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/johnpapa/vscode-cloak/copilot-instructionsgit clone --depth 1 https://github.com/johnpapa/vscode-cloakWrote 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/johnpapa/vscode-cloak/copilot-instructions)<a href="https://agentmods.dev/instructions/johnpapa/vscode-cloak/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/johnpapa/vscode-cloak/copilot-instructions.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 | $0.00868 | $0.00868 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
vscode-cloak copilot-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 5d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions — Cloak
Project Type
This is a VS Code extension written in TypeScript. The package.json contributes field is the product spec — commands, settings, menus, and keybindings are all declared there.
TypeScript Conventions
- Use
strictmode (enforced bytsconfig.json) - Prefer
async/awaitover raw Promises - Use the
vscodenamespace for all VS Code API calls — import asimport * as vscode from 'vscode' - Destructure
vscodesubmodules at the top of a file when used repeatedly (e.g.,const { commands } = vscode) - Export functions and classes — avoid default exports
- Use enums for string constants (
Commands,Settings,Sections) rather than raw strings
Extension Patterns
- Command handler pattern: Each command handler is an exported async function in
src/commands.ts, registered insrc/extension.tsviacommands.registerCommand(Commands.enumValue, handler) - Configuration access: Always use the helpers in
src/configuration/— never callvscode.workspace.getConfiguration()directly in command handlers - Re-export barrels: Both
src/models/index.tsandsrc/configuration/index.tsre-export all members. Import from the barrel ('./models','./configuration') not from individual files - Status bar: Single shared instance in
src/statusbar.ts— left-aligned, uses Codicon$(eye)
Code Style
- Formatter: Prettier — single quotes, trailing commas, 100-char line width, 2-space indent (see
.prettierrc.js) - Linter: ESLint with
@typescript-eslintparser (see.eslintrc) - Lint with
npm run lint, auto-fix withnpm run lint-fix
Test Conventions
- Runner: Mocha with TDD UI (
suite,test,suiteSetup,suiteTeardown) - Host: Tests run inside a VS Code instance via
vscode-test— they are integration tests, not unit tests - Test files: Place tests in
src/test/suite/with.test.tssuffix - Setup/teardown: Use
setupTestSuite()andteardownTestSuite()fromsrc/test/suite/lib/setup-teardown-test-suite.tsto save and restore user settings - Assertions: Use Node's built-in
assertmodule - Run with
npm test(compiles first) ornpm run just-test(assumes already compiled)
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.
- 5d ago First seen · 49 lines · 868 tokens per session scan A 884258a9c13f
vscode-cloak copilot-instructions.md is an instructions file published in the GitHub repository johnpapa/vscode-cloak (119 stars, last pushed 24d ago), licensed MIT. It adds 868 tokens to every session, about $0.0043 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 2026-08-30.
Other instructions, from other repositories
react-seed AGENTS.md
Instructions for guokaigdg/react-seed, covering agents.md, 目录, 1. 项目概览, 2. 技术栈 and 3. 目录结构.
agentic-playwright enums.instructions.md
Instructions for idavidov13/agentic-playwright, covering enums, critical, file locations, instructions and phase 1: decide if the value belongs in an enum.
ui-extensions-sdk CLAUDE.md
Instructions for contentful/ui-extensions-sdk, covering claude project instructions — ui-extensions-sdk, identity & scope, working style, sharp edges and verification before claiming done.
starknet-agentic CLAUDE.md
Instructions for keep-starknet-strange/starknet-agentic, covering starknet agentic -- development context, cairo, typescript, skills and git.
solo copilot-instructions.md
Copilot instructions for hiero-ledger/solo, covering github copilot instructions for hiero-ledger/solo and highest-frequency rules.
openmcp-client CLAUDE.md
Instructions for LSTM-Kirigaya/openmcp-client, covering claude.md, development commands, setup and installation, development and service development.