veryfront-code: Skill for Claude Code

.claude/skills/vf-error-handling/SKILL.md

vf-error-handling is a skill for Claude Code from veryfront/veryfront-code. It costs 30 tokens per session (1,058 once invoked), scanned A, original, Apache-2.0.

A guide to Veryfront’s shared error system, where errors are defined in a central registry and identified by stable text labels called slugs. It covers creating, throwing, and catching these project-specific errors.

In plain words
What is it for?
Use it when adding errors, changing error classes, or handling failures in Veryfront. It explains how to define error details such as category, HTTP status, title, suggestion, context, and cause.
Why use it?
A common error format makes failures easier to identify, classify, expose to users, and connect to their original cause. It also prevents inconsistent raw errors from spreading through the codebase.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is veryfront/veryfront-code's own configuration. It tells Claude Code how to work on veryfront-code itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything veryfront-code configures →

Reuse

Borrowing it

Nothing to install: this file belongs to veryfront/veryfront-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/veryfront/veryfront-code/main/.claude/skills/vf-error-handling/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/veryfront/veryfront-code

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 vf-error-handling

README.md
[![agentmods](https://agentmods.dev/badge/skills/veryfront/veryfront-code/vf-error-handling/github.svg)](https://agentmods.dev/skills/veryfront/veryfront-code/vf-error-handling)
Your own site
<a href="https://agentmods.dev/skills/veryfront/veryfront-code/vf-error-handling"><img src="https://agentmods.dev/badge/skills/veryfront/veryfront-code/vf-error-handling/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 vf-error-handling

Your own site · 80×15
<a href="https://agentmods.dev/skills/veryfront/veryfront-code/vf-error-handling"><img src="https://agentmods.dev/badge/skills/veryfront/veryfront-code/vf-error-handling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,058 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00030 $0.01058
Opus 5.5 $0.00012 $0.00423
Sonnet 5.5 $0.00006 $0.00212
Haiku 4.5 $0.00003 $0.00106

Measured 2mo ago against content hash 8ef54cba13ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vf-error-handling 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 2mo 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.

.claude/skills/vf-error-handling/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Veryfront Error Handling

Overview

Veryfront uses a centralized error registry with slug-based identification. All errors extend VeryfrontError and are created via defineError().

Core principle: Never throw raw Error. Use the registry. Never identify errors by class name. Use slugs.

Error Registry Pattern

Defining New Errors

// In src/errors/error-registry.ts
import { defineError } from "./types.ts";

export const MY_NEW_ERROR = defineError({
  slug: "my-new-error",           // kebab-case, unique
  category: "RUNTIME",            // CONFIG | BUILD | RUNTIME | ROUTE | MODULE | SERVER | BOUNDARY | DEV | DEPLOY | AGENT | GENERAL
  status: 500,                    // default HTTP status
  title: "Something went wrong",  // human-readable
  suggestion: "Try doing X instead", // actionable fix
});

Throwing Errors

import { MY_NEW_ERROR } from "#veryfront/errors";

throw MY_NEW_ERROR.create({
  detail: "Specific description of what happened",
  context: { key: "value", relevantData: data },
  cause: originalError,  // optional: chain the original error
});

Catching Errors

import { VeryfrontError } from "#veryfront/errors";

try {
  riskyOperation();
} catch (error) {
  if (error instanceof VeryfrontError && error.slug === "my-new-error") {
    // Handle specific error
    console.log(error.context.relevantData);
  }
  throw error; // Re-throw unknown errors
}

Migrating Class-Based Errors to Registry

When replacing class FooError extends Error:

Step 1: Define in Registry

// src/errors/error-registry.ts
export const FOO_ERROR = defineError({
  slug: "foo-error",
  category: "RUNTIME",
  status: 500,
  title: "Foo operation failed",
  suggestion: "Check the foo configuration",
});

Step 2: Update Usage Sites

// Before
throw new FooError("something failed", { details: data });

// After
throw FOO_ERROR.create({
  detail: "something failed",
  context: { details: data },
});

Read the full file on GitHub · 153 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. 2mo ago First seen · 153 lines · 30 tokens per session scan A 8ef54cba13ad

Subscribe to this mod's changes

vf-error-handling is a skill published in the GitHub repository veryfront/veryfront-code (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 1,058 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Related

vf-error-handling compared with skills from other repositories

vf-error-handling next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
vf-error-handlingveryfront/veryfront-codeSkill20yesterdayApache-2.0A30Claude Code
investigateAbyssCN/oh-my-dagSkill4426d agoMITA77Claude Code, Codex
bugfix-triageAbyssCN/oh-my-dagSkill4426d agoMITA37Claude Code, Codex
typescript-testingComposioHQ/composioSkill31kyesterdayMITA92Claude Code, Codex
cli-e2eComposioHQ/composioSkill31kyesterdayMITA62Claude Code, Codex
ios-simulatorcallstack/agent-deviceSkill5.3kyesterdayMITA69Claude Code, Codex
cvm-ai-doctorTencentCloud/OctopSkill12kyesterdayMITA70Claude Code, Codex