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/kernel/kernel-mcp-server/agents-mdgit clone --depth 1 https://github.com/kernel/kernel-mcp-serverWhat 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 | $0.01090 | $0.01090 |
| Opus 5 | $0.00545 | $0.00545 |
| Sonnet 5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
kernel-mcp-server AGENTS.md 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.
# In another terminal, send MCP requests with curl: How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Setup Guide
Package Manager
IMPORTANT: This project uses bun as the package manager. You MUST use bun for all dependency management operations.
- DO NOT use
npm,yarn, orpnpm - ALWAYS use
bun installto install dependencies - ALWAYS use
bun add <package>to add new dependencies - ALWAYS use
bun remove <package>to remove dependencies
The lock file is bun.lock - never commit changes from other package managers.
Installing Dependencies
bun install
Environment Setup
-
Copy the example environment file:
cp .env.example .env.local -
Fill in the required environment variables (values can be found in 1password > DevEnvVars > MCP section)
Development
Start the development server:
bun run dev
The server runs on port 3002 by default.
Build
Build the project for production:
bun run build
Production
Start the production server:
bun run start
Code Quality
Linting
Run ESLint (via Next.js):
bun run lint
Formatting
This project uses Prettier for code formatting.
Check formatting:
bun run format:check
Fix formatting issues:
bun run format
Prettier formats the following file types: *.ts, *.js, *.json, *.md
Project Structure
src/- Source code directorypublic/- Static assetsnext.config.ts- Next.js configurationtsconfig.json- TypeScript configuration
Tech Stack
- Framework: Next.js 16
- Language: TypeScript
- Styling: Tailwind CSS 4
- Authentication: Clerk
- Package Manager: Bun (required)
Cursor Cloud specific instructions
Running commands
Always use make targets instead of raw bun commands to ensure 1Password (op) injects secrets from the .env file:
make dev— start dev server (port 3002)make build— production buildmake start— start production servermake install— install dependenciesmake lint— run linter
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 · 151 lines · 1,090 tokens per session scan A de40f303c14f
kernel-mcp-server AGENTS.md is an instructions file published in the GitHub repository kernel/kernel-mcp-server (32 stars, last pushed yesterday), licensed MIT. It adds 1,090 tokens to every session, about $0.0054 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 2026-08-30.
Other instructions, from other repositories
browser-harness CLAUDE.md
Instructions for browser-use/browser-harness, a project described as: Browser Harness | Self-healing harness that enables LLMs to complete any task.
obscura AGENTS.md
Instructions for h4ckf0r0day/obscura, covering agents.md, build, rendering and stealth, no rendering, with rustls or stealth and test.
browser-control AGENTS.md
Instructions for keon/browser-control: Use this project as a tiny browser pipe, not an agent framework.
stealth-browser-mcp AGENTS.md
Instructions for vibheksoni/stealth-browser-mcp, covering agent instructions, start here, recommended proxy services, environment and validation.
actionbook CLAUDE.md
Instructions for actionbook/actionbook, covering claude.md, project overview, architecture, domain model hierarchy and module structure.
AutomatiQ AGENTS.md
Instructions for StoneSteel27/AutomatiQ, covering agent guidelines, background context, our partner: nodemaven, package structure and important commands.