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 latestaiagents/agent-skills --skill bug-reportinggit clone --depth 1 https://github.com/latestaiagents/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/latestaiagents/agent-skills/bug-reporting)<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/bug-reporting"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/bug-reporting/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/latestaiagents/agent-skills/bug-reporting"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/bug-reporting.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 | $0.00053 | $0.01770 |
| Opus 5.5 | $0.00021 | $0.00708 |
| Sonnet 5.5 | $0.00011 | $0.00354 |
| Haiku 4.5 | $0.00005 | $0.00177 |
Grade A, and why
bug-reporting 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 1mo 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Reporting
Write clear, actionable bug reports that get fixed faster.
When to Use
- Reporting a new bug
- Improving existing bug reports
- Training team on bug reporting
- Setting up bug templates
- Triaging and prioritizing issues
Bug Report Template
## Bug: [Clear, descriptive title]
**ID:** BUG-[number]
**Reporter:** [Name]
**Date:** [Date]
### Severity & Priority
- **Severity:** Critical / High / Medium / Low
- **Priority:** P0 / P1 / P2 / P3
### Environment
- **OS:** [e.g., macOS 14.1, Windows 11]
- **Browser:** [e.g., Chrome 120.0.6099]
- **App Version:** [e.g., 2.3.1]
- **Environment:** [Production / Staging / Dev]
- **Device:** [Desktop / Mobile / Tablet]
### Description
[1-2 sentences describing what's wrong]
### Steps to Reproduce
1. [First step]
2. [Second step]
3. [Third step]
4. [Continue until bug occurs]
### Expected Result
[What should happen]
### Actual Result
[What actually happens]
### Evidence
- Screenshot: [attachment]
- Video: [link]
- Console logs: [attachment]
- Network logs: [attachment]
### Additional Context
- Frequency: [Always / Sometimes / Rarely]
- Workaround: [If any]
- Related issues: [Links]
### Technical Notes (if known)
- Error message: [exact text]
- Stack trace: [if available]
- Related code: [file/function if known]
Example Bug Reports
Good Bug Report
## Bug: Checkout fails with "undefined" error when applying discount code
**ID:** BUG-1234
**Reporter:** Jane Smith
**Date:** 2026-02-05
### Severity & Priority
- **Severity:** High (blocks purchases)
- **Priority:** P1
### Environment
- **OS:** macOS 14.2
- **Browser:** Chrome 121.0.6167.85
- **App Version:** 3.2.0
- **Environment:** Production
### Description
When applying a valid discount code at checkout, the page shows an "undefined" error and prevents order completion.
### Steps to Reproduce
1. Add any item to cart
2. Go to checkout (/checkout)
3. Enter discount code "SAVE20"
4. Click "Apply"
5. Error appears, "Apply" button becomes disabled
### Expected Result
- Discount of 20% applied to order total
- Updated total displayed
- User can proceed to payment
### Actual Result
- Red error message: "Error: undefined"
- Apply button grayed out
- Cannot proceed with checkout
- Must refresh page to continue (without discount)
### Evidence
- Screenshot: [checkout-error.png]
- Console error: `TypeError: Cannot read property 'value' of undefined at applyDiscount (checkout.js:142)`
- Network: POST /api/discounts returns 200 with valid response
### Additional Context
- Frequency: Always (100% reproducible)
- Workaround: Complete checkout without discount code
- Started after deploy on 2026-02-04
- Works correctly on staging environment
### Technical Notes
- Error in checkout.js:142
- Appears to be missing null check on discount response
- Related PR: #1456 (discount feature)
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.
- 1mo ago First seen · 302 lines · 53 tokens per session scan A 3499e115f55e
bug-reporting is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 53 tokens to every session and 1,770 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
ai-critique
A general diagnosis assistant for product, operations, technical, and software work. It analyzes supplied material and produces a summary, conclusions, action suggestions, and reusable deliverables.
ai-equipment-failure-rca-draft
A root-cause analysis draft assistant for investigating equipment failures. Root-cause analysis means looking for the underlying reason a failure happened, not only its visible symptom.
ai-performance
A performance diagnosis assistant for finding what may be slowing a service or product down.
ai-quality-complaint-8d-report
A business-diagnosis assistant for creating or reviewing an 8D report. An 8D report is a structured method for investigating a quality problem and documenting corrective action.
nexent-daily-test
A procedure for running Nexent daily, full-layer tests on a self-hosted Ubuntu machine. Nexent is tested across separate layers such as unit, service, AI runtime, and browser journeys, with results and evidence kept locally.
moai-lane-watchdog
One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…