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/esaruoho/apple/claude-mdgit clone --depth 1 https://github.com/esaruoho/appleWhat 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 | $0.01747 | $0.01747 |
| Opus 5 | $0.00873 | $0.00873 |
| Sonnet 5 | $0.00349 | $0.00349 |
| Haiku 4.5 | $0.00175 | $0.00175 |
Grade A, and why
apple 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 3d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Repo — Claude Code Instructions
Project-specific instructions for sessions in /Users/esaruoho/work/apple/. Skill loader is skill.md; wiki index is wiki/INDEX.md; rules from ~/.claude/CLAUDE.md also apply.
🔴🔴🔴 GROUND RULE: NEVER USE NOHUP. NEVER USE A DAEMON. ALWAYS USE CLOUDCITY-BOOT.app + SYSTEMS.yaml 🔴🔴🔴
On the Mac Mini (cloudcity), the ONLY acceptable way to RUN any long-lived process is Cloudcity-Boot.app driven by systems.yaml (convey/systems.yaml).
- NEVER
nohupanything — not a worker (e.g.fm-worker/fm-service), not a daemon, not a "bounded probe," not as atimeoutsubstitute. macOS lackingtimeoutis NOT an excuse. - NEVER start a background daemon,
launchd/LaunchAgent, SSH-launched&process, or any "leave it running" process. SSH-launched daemons don't persist — proof it's the wrong tool. - ALWAYS run via Cloudcity-Boot.app (visible iTerm panes, crash-only
while-truewrappers + guardians) generated fromsystems.yaml. Add/change a service: editsystems.yaml, regenerate/edit the applet, restart via!pk cloudcity restart(Discord / file-drop~/work/comms/queue/pakettibot-inbox/). Neveropen Cloudcity-Boot.appover SSH. Restart a wedged worker the same way — let Boot relaunch its pane. - Acceptable Mini commands are exactly two kinds: (1) Cloudcity-Boot +
systems.yamlto run/restart; (2) client calls + read-only inspection (fm-submit,convey,cat,ls,ps,git -C <abs>) — no&, nonohup; bound any probe inside the process (asyncio.wait_for), never a backgrounded killer loop.
Why (2026-06-12): while debugging wedged FM I repeatedly nohup'd fm-worker/fm-service and bounded read-only probes with nohup … & kill. Robust wins over brittle. Companions: ~/.claude/CLAUDE.md, comms/CLAUDE.md, convey/CLAUDE.md, ~/.claude/skills/cloudcity/skill.md.
🔴 GROUND RULE: EVERY APP SHIPS THE SHARED HELP + DONATE PANEL
Every Apple-native app we make — Guidance, Fleet, Converse, Recburn, AppleToolbox, and every future one — ships the SAME Help, which is the SAME set of ways to donate to Esa. Do not write a per-app Help or per-app donation list. There is one component and one canonical link list.
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.
- 3d ago First seen · 63 lines · 1,747 tokens per session scan A 1025dd5bfccc
apple CLAUDE.md is an instructions file published in the GitHub repository esaruoho/apple (11 stars, last pushed 6d ago), licensed MIT. It adds 1,747 tokens to every session, about $0.0087 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
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.