pwp-debug

A step-by-step method for finding the cause of software bugs, errors, crashes, and unexpected behavior.

In plain words
What is it for?
Use it when software is broken or failing and you need to determine what triggers the problem and confirm that a change resolves it.
Why use it?
It replaces guesswork with a process that reproduces the problem, examines the full error, isolates the cause, and verifies the fix.

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/shandar/pwp-plugin/pwp-debug
Any agent
npx skills add shandar/pwp-plugin --skill pwp-debug
Clone the repo
git clone --depth 1 https://github.com/shandar/pwp-plugin

Made for: Claude Code, Codex.

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,123 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 $0.00090 $0.01123
Opus 5 $0.00045 $0.00562
Sonnet 5 $0.00018 $0.00225
Haiku 4.5 $0.00009 $0.00112

Measured yesterday against content hash 31461ce131a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pwp-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 yesterday.

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.

skills/pwp-debug/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging Skill

This skill defines how to approach bugs systematically. No guessing. No random changes. Reproduce, isolate, fix, verify.

Debugging Mindset

  • Reproduce first. Never propose a fix for a bug you haven't seen. If you can't reproduce it, you don't understand it.
  • Read the error. The full error message. The stack trace. The line number. Not just the first line.
  • One change at a time. Change one thing, test, observe. Never change three things and hope one of them fixes it.
  • The bug is in your code. Until proven otherwise, assume the framework, library, and runtime are correct. Your code is the most likely source.

Debugging Protocol

Step 1: Reproduce

  • Get the exact steps that trigger the bug
  • Reproduce it yourself (or see the error output)
  • If you can't reproduce it: ask for more context, check environment differences

Step 2: Read the Error

  • Read the full error message and stack trace
  • Identify the file and line where the error originates
  • Trace the call chain — where was this function called from?
  • Check if the error message tells you exactly what's wrong (it usually does)

Step 3: Isolate

Use binary search to narrow the problem:

Layer 1: Is it a UI issue or a data issue?
  → Check the data: is it correct at the source?
  → If data is correct, the bug is in rendering
  → If data is wrong, trace it backward

Layer 2: Is it a client issue or a server issue?
  → Check the network request/response
  → If response is wrong, debug the server
  → If response is correct, debug the client

Layer 3: Is it this commit or a previous one?
  → Use git log and git diff to find when it broke
  → git bisect for harder cases

Step 4: Understand the Root Cause

  • Don't just find what broke — understand why it broke
  • Is this a one-off mistake or a systemic pattern?
  • Are there other places in the codebase with the same issue?

Step 5: Fix

  • Fix the root cause, not just the symptom
  • Make the smallest effective change
  • If the fix is complex, write a plan before implementing

Read the full file on GitHub · 105 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. yesterday First seen · 105 lines · 90 tokens per session scan A 31461ce131a2

Subscribe to this mod's changes

pwp-debug is a skill published in the GitHub repository shandar/pwp-plugin (1 stars, last pushed 6mo ago), licensed MIT. It adds 90 tokens to every session and 1,123 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.