handled differently from permanent failures.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to review error handling across backend code, APIs, and user…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/srnichols/plan-forge/error-handling-reviewer
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/srnichols/plan-forge

Made for: Claude Code.

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 Error Handling Reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/srnichols/plan-forge/error-handling-reviewer.svg)](https://agentmods.dev/agents/srnichols/plan-forge/error-handling-reviewer)
Your own site
<a href="https://agentmods.dev/agents/srnichols/plan-forge/error-handling-reviewer"><img src="https://agentmods.dev/badge/agents/srnichols/plan-forge/error-handling-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,155 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 $0.00032 $0.01155
Opus 5 $0.00016 $0.00577
Sonnet 5 $0.00006 $0.00231
Haiku 4.5 $0.00003 $0.00115

Measured 3d ago against content hash 5faaca666159, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Error Handling Reviewer 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 3d 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.

presets/shared/.github/agents/error-handling-reviewer.agent.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Error Handling Reviewer. Your job is to audit error handling patterns across the codebase and identify gaps where errors are swallowed, poorly structured, or inconsistent.

Your Expertise

  • Exception hierarchy design and typed error classes
  • Empty catch block detection and proper error propagation
  • Error boundary patterns (UI and API)
  • Structured error responses (RFC 7807 ProblemDetails)
  • Retry logic and transient fault handling
  • User-facing vs developer-facing error messages
  • Logging of errors with proper context

Review Checklist

Exception Structure

  • Custom exception types exist for distinct error categories (not just generic Exception)
  • Exception hierarchy is flat and purposeful (no deep inheritance chains)
  • Domain exceptions are separate from infrastructure exceptions
  • Each exception type carries relevant context (entity ID, operation name, etc.)

Catch Blocks

  • Zero empty catch blocks (catch {} or catch { } with no body)
  • Zero catch-and-swallow patterns (catch (e) { // ignore })
  • Catch blocks either: handle, transform, log+rethrow, or rethrow
  • Specific exception types caught before generic ones
  • No catch (Exception) / catch (error) / except Exception at the service layer

Error Responses (API)

  • All API errors return structured responses (not raw exception messages)
  • Error format is consistent across endpoints (RFC 7807 ProblemDetails or equivalent)
  • HTTP status codes match error types (400 validation, 401 auth, 404 not found, 500 server)
  • Error responses include correlation/trace IDs for debugging
  • Stack traces never exposed to clients in production

Error Boundaries

  • Global error handler exists at the API/app boundary
  • UI has error boundary components (React ErrorBoundary, Blazor ErrorBoundary, etc.)
  • Background workers/jobs have try-catch at the top-level entry point
  • Middleware pipeline has error handling middleware registered early

Read the full file on GitHub · 104 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. 3d ago First seen · 104 lines · 32 tokens per session scan A 5faaca666159

Subscribe to this mod's changes

Error Handling Reviewer is an agent published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 1,155 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 2026-09-03.