Borrowing it
Nothing to install: this file belongs to kaininx/PlainTab. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kaininx/PlainTab/main/.agents/skills/diagnose/SKILL.mdgit clone --depth 1 https://github.com/kaininx/PlainTabWrote 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/kaininx/plaintab/diagnose)<a href="https://agentmods.dev/skills/kaininx/plaintab/diagnose"><img src="https://agentmods.dev/badge/skills/kaininx/plaintab/diagnose/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/kaininx/plaintab/diagnose"><img src="https://agentmods.dev/badge/skills/kaininx/plaintab/diagnose.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 | $0.00034 | $0.00695 |
| Opus 5.5 | $0.00014 | $0.00278 |
| Sonnet 5.5 | $0.00007 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
diagnose 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 2mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose PlainTab
Use this skill for bug reports and performance regressions. Adapted for PlainTab from Matt Pocock's diagnose skill.
Core Rule
Build a feedback loop first. Do not guess at fixes until the symptom can be reproduced or measured well enough to prove the fix.
PlainTab Context
- Read
.claude/rules/00-core.mdand the relevant module rule from.claude/rules/README.md. - Preserve the startup invariant in
index.html:#wallpaperBack, synchronousjs/preload.js,#wallpaperFront, then the rest of the page. - Keep storage access behind
window.WallpaperDataand preserve localStorage compatibility unless a migration exists. - Use
docs/ai-tasks/for temporary repro scripts or notes that should remain with the task.
Build the Loop
Prefer the fastest deterministic signal that reaches the real symptom:
- A small Node repro script in
docs/ai-tasks/for pure JavaScript, storage migration, parser, or data-shaping bugs. node --checkon touched files or the wholejstree for syntax regressions.- A browser/Playwright script for DOM, settings panel, command palette, wallpaper rendering, or extension/web-mode behavior.
- A direct
index.htmlweb-mode run when extension APIs are not required. - A measured timing harness using
performance.now()for startup or wallpaper performance regressions. - A manually assisted loop only as a last resort; write exact steps, expected result, actual result, and screenshots/logs when available.
If no loop is possible, stop and say what was tried. Ask for the missing artifact: console log, screen recording, settings export, uploaded media sample, HAR, or permission to add temporary instrumentation.
Diagnose
- Reproduce the user-visible symptom, not a nearby error.
- Capture the exact failure: console message, wrong DOM state, storage value, timing, image layer state, or user-facing result.
- Generate 3 to 5 ranked hypotheses. Each must predict what will change if it is true.
- Probe one hypothesis at a time. Use targeted logs or assertions at module boundaries.
- Prefix temporary logs with a unique tag such as
[DEBUG-9f3a]so cleanup is reliable.
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.
- 2mo ago First seen · 60 lines · 34 tokens per session scan A 5fe4712b165e
diagnose is a skill published in the GitHub repository kaininx/PlainTab (96 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 695 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
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.
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…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…