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 shennawardana23/skillme --skill bug-triage-and-severity-classificationgit clone --depth 1 https://github.com/shennawardana23/skillmeWrote 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/shennawardana23/skillme/bug-triage-and-severity-classification)<a href="https://agentmods.dev/skills/shennawardana23/skillme/bug-triage-and-severity-classification"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/bug-triage-and-severity-classification/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/shennawardana23/skillme/bug-triage-and-severity-classification"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/bug-triage-and-severity-classification.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 | $0.00099 | $0.01145 |
| Opus 5 | $0.00049 | $0.00573 |
| Sonnet 5 | $0.00020 | $0.00229 |
| Haiku 4.5 | $0.00010 | $0.00114 |
Grade A, and why
bug-triage-and-severity-classification 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 11d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Triage and Severity Classification
Severity and priority are two different axes, and conflating them is the single most common triage mistake. Getting this right determines whether the right bug gets fixed at 2am versus next sprint.
Severity vs. Priority — they are orthogonal
- Severity = objective technical/business impact if the bug is not fixed. Does not change based on who reported it or how busy the team is.
- Priority = how soon it gets worked, given everything else in flight. Business context can shift this independently of severity.
A bug can be high severity, low priority (data corruption in a feature used by one deprecated internal tool nobody touches this quarter) or low severity, high priority (a cosmetic logo glitch on the page the CEO is demoing to investors tomorrow). Both axes are legitimate; neither should be inflated to force the other's outcome — inflating severity to jump the queue burns the taxonomy's credibility for the next real Sev1.
The Sev1-4 / P0-P3 taxonomy
This is the industry-common shape (used in variants by Google, PagerDuty, Atlassian, and most on-call rotations):
| Severity | Definition | Example | Typical response SLA |
|---|---|---|---|
| Sev1 / P0 | Full outage, data loss, security breach, or revenue-blocking failure in production | Booking engine can't process any reservations; payment data exposed | Page on-call immediately, respond in minutes |
| Sev2 | Major functionality broken or badly degraded for a significant user subset, no workaround | Rate calculation wrong for one hotel brand; search returns errors for 20% of queries | Same business day, often within hours |
| Sev3 | Minor functionality broken, workaround exists, limited blast radius | A filter on a report page doesn't persist; one edge case in date formatting | Next sprint / few business days |
| Sev4 / P3 | Cosmetic, typo, or negligible impact | Misaligned button, wrong icon color | Backlog, best-effort |
Exact SLA numbers vary by org — the point of the taxonomy is that everyone agrees on what the four buckets mean, so the SLA table can be applied mechanically instead of debated per-ticket.
What ships with it
1 file 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.
- 11d ago First seen · 92 lines · 99 tokens per session scan A e42b6ad3a78c
bug-triage-and-severity-classification is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 99 tokens to every session and 1,145 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
ego-lite-simplify
Find and implement evidence-backed simplifications in the ego-lite repository. Use when reviewing the codebase for dead code, duplicated state or APIs, speculative abstractions, unnecessary compatibility layers, hand-written infrastructure, excessive tests or documentation, or when the user asks to reduce code size or…
coding-protocol
Risk-scaled repo execution and code-evidence protocol. Skip architecture-only work, explanation, contract-preserving prose, and status. Use for contract changes, debugging, code review, implementation plans, and Git mutation; mixed tasks: only those parts.
fix-bug
Resolves a single bug from any starting evidence — Dash0 telemetry (span / log / web event / RUM error link), raw stack trace, error message, code pointer (file:line), screen recording, Linear ticket URL, or free-text symptom. Classifies the input, triages complexity (Phase 0.5) to pick between a fast lane and a full…
holistic-analysis
Forces a full holistic re-analysis when a fix or refactor isn't working. Instead of continuing to patch in isolation, this skill triggers a structured step-back analysis that traces the entire execution path end-to-end — from entry point to exit — analyzing each block, every contract boundary, and the full data flow.…
ci-auto-fix
Diagnoses a failed CI check, classifies it with an explicit verdict (code-bug | workflow-bug | dep-bug | env-bug | flaky | unsure), confidence-gates the fix (>=90 auto, 80-89 ask, <80 escalate), applies it, pushes, and iteratively verifies until CI passes — reverting the last commit if a brand-new failure appears.…