Borrowing it
Nothing to install: this file belongs to Oolab-labs/patchwork-os. 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/Oolab-labs/patchwork-os/main/.claude/skills/ide-quality/SKILL.mdgit clone --depth 1 https://github.com/Oolab-labs/patchwork-osWrote 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/oolab-labs/patchwork-os/ide-quality)<a href="https://agentmods.dev/skills/oolab-labs/patchwork-os/ide-quality"><img src="https://agentmods.dev/badge/skills/oolab-labs/patchwork-os/ide-quality/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/oolab-labs/patchwork-os/ide-quality"><img src="https://agentmods.dev/badge/skills/oolab-labs/patchwork-os/ide-quality.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 | $0.00040 | $0.01252 |
| Opus 5.5 | $0.00016 | $0.00501 |
| Sonnet 5.5 | $0.00008 | $0.00250 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
ide-quality 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.
This is a copy
100% identical to ide-quality — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IDE Quality Sweep Workflow
Prerequisites
- Check if the
getToolCapabilitiesMCP tool is available to you.- Available: call it, check
extensionConnected→ use IDE Path below. - Not available: use CLI Path below.
- Available: call it, check
IDE Path
Use this path when bridge MCP tools are available and extension is connected.
Phase 1: Assess the environment
- Use
getToolCapabilitiesto discover available linters, formatters, and test runners - Use
getProjectInfoto understand the project type and languages - Determine the scope: if
$ARGUMENTSis provided, focus on that path; otherwise sweep the whole workspace
Phase 2: Collect all diagnostics
- Use
getDiagnosticsto get errors and warnings across the workspace - Group diagnostics by severity (error → warning → info) and by file
- Report the total count: "Found N errors, M warnings across K files"
Phase 3: Auto-fix
- For each file with fixable diagnostics:
- Use
fixAllLintErrorsto apply auto-fixes - Use
organizeImportsto clean up imports - Use
formatDocumentto apply consistent formatting
- Use
- Use
getDiagnosticsagain to see what remains after auto-fixing - Report: "Auto-fixed X issues. Y issues remain that need manual attention."
Phase 4: Manual fixes (remaining errors only)
- For remaining errors (not warnings), analyze the diagnostic message
- Use
getHoverandgoToDefinitionto understand the context - Use
editTextto apply targeted fixes - Use
saveDocumentafter each fix
Phase 5: Verify
- Use
runTeststo run the test suite - If tests fail, identify if the failure was caused by our changes:
- Use
getDiagnosticson test files - If we broke something, revert the specific change
- Use
- Use
getDiagnosticsone final time to confirm we haven't introduced new issues
Phase 6: Report and optionally commit
- Summarize all changes made:
- Files modified
- Issues fixed (auto vs manual)
- Issues remaining (with explanations)
- Test results
- Ask whether to commit the cleanup:
- If yes:
gitAddthe changed files,gitCommitwith message "chore: fix lint errors and format code"
- If yes:
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 · 128 lines · 40 tokens per session scan A d832946a7fe1
ide-quality is a skill published in the GitHub repository Oolab-labs/patchwork-os (31 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,252 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to ide-quality, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
bug-report
Structured bug report from a description, or analyze code for potential bugs. Reproduction steps, severity.
bug-triage
Re-evaluate open bugs — priority vs severity, assign to sprints, surface systemic trends. Run when the count grows.
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.
openclaw-debugger
Trigger when an OpenClaw agent is broken, silent, crashing, stuck, not responding, returning empty output, or the user says "my agent is down", "agent not working", "/openclaw-debugger". Walks through the standard OpenClaw 2026.4 diagnosis checklist and prints a report.