debug

A systematic debugging guide for command-line tools, terminal interfaces, extensions, and MCP servers. It requires investigating the cause of a bug before suggesting a fix.

In plain words
What is it for?
Use it when a test fails, a bug appears, or software behaves unexpectedly, to reproduce the issue, find its root cause, compare working examples, and then plan a fix.
Why use it?
It helps avoid trial-and-error patches that hide the real problem or create new ones. The process uses reproduction, logs, recent changes, and data-flow tracing.

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/joshsmithxrm/power-platform-developer-suite/debug
Any agent
npx skills add joshsmithxrm/power-platform-developer-suite --skill debug
Clone the repo
git clone --depth 1 https://github.com/joshsmithxrm/power-platform-developer-suite

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,025 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 $0.00028 $0.02025
Opus 5 $0.00014 $0.01012
Sonnet 5 $0.00006 $0.00405
Haiku 4.5 $0.00003 $0.00202

Measured 2d ago against content hash ba1d8f71f64c, 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.

.claude/skills/debug/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug

Systematic debugging for CLI, TUI, Extension, and MCP development. Combines interactive feedback loops with disciplined root-cause analysis.

The Iron Law

NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.

If you have not completed Phase 1 (Root Cause Investigation), you cannot propose fixes. Period. Skipping this is the single most common source of thrashing, wasted time, and user frustration.

Four Phases (Required Sequence)

Phase 1: Root Cause Investigation

Before touching any code:

  1. Read error messages carefully — the full message, not just the first line
  2. Reproduce consistently — if you can't reproduce it, you can't fix it
  3. Check recent changesgit diff and git log for what changed since it last worked
  4. Gather evidence at component boundaries — logs, network calls, RPC responses, console output
  5. Trace data flow backward — start from the symptom, trace back through the call chain to find the original trigger

Do NOT skip this phase. Do NOT propose "quick fixes" during this phase.

Phase 2: Pattern Analysis

  1. Find working examples in the codebase — how do similar features handle this?
  2. Compare against references — what does the working version do differently?
  3. Identify differences — the bug is in the delta between working and broken

Phase 3: Hypothesis Testing

  1. Form a single hypothesis — "The bug is caused by X because of evidence Y"
  2. Test with the smallest possible change — one variable at a time
  3. If it doesn't work, form a NEW hypothesis — do NOT stack fixes on top of failed attempts
  4. Revert failed attempts before trying the next hypothesis

Phase 4: Implementation

  1. Create a failing test case that reproduces the bug
  2. Implement a single fix at the root cause (not at the symptom)
  3. Verify the fix — the test passes, the original error is gone
  4. If 3+ fixes have failed, STOP — see the escalation rule below

3-Fix Escalation Rule

Read the full file on GitHub · 219 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 · 219 lines · 28 tokens per session scan A ba1d8f71f64c

Subscribe to this mod's changes

debug is a skill published in the GitHub repository joshsmithxrm/power-platform-developer-suite (5 stars, last pushed 8d ago), licensed MIT. It adds 28 tokens to every session and 2,025 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 2026-08-31.

Related

Other skills, from other repositories

PowerAppsControl

Drive the PowerAppsControl MCP server to UX-test a Power App end to end: open and verify an app URL, let the user choose a mode (smoke test = in-depth read-only exploration that produces a repeatable natural-language test plan; or run my test plan), then run it in a recorded session and produce a video + HTML report…

ilyafainberg/PowerAppsControl · 177 tokens

xrm-mcp

Skip steps you already have answers for. If you ran listtables or describetable earlier in the session, reuse those results.

jukkan/xrm-mcp · 0 tokens

run-integration-tests

Build, pack, and run .NET MAUI integration tests locally. Validates templates, samples, and end-to-end scenarios using the local workload.

dotnet/maui · 35 tokens

run-helix-tests

Submit and monitor .NET MAUI unit tests on Helix infrastructure. Supports running XAML, Resizetizer, Core, Essentials, and other unit test projects on distributed Helix queues.

dotnet/maui · 45 tokens

mpg-migration

Handles Azure SDK for .NET management-plane migrations from AutoRest/Swagger to TypeSpec; use for MPG, mgmt migration, or Azure.ResourceManager. migration requests.

Azure/azure-sdk-for-net · 39 tokens

refresh-arm-sdk-release

WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…

Azure/azure-sdk-for-net · 91 tokens