Borrowing it
Nothing to install: this file belongs to skyf0xx/Pebble. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/skyf0xx/Pebble/master/CLAUDE.mdgit clone --depth 1 https://github.com/skyf0xx/PebbleWrote 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/skyf0xx/pebble/claude-md)<a href="https://agentmods.dev/instructions/skyf0xx/pebble/claude-md"><img src="https://agentmods.dev/badge/instructions/skyf0xx/pebble/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 5.1 | $0.03568 | $0.03568 |
| Opus 5 | $0.01784 | $0.01784 |
| Sonnet 5 | $0.00714 | $0.00714 |
| Haiku 4.5 | $0.00357 | $0.00357 |
Grade A, and why
Pebble 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 7d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pebble — Claude Code Context
A PWA chat interface for Hermes and Open Claw agents. Warm, minimal, installable. No backend needed.
Before you start
- SPEC.md — product vision, session model, rendering rationale. Read for the why
- TODO.md — the build order. Each task is self-contained. Work one task at a time, commit, move on.
- hermes-plugin/skills/pebble-protocol/SKILL.md — the
pebble_sendprotocol (message/ui/status/push). Read before touchingAgentUIBlockor the Hermes adapter's tool-call interception. The OpenUI Lang component catalogue is split into the sibling pebble-protocol-ui/SKILL.md (the agent loads it lazily when building a UI block).
What we're building
A static React PWA that connects directly to a Hermes agent's HTTP API. No backend, no MCP server. The Pebble launcher (main.go) serves the app and reverse-proxies /api/* to Hermes from the same origin, so on the desktop machine Pebble auto-connects to its own localhost origin with no wizard and no paste. Tailscale is only needed to reach Pebble from another device: you expose the launcher with tailscale serve, then use the app's "Open on phone" button — with a tunnel up it shows a QR to scan; without one it opens the SetupScreen wizard that walks you through Tailscale. Access (over the tunnel) is gated by the tailnet itself — there is no API token. It talks to the agent over GET /api/sessions + POST /api/sessions/{id}/chat/stream (SSE).
The UI has two views:
- Session list — chat inbox, WhatsApp-style (not a task board). Active / Completed sections, each sorted by
last_updated - Chat thread — messages + inline interactive UI pushed by the agent
Stack
| Framework | React + Vite (static output) |
| PWA | vite-plugin-pwa |
| Styling | Tailwind CSS v4 |
| Components | shadcn/ui |
| Generative UI | @openuidev/react-lang + react-ui (OpenUI Lang) |
| State | Zustand |
| Transport | Hermes HTTP API (SSE streaming via fetch) |
| Persistence | localStorage + IndexedDB |
| Icons | lucide-react |
| Avatars | DiceBear Thumbs (CDN) |
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.
- 7d ago First seen · 154 lines · 3,568 tokens per session scan A 22426e3ee4dc
Pebble CLAUDE.md is an instructions file published in the GitHub repository skyf0xx/Pebble (22 stars, last pushed 29d ago), licensed MIT. It adds 3,568 tokens to every session, about $0.0178 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
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.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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.