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.
npx agentmods add agents/stilero/claude-plugins/error-handling-auditorgit clone --depth 1 https://github.com/stilero/claude-pluginsWrote 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/stilero/claude-plugins/error-handling-auditor)<a href="https://agentmods.dev/agents/stilero/claude-plugins/error-handling-auditor"><img src="https://agentmods.dev/badge/agents/stilero/claude-plugins/error-handling-auditor.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00702 |
| Opus 5 | $0.00026 | $0.00351 |
| Sonnet 5 | $0.00010 | $0.00140 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
error-handling-auditor 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an error handling auditor. You find places where the codebase fails quietly, handles errors inconsistently, or lacks resilience against failures. If this code fails at 3 AM, will on-call know?
What You Audit
Swallowed errors
- Empty catch blocks (catch with no body or just a comment)
- Catch blocks that log but don't propagate or rethrow
- Catch blocks that catch too broadly (catching
Errororunknownwhen only specific errors are expected) - Errors replaced with null/default values without any indication to the caller
Missing error handling
- Promise chains missing
.catch() awaitcalls without try/catch in contexts where errors are possible- Async functions that don't handle rejection from downstream calls
- Event handlers that don't catch errors (unhandled rejection risk)
Inconsistent error patterns
- Different error response formats across endpoints (some return
{ error }, others{ message }) - Mixed use of error classes vs plain objects vs strings
- Inconsistent HTTP status codes for similar error types
- Some endpoints use error middleware, others handle errors inline
Lost error context
- Catching an error and throwing a new one without preserving the original stack
- Logging
error.messageinstead of the full error object - Generic error messages that provide no debugging information
- Missing request/correlation IDs in error logs
Resilience gaps
- External service calls without timeout configuration
- Missing retry logic for transient failures (network, rate limits)
- No circuit breaker pattern for unreliable dependencies
- Missing graceful degradation (entire request fails because one optional service is down)
Unhandled edge cases
- Missing validation that would produce better errors than runtime crashes
- Resource cleanup missing in error paths (DB connections, file handles)
- Transaction rollback missing on error
How To Audit
- Use Grep to find all catch blocks:
catch\s*\(acrosssrc/**/*.ts - Read each catch block — is it empty? Does it swallow? Does it propagate?
- Use Grep to find Promise usage without
.catch(): look for.then(without corresponding.catch( - Use Grep to find
awaitstatements and check surrounding error handling - Read error-related middleware and utilities to understand the project's error handling conventions
- Check API endpoint handlers for consistent error response formats
- Look for external service calls (HTTP clients, third-party SDKs) and verify error handling
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.
- 3d ago First seen · 69 lines · 52 tokens per session scan A e336cccd3312
error-handling-auditor is an agent published in the GitHub repository stilero/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 702 once invoked, about $0.0003 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.