defect-lifecycle-manager

defect-lifecycle-manager is a skill for Claude Code, Codex from javalenciacai/QASkills. It costs 32 tokens per session (1,665 once invoked), scanned A, original, MIT.

A skill for tracking software defects from discovery through assignment, fixing, verification, and closure. It also covers root-cause analysis, trend metrics, and quality reporting.

In plain words
What is it for?
Use it to write complete defect reports, manage statuses, analyze recurring problems, verify fixes, report quality, and prevent the same defect from returning.
Why use it?
It prevents bugs from being lost between discovery and release and makes it clear whether a fix has actually been checked.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to write complete defect reports, manage statuses, analyze recurring problems, verify fixes, report quality, and prevent the same defect from returning.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/javalenciacai/qaskills/defect-lifecycle-manager
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 javalenciacai/QASkills --skill defect-lifecycle-manager
Clone the repo
git clone --depth 1 https://github.com/javalenciacai/QASkills

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 defect-lifecycle-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/javalenciacai/qaskills/defect-lifecycle-manager/github.svg)](https://agentmods.dev/skills/javalenciacai/qaskills/defect-lifecycle-manager)
Your own site
<a href="https://agentmods.dev/skills/javalenciacai/qaskills/defect-lifecycle-manager"><img src="https://agentmods.dev/badge/skills/javalenciacai/qaskills/defect-lifecycle-manager/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.

agentmods 80×15 button for defect-lifecycle-manager

Your own site · 80×15
<a href="https://agentmods.dev/skills/javalenciacai/qaskills/defect-lifecycle-manager"><img src="https://agentmods.dev/badge/skills/javalenciacai/qaskills/defect-lifecycle-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,665 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 $0.00032 $0.01665
Opus 5 $0.00016 $0.00833
Sonnet 5 $0.00006 $0.00333
Haiku 4.5 $0.00003 $0.00167

Measured 9d ago against content hash d5f7e8e1ce0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

defect-lifecycle-manager 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.

.agents/skills/defect-lifecycle-manager/SKILL.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Defect Lifecycle Manager

Expert skill for managing defects throughout their lifecycle and tracking quality metrics.

When to Use

Use this skill when you need to:

  • Log new defects with complete information
  • Track defect status and lifecycle
  • Analyze defect trends and metrics
  • Conduct root cause analysis
  • Report quality status to stakeholders
  • Verify defect fixes
  • Prevent defect recurrence

Defect Lifecycle States

NEW → ASSIGNED → IN PROGRESS → RESOLVED → VERIFIED → CLOSED
                                    ↓
                                REOPENED (if verification fails)

State Definitions

NEW: Just logged, awaiting triage ASSIGNED: Assigned to developer IN PROGRESS: Developer actively working RESOLVED: Fix completed, ready for verification VERIFIED: QA confirmed fix works CLOSED: Accepted and archived REOPENED: Fix didn't work, back to dev

Defect Logging Standards

Complete Defect Report

Defect ID: [Auto-generated or manual]
Title: [Action] + [Component] + [Unexpected Behavior]
  Example: "Login button does not respond on mobile Chrome"

Type: [Functional/UI/Performance/Security/Data/Integration]
Severity: [Critical/High/Medium/Low]
Priority: [P0/P1/P2/P3]

Reported By: [Name]
Date Reported: [Date]
Detected In: [Environment]
Build/Version: [x.y.z]

Environment Details:
- OS: [Platform + version]
- Browser/Device: [Details]
- Network: [WiFi/Mobile/etc]

Preconditions:
[System state before reproduction]

Steps to Reproduce:
1. [Exact action]
2. [Exact action]
3. [Exact action]

Expected Result:
[What should happen per requirements]

Actual Result:
[What actually happened]

Reproducibility: [Always / Intermittent (X out of Y attempts)]

Impact:
[Who is affected? How many users? What's blocked?]

Attachments:
- Screenshot: [filename]
- Error log: [filename]
- Video: [filename]
- Network trace: [filename]

Additional Context:
- Related defects: [Links]
- Related requirements: [Links]
- Workaround: [If available]

Read the full file on GitHub · 303 lines

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. 9d ago First seen · 303 lines · 32 tokens per session scan A d5f7e8e1ce0f

Subscribe to this mod's changes

defect-lifecycle-manager is a skill published in the GitHub repository javalenciacai/QASkills (5 stars, last pushed 7mo ago), licensed MIT. It adds 32 tokens to every session and 1,665 once invoked, about $0.0002 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.

Related

Other skills, from other repositories