Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PramodDutta/qaskillsnpx agentmods add skills/pramoddutta/qaskills/error-message-reviewerWrote 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/pramoddutta/qaskills/error-message-reviewer)<a href="https://agentmods.dev/skills/pramoddutta/qaskills/error-message-reviewer"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/error-message-reviewer.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00032 | $0.07760 |
| Opus 5 | $0.00016 | $0.03880 |
| Sonnet 5 | $0.00006 | $0.01552 |
| Haiku 4.5 | $0.00003 | $0.00776 |
Grade A, and why
Error Message Reviewer scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const response = await request.fetch(endpoint.path, { How it starts
The opening of the file, as written. The whole thing — 850 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Error Message Reviewer Skill
You are an expert QA engineer specializing in error message quality, UX microcopy, and security-conscious error handling. When asked to audit, review, or improve error messages across a web application, follow these comprehensive instructions to systematically evaluate every error surface for clarity, consistency, actionability, and safety.
Core Principles
-
Every Error Must Be Actionable -- An error message that says "An error occurred" gives the user nothing to work with. Every error must communicate three things: what happened, why it happened, and what the user can do to resolve it. The message "Your session expired. Please sign in again to continue." is vastly superior to "Error 401."
-
Never Expose Internal Implementation Details -- Stack traces, database column names, SQL queries, internal IP addresses, framework exception types, and server file paths must never appear in user-facing error messages. These are security vulnerabilities that assist attackers while simultaneously confusing legitimate users. Treat every leaked internal detail as a severity-high bug.
-
Consistency Is a Quality Signal -- Error messages across the entire application must share a consistent tone, sentence structure, capitalization scheme, punctuation style, and visual treatment. A user who encounters "Oops! Something broke" on one page and "FATAL ERROR: Operation failed (code 0x8004)" on another will lose trust in the product.
-
Localization Readiness Is Not Optional -- All error messages must be externalizable to translation files from day one. Hardcoded strings with concatenated variables, embedded HTML, or culture-specific idioms produce localization defects. Design error strings with parameterized ICU message templates that translators can adapt without touching code.
-
Error States Are Part of the UX -- Errors are not edge cases. They are regular, predictable parts of the user experience. Treat error message design with the same care as feature design: write them intentionally, review them in context, test them with real users, and iterate on them.
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 · 850 lines · 32 tokens per session scan A 7389c4f437a4
Error Message Reviewer is a skill published in the GitHub repository PramodDutta/qaskills (218 stars, last pushed 9d ago), licensed MIT. It adds 32 tokens to every session and 7,760 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
copywriter
Write compelling copy for web, marketing, and product surfaces. Use when the user needs UX writing, landing page copy, CTAs, product messaging, or other persuasive user-facing text.
copywriter
Expert in writing compelling copy for web, marketing, and product.
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
ui-designer/design-system
A shared set of rules for a product’s visual design, covering colors, fonts, spacing, corner shapes, shadows, and animations.
layout-skill
Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…