mcp-ratchet: Skill for Windsurf

.windsurf/skills/error-handling/SKILL.md

error-handling is a skill for Windsurf from hexxla/mcp-ratchet. It costs 10 tokens per session (141 once invoked), scanned A, original, MIT.

A code-review and coding guide for handling errors in Go programs.

In plain words
What is it for?
Use it to review error checks, wrapping with %w, errors.Is and errors.As, custom error types, early returns, and error propagation.
Why use it?
It helps prevent ignored errors and makes failures easier to understand, compare, wrap, and pass through the program.

Skill for Windsurf

Written for Windsurf: installed under .windsurf/.

This is hexxla/mcp-ratchet's own configuration. It tells Windsurf how to work on mcp-ratchet 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 mcp-ratchet configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hexxla/mcp-ratchet. 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/hexxla/mcp-ratchet/main/.windsurf/skills/error-handling/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hexxla/mcp-ratchet

Made for: Windsurf.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/hexxla/mcp-ratchet/error-handling"><img src="https://agentmods.dev/badge/skills/hexxla/mcp-ratchet/error-handling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 141 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 $0.00010 $0.00141
Opus 5 $0.00005 $0.00071
Sonnet 5 $0.00002 $0.00028
Haiku 4.5 $0.00001 $0.00014

Measured 9d ago against content hash c0b95322cd57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 9d 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.

.windsurf/skills/error-handling/SKILL.md · 20 lines

What it actually says

Go Error Handling Skill

When reviewing or writing Go code:

  • Ensure all errors are checked and not ignored
  • Validate error wrapping with %w for context preservation
  • Check that error messages are informative and actionable
  • Recommend using errors.Is and errors.As for error comparison
  • Ensure errors are returned early when possible (fail fast)
  • Validate error types are appropriate for the domain
  • Check for proper error propagation through the call stack
  • Avoid returning wrapped errors at package boundaries
  • Use custom error types for domain-specific errors
  • Ensure error variables are exported for use by callers
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. 9d ago First seen · 20 lines · 10 tokens per session scan A c0b95322cd57

Subscribe to this mod's changes

error-handling is a skill published in the GitHub repository hexxla/mcp-ratchet (2 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 141 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.