Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/florianbruniaux/ccboard/claude-md)<a href="https://agentmods.dev/instructions/florianbruniaux/ccboard/claude-md"><img src="https://agentmods.dev/badge/instructions/florianbruniaux/ccboard/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 | $0.05316 | $0.05316 |
| Opus 5 | $0.02658 | $0.02658 |
| Sonnet 5 | $0.01063 | $0.01063 |
| Haiku 4.5 | $0.00532 | $0.00532 |
Grade B, and why
ccboard CLAUDE.md scanned grade B with 1 finding 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 6d 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.
| Global settings | `~/.claude/settings.json` | `SettingsParser` | JSON with merge | How it starts
The opening of the file, as written. The whole thing — 493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
ccboard is a unified dashboard for Claude Code management, providing both TUI and web interfaces from a single binary to visualize sessions, stats, configuration, hooks, agents, costs, and history from ~/.claude directories.
Stack: Rust workspace with 4 crates, Ratatui (13-tab TUI), Axum (Web API backend), Leptos (WASM frontend), Arc + parking_lot for concurrency.
Workspace Architecture
This is a Cargo workspace with a layered architecture:
ccboard/ # Root binary - CLI entry point
├─ ccboard-core/ # Shared data layer (parsers, models, store, watcher)
├─ ccboard-tui/ # Ratatui frontend (13 tabs)
└─ ccboard-web/ # Axum API backend + Leptos WASM frontend
Dependency flow: ccboard → ccboard-tui + ccboard-web → ccboard-core
Core principle: Single binary, dual frontends sharing a thread-safe DataStore.
Development Commands
Build & Run
# Build all crates
cargo build --all
# Run TUI (default mode)
cargo run
# Run web interface
cargo run -- web --port 3333
# Run both TUI and web
cargo run -- both --port 3333
# Print stats and exit
cargo run -- stats
# Session management commands
cargo run -- search "query" --limit 10 # Search sessions
cargo run -- search "bug" --since 7d # Search last 7 days
cargo run -- recent 10 # Show 10 most recent sessions
cargo run -- recent 5 --json # JSON output
cargo run -- info <session-id> # Show session details
cargo run -- resume <session-id> # Resume session in Claude CLI
cargo run -- clear-cache # Clear SQLite cache
# Specify Claude home directory
cargo run -- --claude-home ~/.claude --project /path/to/project
# Frontend (Leptos/WASM)
trunk serve --port 3333 # Serve frontend on http://127.0.0.1:3333
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.
- 6d ago First seen · 493 lines · 5,316 tokens per session scan B d2bf2e81c97d
ccboard CLAUDE.md is an instructions file published in the GitHub repository FlorianBruniaux/ccboard (95 stars, last pushed 4d ago), licensed MIT. It adds 5,316 tokens to every session, about $0.0266 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
Commit Message
Comprehensive Conventional Commits guidelines for openwebui-extensions.
framework AGENTS.md
AGENTS.md instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.
claude-crusts CLAUDE.md
Claude Code instructions for Abinesh-L/claude-crusts, covering identity, cli commands, rules, format and architecture.
3notch AGENTS.md
Instructions for coldlogicAI/3notch, covering 3notch agent guide, purpose, read first, long-run goal and shipped surface (build this, nothing else).
ai-readiness-assessment AGENTS.md
Instructions for techtalk/ai-readiness-assessment, covering agents.md, gotchas, workflows, changing the instrument and cutting a release.
ZipAI CLAUDE.md
Claude Code instructions for nickdesi/ZipAI, covering claude.md — zipai: ultra-dense token optimizer, rules, 1. zero filler, 2. ambiguity and 3. prompt caching.