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 skills/vvedantb/eva/write-better-error-messagesnpx skills add vvedantb/eva --skill write-better-error-messagesgit clone --depth 1 https://github.com/vvedantb/evaWrote 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/skills/vvedantb/eva/write-better-error-messages)<a href="https://agentmods.dev/skills/vvedantb/eva/write-better-error-messages"><img src="https://agentmods.dev/badge/skills/vvedantb/eva/write-better-error-messages.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 | $0.00073 | $0.01461 |
| Opus 5 | $0.00036 | $0.00731 |
| Sonnet 5 | $0.00015 | $0.00292 |
| Haiku 4.5 | $0.00007 | $0.00146 |
Grade A, and why
write-better-error-messages 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 5d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Better Error Messages
Use this skill to make error messages specific, calm, accountable, and useful.
Attribution
This skill is adapted from Jenni Nadler's Wix UX article "When life gives you lemons, write better error messages", published by Wix UX. It incorporates the article's guidance and the lessons shown in its annotated screenshots: the bad-message modal, the improved-message modal, the generic-vs-unclear comparison, and the error-inventory board.
Core Test
Before writing or approving an error message, answer:
- What happened?
- Why did it happen, at the most useful level of detail the product can honestly provide?
- What was not affected, if anything needs reassurance?
- What can the user do now?
- What can they do if that does not work?
If the product cannot answer these questions, treat it as a product or engineering gap, not only a copy problem.
Avoid
- Do not use cutesy or casual tone when the stakes are high. Avoid "Oops", "Whoops", "Uh oh", "Yikes", and jokes for flows involving money, publishing, work continuity, account access, data, or user trust.
- Do not blame the user. Focus on the problem and the recovery path.
- Do not blame third parties when the user is operating inside your product. Prefer "We're having trouble connecting to [service]" over "[service] is not responding."
- Do not expose implementation details unless they help the user act. Replace terms like "fetch", "credentials denied", "500", or "unknown exception" with the outcome and next step.
- Do not ship "Something went wrong" when the system knows more. A generic fallback is acceptable only when no specific diagnosis is available, and even then it should include a next step or escape route.
- Do not confuse "specific" with "clear." A message can mention permissions, tokens, scopes, or settings and still be unclear if the user cannot tell what to do.
Prefer
- State the result first: "We couldn't connect your account", "Your image was not uploaded", or "Your changes were saved, but the email was not sent."
- Explain why when possible: "because the file is larger than 25 MB", "because your session expired", or "because of an issue on our end."
- Reassure users about preserved work: "Your draft is saved", "Your billing settings were not changed", or "No one has been invited yet."
- Give a concrete next step: "Try connecting again", "Choose a file under 25 MB", "Sign in again", or "Check that pop-ups are allowed."
- Provide a way out when the user may be blocked: link to support, a help article, retry, cancel, save draft, download data, or contact Customer Care.
- Use "please" sparingly for empathy in serious or unrecoverable situations, not as filler.
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.
- 5d ago First seen · 105 lines · 73 tokens per session scan A 2b9fcd131c1e
write-better-error-messages is a skill published in the GitHub repository vvedantb/eva (101 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 1,461 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…