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 skills add joshuadavidthomas/agent-skills --skill writing-error-messagesgit clone --depth 1 https://github.com/joshuadavidthomas/agent-skillsWrote 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/joshuadavidthomas/agent-skills/writing-error-messages)<a href="https://agentmods.dev/skills/joshuadavidthomas/agent-skills/writing-error-messages"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/writing-error-messages/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.
<a href="https://agentmods.dev/skills/joshuadavidthomas/agent-skills/writing-error-messages"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/writing-error-messages.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 141 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00068 | $0.01451 |
| Opus 5 | $0.00034 | $0.00726 |
| Sonnet 5 | $0.00014 | $0.00290 |
| Haiku 4.5 | $0.00007 | $0.00145 |
Grade A, and why
writing-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 12d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Error Messages
Quick Start
Before writing, identify:
- Audience: end user, admin, developer, support agent, or operator.
- Failure: what action failed and what still happened successfully.
- Cause: known, unknown, user-correctable, service-side, third-party, or security-sensitive.
- Recovery: what the reader can do now, what the system will do next, and where they can get help.
Then write this shape:
[What happened]
[Reassurance if useful]. [Why it happened, if known and safe]. [Specific next action]. [Backup path if it keeps happening].
Example:
Unable to connect your account
Your changes were saved, but we couldn't connect the account because of an issue on our end. Try connecting again. If this keeps happening, contact support.
Core Rules
| Rule | Do | Avoid |
|---|---|---|
| Say what happened | "We couldn't save your file." | "Something went wrong." |
| Say what was not affected | "Your draft was saved." | Leaving the user to wonder if data was lost |
| Give the next action | "Check the card number and try again." | "OK" / "Close" as the only path |
| Use plain language | "We couldn't connect to Dropbox." | "Fetch failed" / "credentials denied" |
| Avoid blame | "Store name is required." | "You forgot to enter a store name." |
| Match the stakes | Calm, direct, respectful | "Oops!" / jokes / cutesy tone |
| Be specific when safe | "Enter a date in the past." | "Invalid input." |
| Be generic when security requires it | "Invalid email or password." | "That email exists, but the password is wrong." |
Message Anatomy
Use only the pieces the situation needs.
| Piece | Purpose | Pattern |
|---|---|---|
| Title | Summarize the failed action | "Couldn't save changes" |
| Body | Explain consequence and cause | "Your changes are still open, but we couldn't save them because the connection dropped." |
| Primary action | Tell the reader what to do | "Try again", "Update details", "Choose another file" |
| Backup path | Provide a way out | "If this keeps happening, contact support." |
| Diagnostic detail | Help technical readers or support | Error code, request ID, expected/received values, log location |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 167 lines · 68 tokens per session scan A 6e4f6b093abd
writing-error-messages is a skill published in the GitHub repository joshuadavidthomas/agent-skills (49 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,451 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 2026-08-30.
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…