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 instructions/kevinrabun/judges/vscode-extension-debugginggit clone --depth 1 https://github.com/KevinRabun/judgesWrote 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/instructions/kevinrabun/judges/vscode-extension-debugging)<a href="https://agentmods.dev/instructions/kevinrabun/judges/vscode-extension-debugging"><img src="https://agentmods.dev/badge/instructions/kevinrabun/judges/vscode-extension-debugging.svg" alt="Measured on agentmods" 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 | $0.01365 | $0.01365 |
| Opus 5 | $0.00682 | $0.00682 |
| Sonnet 5 | $0.00273 | $0.00273 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
judges vscode-extension-debugging.instructions.md 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 4d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VS Code Extension Debugging — Agent Instructions
When debugging issues with the VS Code extension (vscode-extension/), follow this exact sequence. Do NOT skip steps or investigate source code speculatively before checking runtime logs.
Step 1: Get the runtime error (ALWAYS DO THIS FIRST)
Ask the user to provide the exact error from one of these sources:
- Extension Host Log:
View > Output > Extension Host— shows activation failures and API errors. - Developer Tools Console:
Help > Toggle Developer Tools > Console— shows manifest validation errors and uncaught exceptions. Filter forjudgesorkevinrabun. - Window Log:
Developer: Open Log File...from the Command Palette.
Tell the user:
Open
Help > Toggle Developer Tools, switch to the Console tab, then runDeveloper: Reload Windowfrom the Command Palette. Filter the console for "judges" and paste any errors you see.
Do NOT proceed to source code analysis until you have the runtime error message. Compile success does not mean runtime success. Manifest schema violations, missing required fields, and API availability issues are only visible at runtime.
Step 2: Classify the error
Once you have the error, classify it:
| Error pattern | Root cause area | Where to look |
|---|---|---|
CANNOT register tool with... |
Manifest schema violation | vscode-extension/package.json contributes section |
No activated agent with id... |
Extension failed to activate — look for the PRECEDING error | Extension Host Log (the real error comes before this one) |
is not a function / undefined |
API not available in this VS Code version | Check engines.vscode version vs API availability |
Cannot find module |
Bundle/dependency issue | esbuild config, dependencies in package.json |
command not found |
Command not registered | contributes.commands + activate() registration |
| No error, just not working | Extension not activating | Check activationEvents match actual triggers |
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.
- 4d ago First seen · 79 lines · 1,365 tokens per session scan A fae6f1f8cd4f
judges vscode-extension-debugging.instructions.md is an instructions file published in the GitHub repository KevinRabun/judges (7 stars, last pushed 2mo ago), licensed MIT. It adds 1,365 tokens to every session, about $0.0068 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 2026-08-31.
Other instructions, from other repositories
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
flyto-core CLAUDE.md
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.