Bug Triage

Bug Triage is a skill for Claude Code, Codex from Xiaowen-Jiang/agent-enterprise. It costs 18 tokens per session (432 once invoked), scanned A, original, MIT.

A structured process for investigating a reported software bug, judging its urgency, finding its root cause, and suggesting a fix.

In plain words
What is it for?
Use it to classify bugs from critical to minor, trace the relevant code, describe reproduction steps, and recommend a fix with effort and regression risk.
Why use it?
It separates the visible symptom from the underlying code problem and shows what other parts of the software may be affected.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to classify bugs from critical to minor, trace the relevant code, describe reproduction steps, and recommend a fix with effort and regression risk.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xiaowen-jiang/agent-enterprise/bug_triage
Install

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.

Any agent
npx skills add Xiaowen-Jiang/agent-enterprise --skill bug_triage
Clone the repo
git clone --depth 1 https://github.com/Xiaowen-Jiang/agent-enterprise

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for Bug Triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiaowen-jiang/agent-enterprise/bug_triage.svg)](https://agentmods.dev/skills/xiaowen-jiang/agent-enterprise/bug_triage)
Your own site
<a href="https://agentmods.dev/skills/xiaowen-jiang/agent-enterprise/bug_triage"><img src="https://agentmods.dev/badge/skills/xiaowen-jiang/agent-enterprise/bug_triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 432 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00432
Opus 5 $0.00009 $0.00216
Sonnet 5 $0.00004 $0.00086
Haiku 4.5 $0.00002 $0.00043

Measured 8d ago against content hash 7464b7cfe142, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Bug Triage 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 8d 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.

agent_enterprise/skills_data/bug_triage/SKILL.md · 54 lines

What it actually says

Process

  1. Understand the bug report — What was expected? What happened instead?
  2. Read related code — Find the code path where the bug occurs
  3. Reproduce mentally — Trace the execution flow to understand why the bug happens
  4. Classify severity:
    • P0 (Critical): Data loss, security vulnerability, complete feature broken
    • P1 (High): Major feature degraded, no workaround
    • P2 (Medium): Feature partially broken, workaround exists
    • P3 (Low): Cosmetic issue, minor inconvenience
  5. Identify root cause — The actual code/logic error, not just symptoms
  6. Assess blast radius — What else could be affected?
  7. Propose fix — Specific code changes with effort estimate

Output Format

## Bug Triage Report

**Severity**: P0/P1/P2/P3
**Component**: [module/file affected]
**Root Cause**: [1-2 sentence explanation]
**Blast Radius**: [what else is affected]

### Reproduction Steps
1. ...

### Proposed Fix
- File: path/to/file.py
- Change: [description of fix]
- Effort: Small (< 1hr) / Medium (1-4hr) / Large (4hr+)

### Regression Risk
[What could break if we fix this incorrectly]

Guidelines

  • Always read the actual code before diagnosing — don't guess
  • Distinguish symptoms from root cause
  • Consider if the bug is a regression (did this work before?)
  • Check for similar patterns elsewhere in the codebase
  • Prioritize data integrity and security bugs above all else
  • Include a test case that would catch this bug
Changes

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.

  1. 8d ago First seen · 54 lines · 18 tokens per session scan A 7464b7cfe142

Subscribe to this mod's changes

Bug Triage is a skill published in the GitHub repository Xiaowen-Jiang/agent-enterprise (52 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 432 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

ce-debug

Diagnosis loop for bugs and failing behavior. Use when asked to debug or fix failing or slow behavior.

EveryInc/compound-engineering-plugin · 23 tokens

ce-sweep

Sweep configured feedback sources (Slack, GitHub Issues; email experimental) for new items: acknowledge at source, analyze recordings, verify fixes merged to main, and emit an lfg-ready plan. First run sets up sources; supports mode:non-interactive for scheduled runs.

EveryInc/compound-engineering-plugin · 62 tokens

ce-riffrec-feedback-analysis

Analyze recorded product feedback into evidence for bugs and requirements. Use when a Riffrec capture or other screen, voice, or notes artifact needs interpretation. Use for Riffrec setup, capture, or sharing help when no recording exists yet.

EveryInc/compound-engineering-plugin · 55 tokens

military-discipline

A strict review and debugging procedure based on checking work, asking for reasons, correcting problems, accepting only verified results, and recording lessons. It is designed as a quality-control process.

linkerlin/PUAX · 18 tokens

data-data-observability

Use this skill when designing data observability: data quality monitoring, data lineage, data profiling, anomaly detection, data health dashboards, freshness checks, row count tracking, schema drift detection, and data incident management. This skill enforces: monitoring all data pipeline stages, automated quality…

j4flmao/agent-skills · 105 tokens

qa-bug-root-cause-analysis

A method for finding the underlying causes of recurring or production bugs using approaches such as asking “why” repeatedly, cause-and-effect diagrams, and fishbone diagrams. It separates immediate, contributing, and system-level causes.

Kokxi/qa-test-skills · 143 tokens