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 rockscy/solo-skills --skill bug-from-usergit clone --depth 1 https://github.com/rockscy/solo-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/rockscy/solo-skills/bug-from-user)<a href="https://agentmods.dev/skills/rockscy/solo-skills/bug-from-user"><img src="https://agentmods.dev/badge/skills/rockscy/solo-skills/bug-from-user/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/rockscy/solo-skills/bug-from-user"><img src="https://agentmods.dev/badge/skills/rockscy/solo-skills/bug-from-user.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00060 | $0.01164 |
| Opus 5 | $0.00030 | $0.00582 |
| Sonnet 5 | $0.00012 | $0.00233 |
| Haiku 4.5 | $0.00006 | $0.00116 |
Grade A, and why
bug-from-user 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug from User / 用户反馈转 Bug
When to use
- A user has reported a problem in prose (email, Discord, Twitter DM, support ticket).
- The dev cannot tell from the message:
- what was expected vs. what actually happened
- the steps to reproduce
- whether it's a real bug, user error, or a feature request in disguise
- The dev wants a GitHub issue or internal note they can later sit down and fix.
When NOT to use
- The user has already produced a clean, reproducible report. Don't re-process it.
- The complaint is subjective ("it's slow", "it's ugly") with no measurable claim — that's a UX or perf investigation, not a bug.
- The user is asking for a feature (e.g. "can you add X?") — file as feature request, not bug.
The four-question conversion
For any prose complaint, reduce it to:
- Trigger — what did the user do (action, click, command, input)?
- Expected — what did they expect to happen?
- Actual — what actually happened?
- Surface — where did it happen (URL, screen, version, browser, OS)?
If any of the four is missing, flag it as a follow-up question rather than guessing.
Output format
### Bug: <one-sentence headline, user-perspective>
**Trigger:**
1. <step>
2. <step>
**Expected:** <what they expected>
**Actual:** <what actually happened>
**Surface:** <version / browser / OS / URL>
**Confidence:** <high | medium | low>
- high: report is self-contained, can repro from this alone
- medium: 1–2 reasonable assumptions made
- low: significant guessing — ask user to confirm
**Follow-ups (if any):**
- <question to ask the user>
Worked example
Input (raw user email):
"hey i tried buying the pro plan tonight and the website just kept loading forever, i refreshed a few times then gave up. using safari on my macbook"
Output:
### Bug: Pro plan checkout hangs on Safari (macOS)
**Trigger:**
1. Visit pricing page on Safari (macOS).
2. Click "Pro plan" purchase button.
3. Observe checkout flow.
**Expected:** Stripe checkout opens within a few seconds.
**Actual:** Page stays in loading state indefinitely; refresh does not recover.
**Surface:** Safari on macOS. Version of Safari and macOS unknown. Pricing page URL unknown (likely /pricing).
**Confidence:** medium
- Assumed pricing page URL is /pricing.
- Assumed checkout uses Stripe.
**Follow-ups:**
- Which Safari version + macOS version?
- Does Chrome on the same machine reproduce it?
- Browser console errors (if comfortable opening DevTools)?
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.
- 9d ago First seen · 149 lines · 60 tokens per session scan A 10eb5b63649e
bug-from-user is a skill published in the GitHub repository rockscy/solo-skills (8 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 1,164 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 2026-08-31.
Other skills, from other repositories
error-translator
A Chinese-language assistant that translates English programming errors and explains what they mean. It covers common errors from languages and frameworks including Python, JavaScript, TypeScript, Java, and others.
eslint-fix
A project-aware assistant for finding and fixing ESLint errors, warnings, and configuration compatibility problems. ESLint is a tool that checks JavaScript and TypeScript code for style and common mistakes.
perf-profiler
A performance investigation guide that uses repeatable measurements and profiling evidence to find where software spends time or resources. Profiling records runtime activity such as CPU use, memory use, database work, or network delays.
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.
tool-calling-tutor
Use when a tool-calling agent does not call a tool, sends wrong arguments, loops without stopping, or needs a function schema. Guides a four-branch diagnosis and five-step schema repair. Do not use for framework-specific, MCP-server, or production-observability questions.
dep-auditor
A read-only audit of a project’s third-party packages for known security issues, version health, and license facts. It uses the versions actually selected by lockfiles, which record the exact packages installed, rather than relying only on version ranges.