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 agentmods add skills/adilkalam/orca/debugging-firstnpx skills add adilkalam/orca --skill debugging-firstgit clone --depth 1 https://github.com/adilkalam/orcaWhat 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 | $0.00037 | $0.01484 |
| Opus 5 | $0.00018 | $0.00742 |
| Sonnet 5 | $0.00007 | $0.00297 |
| Haiku 4.5 | $0.00004 | $0.00148 |
Grade A, and why
debugging-first scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -v [endpoint] How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging First
RULE: Use debugging tools BEFORE examining or modifying code when investigating issues.
The Principle
When something isn't working, gather evidence FIRST before making changes. Debugging tools give you facts; guessing wastes time.
Debugging Tool Priority
1. Console/Logs (First Priority)
DO:
- Check console output for errors
- Look at warning messages
- Review log files
- Check for stack traces
- Note the exact error message and location
# Browser console (via Puppeteer evaluate)
mcp__puppeteer__puppeteer_evaluate({ script: "console.log('checking...')" })
# Server logs
tail -f logs/app.log
# Build output
npm run build 2>&1 | head -50
2. Network Requests (Second Priority)
DO:
- Check API call responses
- Verify request payloads
- Look for failed requests (4xx, 5xx)
- Check response status codes
- Examine request/response headers
# Browser network (via Puppeteer evaluate)
mcp__puppeteer__puppeteer_evaluate({ script: "performance.getEntriesByType('resource')" })
# CLI testing
curl -v [endpoint]
# Check for CORS issues
# Look for preflight failures
3. Application State (Third Priority)
DO:
- Inspect current state values
- Check what data is loaded
- Verify props/arguments received
- Look at environment variables
- Check localStorage/sessionStorage
4. Code Examination (Last Priority)
Only AFTER gathering evidence from above:
- Read the relevant code
- Trace the execution path
- Check the logic
- Verify assumptions
The Debugging Process
Step 1: Gather Evidence
User: "The login isn't working"
Agent (CORRECT approach):
1. Check console logs for errors
2. Check network tab for API calls
3. Check what error message (if any) is shown
4. Check if user is redirected or stays on page
5. NOW look at the code with context
Step 2: Analyze Before Acting
With debugging evidence in hand:
- Identify the actual failure point
- Understand the error cause
- Form a hypothesis
- Verify hypothesis before fixing
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.
- yesterday First seen · 264 lines · 37 tokens per session scan A 5cfdb3bb38bb
debugging-first is a skill published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,484 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
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…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
mintlify-preview
Run the public Mintlify product docs site locally for live preview. Use when previewing or iterating on docs under docs/ (.mdx/.md pages, docs.json nav), or when the user says "start the docs", "run mintlify", "preview the docs site".