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 pwdev-solucoes/pwdev-claude-marketplace --skill power-debuggit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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/pwdev-solucoes/pwdev-claude-marketplace/power-debug)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/power-debug"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/power-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/pwdev-solucoes/pwdev-claude-marketplace/power-debug"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/power-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 | $0.00020 | $0.00718 |
| Opus 5 | $0.00010 | $0.00359 |
| Sonnet 5 | $0.00004 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
power-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 5d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find the Root Cause First
The iron law
No fix without root cause investigation first.
A fix applied to a symptom you have not explained is a guess. Guesses that happen to work are worse than guesses that fail, because they hide the real defect until it returns somewhere more expensive.
Phase 0 — Has this already been documented?
If .planning/power/context/pitfalls.md exists, read it before anything else. It is where
previously observed failure modes were recorded with evidence, and the cheapest possible
investigation is discovering that someone already did it.
A match there is a lead, not a verdict: confirm it against the current failure before acting on it.
Phase 1 — Root cause
- Read the entire error. All of it — the message, the type, every frame of the stack, the lines before it. The answer is in there more often than not.
- Reproduce it consistently. An intermittent failure you cannot trigger is not yet understood. Find the condition that makes it deterministic.
- Check what changed recently.
git log,git diff. Most breakage is recent. - In a multi-component system, instrument every boundary before proposing anything. Add logging at each hand-off — caller, transport, handler, storage — and run once to learn where it breaks. Guessing which layer is wrong and fixing that layer is how three fixes go by without touching the defect.
- Trace the data backwards from where it is wrong to where it was right. The bug is between those two points.
Phase 2 — Pattern analysis
Find something in this same codebase that works and does the same kind of thing. Read it completely — not a skim, not the parts you expect to matter. List every difference between it and the broken path, including the ones that look irrelevant. The irrelevant-looking one is frequently the answer.
Phase 3 — One hypothesis at a time
Write it down: "I think X is the cause, because Y." Design the smallest test that would prove it wrong. Change one variable.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 77 lines · 20 tokens per session scan A e8e1140a4148
power-debug is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 20 tokens to every session and 718 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 2026-09-03.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.