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/cai-layer/cai/claude-mdgit clone --depth 1 https://github.com/cai-layer/caiWrote 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/cai-layer/cai/claude-md)<a href="https://agentmods.dev/instructions/cai-layer/cai/claude-md"><img src="https://agentmods.dev/badge/instructions/cai-layer/cai/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 | $0.03988 | $0.03988 |
| Opus 5 | $0.01994 | $0.01994 |
| Sonnet 5 | $0.00798 | $0.00798 |
| Haiku 4.5 | $0.00399 | $0.00399 |
Grade A, and why
cai 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Quick reference for Claude Code. Full docs map: _docs/INDEX.md.
What is Cai?
Native macOS action layer (SwiftUI + AppKit). User presses Option+C anywhere; Cai detects the selected content type and shows context-aware actions powered by an LLM. Privacy-first, local-by-default — no telemetry; runs on-device with the built-in MLX model or Apple Intelligence. Optional cloud providers (OpenRouter, Anthropic).
Design System
Always read docs/design/DESIGN.md before any UI/visual work. All color tokens, type scale, spacing, radii, motion curves, and component patterns live there. In QA mode, flag any code that doesn't match it.
Build & Run
# Dev
cd Cai && open Cai.xcodeproj # then "Cai" scheme → "My Mac" → Cmd+R
# CLI
xcodebuild -scheme Cai -configuration Debug build
xcodebuild -scheme Cai -configuration Debug test
xcodebuild -scheme Cai -configuration Release archive -archivePath /tmp/Cai.xcarchive
Project Structure (entry points)
Cai/Cai/
├── CaiApp.swift # @main → AppDelegate
├── AppDelegate.swift # Menu bar, hotkey, popover, lifecycle
├── Models/ # ActionItem, CaiSettings, CaiShortcut, OutputDestination, BuiltInDestinations, MCPModels
├── Services/ # Window/Clipboard/ContentDetector, LLMService + MLXInference, OutputDestinationService, MCP*, KeychainHelper, ClipboardHistory, OCRService, ExtensionParser/Service, HotKeyManager, PermissionsManager (Accessibility) + NativeAccessManager/TCCRemediation (on-demand TCC grants), UpdateChecker, CrashReportingService, PendingChangeStore/Watcher + ActionHistoryLog (agent proposals)
└── Views/ # ActionListWindow (router), ActionRow, ResultView, CustomPromptView, SettingsView, ShortcutsManagementView, DestinationsManagementView, ExtensionBrowserView, MCPFormView, MCPManagementView ("Connections": Agents / Tools / System Access tabs), NativeAccessSettingsView (macOS grants), ConnectorsSettingsView, ConnectAgentContent + AgentConnection (connect-agent payloads), ModelSetupView, OnboardingPermissionView, ShortcutRecorderView, ActionReviewView (approval sheet), CapabilitySubtitle (capability chips in list rows), CaiColors, CaiLogo, KeyboardHint, AboutView, VisualEffectBackground
Cai/CaiActionCore/ # SPM package: authored-action schema, validator, approval tiers, chain walk + capability detection. Shared with the cai-mcp helper; every function pure and table-tested.
Cai/CaiMCPHelper/ # cai-mcp: the stdio MCP server agents talk to. main.swift (handshake), Tools.swift (the four tools), ToolDispatch, CaiBridge. Embedded in Contents/Helpers, symlinked into ~/Library/Application Support/Cai/bin.
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 · 152 lines · 3,988 tokens per session scan A af2b298ef5b5
cai CLAUDE.md is an instructions file published in the GitHub repository cai-layer/cai (56 stars, last pushed 10d ago), licensed MIT. It adds 3,988 tokens to every session, about $0.0199 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
openquack AGENTS.md
Instructions for larryxiao/openquack, covering agents.md, posture, before you start, workflow and pr template (the required shape).
PokeTokenBar CLAUDE.md
Instructions for chattymin/PokeTokenBar, covering poketokenbar — claude 프로젝트 지침, 참조 문서 (필요할 때 읽는다), 기여 언어 규약 (오픈소스 대비 — english first), 릴리스 (자연어 트리거) and 확장 규약 (새 프로바이더/툴 추가 시).
TokenBar AGENTS.md
Instructions for Nanako0129/TokenBar, covering tokenbar agent routing, read order, invariants, authorization boundary and handoff.
TokenBar CLAUDE.md
Instructions for Nanako0129/TokenBar: Read AGENTS.md first, then docs/knowledge/README.md and the task-specific canonical document it routes to. If .agent-local/CLAUDE.md exists, read it after the canonical documents as additive machine-local guidance only; it must not override the canonical architecture…
localvoxtral AGENTS.md
Instructions for T0mSIlver/localvoxtral, covering localvoxtral — agent guide, build & test — read this first on a non-mac dev box, proof culture — non-negotiable, test tiers — the short version and ci / shipping.
barkeep AGENTS.md
Instructions for iannuttall/barkeep, covering agent notes, product rules, repo map, commands and app structure.