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.
npx skills add shandar/pwp-plugin --skill pwp-debuggit clone --depth 1 https://github.com/shandar/pwp-pluginWrote 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.
[](https://agentmods.dev/skills/shandar/pwp-plugin/pwp-debug)<a href="https://agentmods.dev/skills/shandar/pwp-plugin/pwp-debug"><img src="https://agentmods.dev/badge/skills/shandar/pwp-plugin/pwp-debug/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.
<a href="https://agentmods.dev/skills/shandar/pwp-plugin/pwp-debug"><img src="https://agentmods.dev/badge/skills/shandar/pwp-plugin/pwp-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00090 | $0.01123 |
| Opus 5.5 | $0.00036 | $0.00449 |
| Sonnet 5.5 | $0.00018 | $0.00225 |
| Haiku 4.5 | $0.00009 | $0.00112 |
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 1mo 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.
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
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.
- 1mo ago First seen · 105 lines · 90 tokens per session scan A 31461ce131a2
pwp-debug is a skill published in the GitHub repository shandar/pwp-plugin (1 stars, last pushed 7mo ago), licensed MIT. It adds 90 tokens to every session and 1,123 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
tang-rou
Ative TANG-ROU (Soft Mist) quando o usuário nomear TANG-ROU ou pedir desenvolvimento, correção, auditoria, otimização ou planejamento de Foundry VTT e programação aplicada: macros, módulos, sistemas, CSB, Combat Tracker Dock, Midi-QOL, DAE, Sequencer, Warp Gate, Active Effects, hooks, compêndios, fichas homebrew, erro…
watch-errors
Quiet operator watch for a detached clawback proxy — stream ONLY legitimate errors and never the benign flood. Wakes on [error]/[fatal] lines, crash signatures (uncaught/EADDRINUSE/ECONN/Error:/self-loop), server-side 5xx that are NOT the transient 529, real (non-keep-alive) request failures, and a loud "PROXY DOWN"…
inspect
Statically inspect prompt-cache breakpoints in a captured /v1/messages body or a clawback --state file, with ZERO token spend and no API calls. Answers "where are the cachecontrol breakpoints, and which ephemeral tokens (cch / date / ) sit inside which cached prefixes?" — i.e. what a single mutation cold-starts. Use…
monitor
Run the clawback proxy and watch its log output for errors. Starts the bare proxy (honoring config layering), captures combined stdout+stderr to a log file, and follows it with warn/error/4xx/5xx lines highlighted. Supports foreground follow, background --detach (with --stop/--status), and --attach to tail an…
operate
Watch an already-detached clawback proxy as an event stream — surface only actionable log lines (error/warn/4xx/5xx/crash signatures, plus rebind and runtime-mode toggles) AND announce a loud "PROXY DOWN" line the instant the proxy pid dies. Fills the gap that runmonitor.sh --attach leaves: a bare tail goes SILENT on…
verify-config
Config doctor for clawback — loads the merged config (DEFAULTS < global < ./CLAWBACK.md < CLI overrides) exactly as the proxy's loadConfig does, prints a secret-free summary of the resolved values plus the merge-order sources, and exits non-zero if the canonical CLAWBACK.md did NOT take effect (host not 0.0.0.0, tls…