debug

A workflow for finding the cause of a reported bug, error, exception, or unexpected result and applying the smallest suitable fix. It requires loading the relevant project rules before proposing a fix.

In plain words
What is it for?
Investigating and fixing problems in Java 8, Spring 3.2, Hibernate 4.2, SQL, security, JSP, XML, and related project files.
Why use it?
It replaces guesswork with systematic isolation and helps keep a bug fix from introducing unrelated changes or security regressions.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/zexion7873/copilot-setting/debug
Any agent
npx skills add zexion7873/copilot-setting --skill debug
Clone the repo
git clone --depth 1 https://github.com/zexion7873/copilot-setting

Made for: Claude Code, Codex.

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 721 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00074 $0.00721
Opus 5 $0.00037 $0.00360
Sonnet 5 $0.00015 $0.00144
Haiku 4.5 $0.00007 $0.00072

Measured 2d ago against content hash 4c56386219e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug 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 2d 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.

.github/skills/debug/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug — Workflow

Systematic isolation and minimal fix.

Phase 0 — Load canonical rules

MANDATORY pre-load gate — do NOT propose a fix (Phase 6) until you have opened the instruction files for the layers you touch. Your training data defaults to modern Java/Spring; these files are the version lock for Java 8 / Spring 3.2 / Hibernate 4.2. Open them first, every time — the negative lists in the agent body are a floor, not the full rules:

  • instructions/java.instructions.md — Java 8 language boundary
  • instructions/spring-hibernate.instructions.md — Spring 3.2 + Hibernate 4.2
  • instructions/sql.instructions.md — SQL injection, indexing, JDBC resources
  • instructions/sql-ddl.instructions.md — MySQL DDL & migration safety, stored procedures
  • instructions/security.instructions.md — OWASP Top 10 (a bug fix can regress a security control — XSS, IDOR, injection)

Read-back receipt (self-check, not machine-enforced): before leaving this step, NAME each instruction file you opened above and QUOTE the single most load-bearing rule from each that applies to this change — a generic restatement you could have written from memory means you skipped the file, so open it for real.

Phase 1 — Define the Problem

Expected:      <what should happen>
Actual:        <what actually happens>
Error/Trace:   <exact message, not paraphrased>
Reproducible:  always / sometimes / once
Since when:    recent change / always / unknown

Phase 2 — Gather Evidence

Read stack trace bottom-up — first line in YOUR code is the entry point. Check recent git changes in the affected area.

Phase 3 — Form Hypotheses

List ≥ 3 candidate causes before ranking — never investigate the first hypothesis without listing alternatives. For each: what confirms it, what refutes it, effort to verify. Verify lowest-effort hypothesis first.

Phase 4 — Isolate

Binary search on execution path: entry → failure point → check midpoint → narrow until divergence is one line.

Phase 5 — Verify Root Cause

Read the full file on GitHub · 64 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. 2d ago First seen · 64 lines · 74 tokens per session scan A 4c56386219e7

Subscribe to this mod's changes

debug is a skill published in the GitHub repository zexion7873/copilot-setting (1 stars, last pushed 29d ago), licensed MIT. It adds 74 tokens to every session and 721 once invoked, about $0.0004 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

jira-cli

Interact with Jira from the command line to create, list, view, edit, and transition issues, manage sprints and epics, and perform common Jira workflows. Use when the user asks about Jira tasks, tickets, issues, sprints, or needs to manage project work items.

Code-and-Sorts/awesome-copilot-agents · 60 tokens

azure-prices

Look up and compare Azure service pricing using the Azure Retail Prices API. Use this skill whenever the user asks about Azure costs, pricing, rates, or wants to compare prices across regions or services — even if they don't say "pricing" explicitly. Trigger for questions like "how much does a D2 v2 VM cost?"…

Code-and-Sorts/awesome-copilot-agents · 90 tokens

calculator

Performs arbitrary-precision arithmetic calculations including addition, subtraction, multiplication, division, and exponents. Use when the user asks to calculate, compute, or evaluate math expressions, or when precise decimal arithmetic is needed to avoid floating-point errors.

Code-and-Sorts/awesome-copilot-agents · 50 tokens

az-cli

Use the Azure CLI (az) to manage Azure resources from the command line. Trigger this skill whenever the user asks to create, configure, manage, deploy, or interact with any Azure resource — even if they don't explicitly mention "az cli". Also trigger when the user asks about Azure CLI commands, syntax, or wants to…

Code-and-Sorts/awesome-copilot-agents · 79 tokens

plan-task

Create a detailed implementation plan before coding. Use when starting a new feature, multi-step refactor, or complex task. Invoked by saying "plan", "create a plan", or "plan this task".

savedpixel/ai-agent-rules-generator · 45 tokens

commit

Stage, commit, and push code changes with branch safety and explicit staging. Use when ready to commit work. Invoked by saying "commit", "push", or "commit and push".

savedpixel/ai-agent-rules-generator · 40 tokens