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 KiritoBloom/WinKit --skill winkit-developer-debugginggit clone --depth 1 https://github.com/KiritoBloom/WinKitWrote 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/kiritobloom/winkit/winkit-developer-debugging)<a href="https://agentmods.dev/skills/kiritobloom/winkit/winkit-developer-debugging"><img src="https://agentmods.dev/badge/skills/kiritobloom/winkit/winkit-developer-debugging/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/kiritobloom/winkit/winkit-developer-debugging"><img src="https://agentmods.dev/badge/skills/kiritobloom/winkit/winkit-developer-debugging.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 | $0.00075 | $0.02003 |
| Opus 5.5 | $0.00030 | $0.00801 |
| Sonnet 5.5 | $0.00015 | $0.00401 |
| Haiku 4.5 | $0.00007 | $0.00200 |
Grade A, and why
winkit-developer-debugging 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WinKit Developer Debugging
WinKit is a local, read-only MCP server for Windows that answers why is my dev setup broken without guessing. From inside the agent loop you can probe ports, processes, HTTP, event logs, services, drives, hardware, and workspace state — all bounded and redacted.
This skill is a routing guide: when to call which WinKit tool and how to chain them. Tool schemas live on the server; this file tells you the playbook.
WinKit never runs shell commands, writes files, or reads credentials. Every tool is a read. Windows x64 only.
When to use
- User says: "port in use", "EADDRINUSE", "localhost:3000 not working", "connection refused", "HTTP 500", "machine slow", "tests hanging", "disk full", "what crashed", "BSOD", "is the dev server related to my workspace?"
- You need to answer about local processes, ports, drives, services, event logs, drivers, updates, startup programs, or hardware on Windows.
When NOT to use
- Host is not Windows x64 → explain WinKit is Windows-only.
- Request needs arbitrary shell execution, file writes/deletes, process kills, or credential inspection → refuse plainly and offer the read-only WinKit path.
- Non-local or production debugging → WinKit is local-first only.
Quick Start
npx --yes @winkit/mcp@latest doctor # 0 = all checks PASS
npx --yes @winkit/mcp@latest install --yes # MCP + skill, with .bak backup
Then in the agent:
diagnose_local_webapp {url:"http://localhost:3000"}
find_process_on_port {port:3000}
doctor must pass before you trust tool output. See profiles-and-permissions if a tool says "disabled".
Routing table
Default path for "app broken": diagnose_workspace → diagnose_local_webapp → correlate_recent_failures.
| User says / you observe | Primary tool(s) |
|---|---|
| "My local app is broken" | diagnose_local_webapp → diagnose_workspace → correlate_recent_failures |
| "Port is already in use" | find_process_on_port / list_listening_ports → get_process |
| "Server returns 500/4xx" | diagnose_local_webapp → get_application_errors → correlate_recent_failures |
| "Machine is slow" | system_health → system_health_trend → get_process / get_process_tree |
| "Tests are hanging" | wait_for_port / wait_for_http + list_processes + system_health |
| "Is this dev server related to my workspace?" | list_dev_servers → diagnose_workspace → workspace_snapshot |
| "Where is the project / what runs it?" | workspace_snapshot → dev_environment |
| "Disk is full" | list_drives → disk_usage → directory_overview (recursive size per child, largest first) |
| "Find/read a file or log" | find_files → read_text_file (mode="tail" for log ends) |
| "Why won't my tool start?" | audit_path_env → dev_environment |
| "Is my disk dying?" | disk_health (S.M.A.R.T.) + disk_performance |
| "Something crashed" | crash_history / shutdown_analysis or get_recent_events |
| "Why did it reboot?" | shutdown_analysis → crash_history + system_update_status (update reboots) |
| "What starts with my PC?" | startup_programs |
| "What did WinKit touch?" | privacy_info |
What ships with it
2 files 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.
- 1mo ago First seen · 155 lines · 75 tokens per session scan A 4e358fb2fd71
winkit-developer-debugging is a skill published in the GitHub repository KiritoBloom/WinKit (2 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 2,003 once invoked, about $0.0003 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
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.
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…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
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.