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/linuxfoundation/lfx-self-serve/claude-mdgit clone --depth 1 https://github.com/linuxfoundation/lfx-self-serveWrote 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/linuxfoundation/lfx-self-serve/claude-md)<a href="https://agentmods.dev/instructions/linuxfoundation/lfx-self-serve/claude-md"><img src="https://agentmods.dev/badge/instructions/linuxfoundation/lfx-self-serve/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 | $0.05723 | $0.05723 |
| Opus 5 | $0.02861 | $0.02861 |
| Sonnet 5 | $0.01145 | $0.01145 |
| Haiku 4.5 | $0.00572 | $0.00572 |
Grade D, and why
lfx-self-serve CLAUDE.md scanned grade D with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Hot reload silent? Likely `inotify` watcher limit — `sudo sysctl fs.inotify.max_user_watches=524288`. Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf node_modules && yarn install # nuclear How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Auto-loaded by Claude Code at session start. Read this first.
Important: invoke
/lfx-skills:lfxfor any cross-repo task or "where does X live" question. Routes to owning repos and pulls in their CLAUDE.md, skills, and rules. If/lfx-skills:lfxis not found, install with/plugin marketplace add linuxfoundation/lfx-skillsthen/plugin install lfx-skills@lfx-skills.
Project Overview
LFX One is a Turborepo monorepo containing an Angular 20 SSR application with stable zoneless change detection and Express.js server.
Working mode
You have full file-edit authority in this session — different from a Cowork session where you generate prompts for someone else to execute. For pre-edit hygiene checks (re-read files, type-check after multi-file changes, etc.) invoke the /self-serve-dev skill.
Lean on subagents. Use the Agent tool for broad searches (Explore), independent parallel investigations (multiple Agent calls in one message), and context-heavy reads that would bloat the main thread. For the LFX post-commit audit, launch the central lfx-skills reviewer trio in parallel (subagent_type: lfx-skills:lfx-general-code-reviewer, subagent_type: lfx-skills:lfx-self-serve-code-reviewer, and subagent_type: lfx-skills:lfx-self-serve-learnings-reviewer, all with run_in_background: true). If Claude displays plugin agents without a namespace, use the equivalent displayed names. This repo's local CLAUDE.md, .claude/rules/, .claude/skills/, architecture docs, review checklists, and KB remain the review source of truth. Default to delegating when the task is wide, parallel, or read-heavy.
Domain language
Use these naturally — do not paraphrase:
- PCC — Project Control Center
- ED — Executive Director
- Admin Mode — privileged view variant for EDs and admins
- Affiliation — contributor's company/org link
- L2 — second-level navigation pattern
- Personas — Contributor, Maintainer, ED, Board Member
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 · 290 lines · 5,723 tokens per session scan D 883896aa1fe6
lfx-self-serve CLAUDE.md is an instructions file published in the GitHub repository linuxfoundation/lfx-self-serve (11 stars, last pushed 4d ago), licensed MIT. It adds 5,723 tokens to every session, about $0.0286 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). 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.