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/kelsidavis/system7/claude-mdgit clone --depth 1 https://github.com/Kelsidavis/System7Wrote 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/kelsidavis/system7/claude-md)<a href="https://agentmods.dev/instructions/kelsidavis/system7/claude-md"><img src="https://agentmods.dev/badge/instructions/kelsidavis/system7/claude-md.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 | $0.01934 | $0.01934 |
| Opus 5 | $0.00967 | $0.00967 |
| Sonnet 5 | $0.00387 | $0.00387 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade B, and why
System7 CLAUDE.md scanned grade B 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get install build-essential gcc-multilib grub-pc-bin xorriso qemu-system-x86 python3 vim-common How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Claude Code with System 7
This file contains guidance for using Claude Code (Claude in the IDE, Claude Code CLI, or claude.ai/code) with the System 7 project.
Quick Start
Build & Run
make # Build kernel (x86, English)
make run # Build and run in QEMU
make clean # Clean build artifacts
Add Languages
make LOCALE_FR=1 # Add French to build
make LOCALE_DE=1 LOCALE_JA=1 # Multiple languages
Debug
make debug # Build with GDB support and start QEMU
# In another terminal: gdb kernel.elf -ex "target remote :1234"
Project Structure
System7/
├── include/ # Public headers (organized by subsystem)
├── src/ # Implementation files (mirrors include structure)
├── docs/ # Documentation (start with docs/INDEX.md)
├── scripts/ # Development utilities
├── resources/
│ ├── strings/ # Localization (one .json per language)
│ └── device-tree/ # QEMU device tree files
├── Makefile # Build system
└── README.md # Main documentation
Common Tasks with Claude
Understanding a Component
- Read the component guide in
docs/components/ - Look at the header in
include/ComponentName/ - Study the implementation in
src/ComponentName/ - Ask Claude: "Explain how X works in this codebase"
Finding What's Broken
- Check
docs/KNOWN_ISSUES.md - Search for
TODOorFIXMEcomments - Run
grep -r "HACK" include/ src/ - Look at
docs/IMPLEMENTATION_STATUS_AUDIT.md
Adding a Feature
- Decide which component it belongs to
- Check if it's already partially implemented
- Look for TODOs in that component
- Ask Claude: "What would need to change to add X?"
Fixing a Bug
- Reproduce in QEMU:
make run - Check serial output: look for error messages
- Ask Claude to help trace the issue
- Make minimal fix, test in QEMU first
- Be skeptical of "works in QEMU = works everywhere"
Testing Your Changes
make clean && make run # Quick rebuild + test
make debug # Run with GDB for breakpoints
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 · 252 lines · 1,934 tokens per session scan B d91fd0df8255
System7 CLAUDE.md is an instructions file published in the GitHub repository Kelsidavis/System7 (360 stars, last pushed 1mo ago), licensed MIT. It adds 1,934 tokens to every session, about $0.0097 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.