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/mjbommar/kernel-lore-mcp/claude-mdgit clone --depth 1 https://github.com/mjbommar/kernel-lore-mcpWrote 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/mjbommar/kernel-lore-mcp/claude-md)<a href="https://agentmods.dev/instructions/mjbommar/kernel-lore-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mjbommar/kernel-lore-mcp/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 | $0.04948 | $0.04948 |
| Opus 5 | $0.02474 | $0.02474 |
| Sonnet 5 | $0.00990 | $0.00990 |
| Haiku 4.5 | $0.00495 | $0.00495 |
Grade A, and why
kernel-lore-mcp CLAUDE.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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kernel-lore-mcp — project state
Pointers
- Standards:
docs/standards/. - Reciprocity:
docs/architecture/reciprocity.md. - Threat model:
docs/ops/threat-model.md. - Update frequency / cadence policy:
docs/ops/update-frequency.md. - Training retriever north star:
docs/research/training-retriever.md. - Deployment modes:
docs/architecture/deployment-modes.md. - Legal posture:
LEGAL.md. - Security policy:
SECURITY.md. - Governance:
GOVERNANCE.md. - Top-level 6-month roadmap (best-in-class kernel-research MCP, supersedes framing of the uplift plan):
docs/plans/2026-04-14-best-in-class-kernel-mcp.md. Built on four research streams underdocs/research/2026-04-14-*. - MCP-surface detail (Phases 10–17, still authoritative for code-level scope):
docs/plans/2026-04-15-mcp-spec-coverage-and-uplift.md. Includes the full lessons-learned retro at the bottom.
Standards
Before touching Python code: read docs/standards/python/index.md
and the relevant guide. Before touching Rust code: read
docs/standards/rust/index.md and
the relevant guide. When these standards disagree with this
CLAUDE.md, CLAUDE.md wins — it's the project-specific contract.
Original goal
A public MCP server that makes lore.kernel.org (all kernel mailing
lists) searchable by LLM-backed developer tools — Claude Code,
Codex, Cursor, and anything else that speaks MCP. Target user is a
kernel contributor or security researcher who wants structured,
low-latency queries over every patch, review thread, and bug
report on every kernel list without living inside lei.
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 · 357 lines · 4,948 tokens per session scan A 744d9ee157d5
kernel-lore-mcp CLAUDE.md is an instructions file published in the GitHub repository mjbommar/kernel-lore-mcp (4 stars, last pushed 5d ago), licensed MIT. It adds 4,948 tokens to every session, about $0.0247 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
haystack AGENTS.md
AGENTS.md instructions for deepset-ai/haystack, covering haystack guidelines for ai agents, environment, run scripts with test dependencies, open a shell with test dependencies and install temporary dependencies (for experiments only).
haystack CLAUDE.md
Claude Code instructions for deepset-ai/haystack: Before you start working on this repository, read the AGENTS.md file and follow all the instructions.
atomic-agents AGENTS.md
Instructions for Eigenwise/atomic-agents, covering atomic agents monorepo, what is this repository?, core philosophy, monorepo structure and package details.
kimi-stock-agent CLAUDE.md
Claude Code instructions for dbbbbm/kimi-stock-agent, covering 股票投资专家 agent 规则, 1. 核心纪律：信号驱动，理性执行, 2. 技术指标分析框架（macd + rsi + kdj，量比辅助）, macd — 中期趋势方向与动能 and rsi — 波段位置与多空力量平衡.
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
mcpelevator CLAUDE.md
Instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.