Borrowing it
Nothing to install: this file belongs to unravel-team/tablo. 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/unravel-team/tablo/main/CLAUDE.mdgit clone --depth 1 https://github.com/unravel-team/tabloWrote 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/unravel-team/tablo/claude-md)<a href="https://agentmods.dev/instructions/unravel-team/tablo/claude-md"><img src="https://agentmods.dev/badge/instructions/unravel-team/tablo/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/unravel-team/tablo/claude-md"><img src="https://agentmods.dev/badge/instructions/unravel-team/tablo/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.06137 | $0.06137 |
| Opus 5 | $0.03069 | $0.03069 |
| Sonnet 5 | $0.01227 | $0.01227 |
| Haiku 4.5 | $0.00614 | $0.00614 |
Grade B, and why
tablo CLAUDE.md scanned grade B 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 9d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
summarizer, the generated hook script, and the `~/.claude/settings.json` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
(generated by Tablo) `curl`s the tool call to Tablo's loopback server and blocks How it starts
The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tablo — Implementation Plan
Tablo is a small floating animated cat that watches your Claude Code agents. It lives unobtrusively on screen and reflects activity through animation: when agents are running, Tablo runs and shows the agent count; when a session's context window enters the danger zone (>60%), Tablo becomes alarmed. Tapping Tablo opens a panel with the live context-window meter. This avatar-plus-panel model replaces an always-on-top window, which would take up too much screen space.
This document is the build plan for Claude Code to follow. Phase 1 ships Tablo (the avatar) and the context meter only; later phases add permissions, plan usage, and a dashboard.
Project overview
Goal (Phase 1): A tiny always-on-top animated cat avatar that watches Claude Code session transcripts and reflects activity through its animation state. Tapping it opens a panel showing each active session's context-window fill as a live percentage bar, with a danger warning above 60%.
Interaction model — two surfaces:
- Avatar — a tiny (~64×64), transparent, always-on-top, click-through-except-on-the-cat window. Always visible. Animation is driven by live data (idle / running with agent count / alarmed).
- Panel — a second, larger window that toggles open near the avatar when the cat is tapped, and dismisses on tap-away or a second tap. Contains the context meter(s). Not always visible.
Stack:
- Tauri 2 (Rust backend + webview frontend) — chosen for small footprint, native always-on-top, transparency, and multi-window support.
- Frontend: plain HTML/CSS/JS or a lightweight framework (see Open Questions). Keep it minimal for Phase 1.
- File watching: Rust-side, using the
notifycrate to tail JSONL transcripts. - State bridge: Tauri events (
emit/listen) to push updates from Rust to both windows. - Avatar art: sprite-sheet or SVG/CSS animation (see Open Questions) — designed separately; the plan leaves an asset slot.
Non-goals for Phase 1: permission approval, plan/quota usage, dashboard, multi-machine/LAN. These are scoped in later phases so the architecture leaves room for them but does not build them yet.
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.
- 9d ago First seen · 369 lines · 6,137 tokens per session scan B 40f397cbebdc
tablo CLAUDE.md is an instructions file published in the GitHub repository unravel-team/tablo (23 stars, last pushed 9d ago), licensed MIT. It adds 6,137 tokens to every session, about $0.0307 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.