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/blueocean223/hey-clawd/agents-mdgit clone --depth 1 https://github.com/BlueOcean223/hey-clawdWrote 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/blueocean223/hey-clawd/agents-md)<a href="https://agentmods.dev/instructions/blueocean223/hey-clawd/agents-md"><img src="https://agentmods.dev/badge/instructions/blueocean223/hey-clawd/agents-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 | $0.00856 | $0.00856 |
| Opus 5 | $0.00428 | $0.00428 |
| Sonnet 5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
hey-clawd AGENTS.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 5d 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 — 17 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Sources/ contains the menu-bar macOS app: App/ for startup and assembly, Core/ for the state machine, HTTP server, preferences, hook installation, and SVG pipeline (Core/SVG), Window/ for the floating pet window, Bubble/ for Claude Code, CodeBuddy, and Codex permission prompts, Tray/ for menu bar controls, Mini/ for edge mode, Focus/ for focus-session UI, and Update/ for Sparkle. Resources/ holds runtime assets such as SVGs and sounds, while docs/ holds contributor documentation including the SVG animation spec. hooks/ contains the Node/CommonJS hook handlers and installers for Claude Code, CodeBuddy, Gemini CLI, Cursor, Copilot CLI, Codex CLI, plus the Pi extension/installer bridge, with tests under hooks/test/. agents/ defines per-agent metadata and log-monitor helpers for those integrations. Tests/HeyClawdAppTests/ covers SVG parsing and rendering, the HTTP server, hook installation, permission schemas, and animation pipeline behavior. scripts/ contains maintenance helpers such as svg-audit-scan.js.
Build, Test, and Development Commands
Use swift build for the default debug build and .build/debug/hey-clawd to run it. Use swift build -c release for a local release build. Run swift test for the Swift test target in Tests/HeyClawdAppTests/. CI archives with xcodebuild -project hey-clawd.xcodeproj -scheme hey-clawd -configuration Release archive, so keep that path healthy when changing packaging or signing behavior. Run ./test-bubble.sh all for permission-bubble integration checks, or swap all for single, stack, passthrough, disconnect, or dnd. Run ./test-animations.sh when validating SVG playback against a running app. Run cd hooks && node test/index.js for hook-side tests.
Coding Style & Naming Conventions
Follow the existing Swift 6 style: 4-space indentation, UpperCamelCase for types, lowerCamelCase for methods and properties, and one primary type per file named after that type, such as StateMachine.swift. Keep UI work on @MainActor; long-lived coordination belongs in actors and monitor types under Core/. In hooks/ and agents/, stay with CommonJS, double quotes, and small single-purpose modules. Keep duplicated event mappings in sync when a hook script, agent descriptor, installer allowlist, or docs/integrations/ page encodes the same behavior. Name SVG assets with the existing clawd-<state>.svg pattern.
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.
- 5d ago First seen · 17 lines · 856 tokens per session scan A 3f383af14cf1
hey-clawd AGENTS.md is an instructions file published in the GitHub repository BlueOcean223/hey-clawd (5 stars, last pushed 3mo ago), licensed MIT. It adds 856 tokens to every session, about $0.0043 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
Peekaboo AGENTS.md
AGENTS.md instructions for openclaw/Peekaboo, covering repository guidelines, start here, project structure & modules, build, test, and development commands and coding style & naming conventions.
Applite CLAUDE.md
Instructions for milanvarady/Applite, covering claude.md, project overview, build & run, architecture and data flow.
scarf AGENTS.md
AGENTS.md instructions for awizemann/scarf: This repo carries its own agent memory — plain files in git, served by the in-repo memophant-mcp MCP server, managed by the Memophant macOS app. It works the same for every agent (Claude Code, Codex, Cursor, Gemini, Copilot). This block is regenerated between the memophant…
palmier-pro AGENTS.md
AGENTS.md instructions for palmier-io/palmier-pro, covering palmierpro, build, agents, engineering approach and code style.
scarf copilot-instructions.md
Copilot instructions for awizemann/scarf: File memory notes under one of six folders (architecture/conventions/decisions/operations/project/roadmap), never the root. When a note is grounded in code, pass sourcepaths (the repo files it depends on) so Memory Health can drift-check it — an unanchored code note can't be…
HomeClaw AGENTS.md
AGENTS.md instructions for omarshahine/HomeClaw, covering homeclaw, architecture, project structure, build system and xcode version.