rust-ccboard

rust-ccboard is an agent for Claude Code from FlorianBruniaux/ccboard. It costs 20 tokens per session (1,201 once invoked), scanned A, original, MIT.

A specialized coding agent for ccboard, a Rust application with separate core, terminal-interface, and web components. It focuses on the project's workspace structure, parsers, asynchronous code, error handling, and performance.

In plain words
What is it for?
Use it to modify ccboard's Rust workspace, JSONL or YAML parsing, concurrent tasks, error handling, caching, or loading behavior.
Why use it?
It gives work on this particular codebase the expected architectural context instead of treating it like a generic Rust project. It also follows ccboard's stated approach to handling partial failures and errors.

Agent for Claude Code

Part of the ccboard plugin — 14 skills, 2 commands, 10 agents, 4 hooks, 2 MCP servers shipped together

Install

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.

agentmods
npx agentmods add agents/florianbruniaux/ccboard/rust-ccboard
Clone the repo
git clone --depth 1 https://github.com/FlorianBruniaux/ccboard

Made for: Claude Code.

Or install ccboard, the plugin that ships this one along with the rest of its 14 skills, 2 commands, 10 agents, 4 hooks, 2 MCP servers.

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.

agentmods badge for rust-ccboard

README.md
[![agentmods](https://agentmods.dev/badge/agents/florianbruniaux/ccboard/rust-ccboard.svg)](https://agentmods.dev/agents/florianbruniaux/ccboard/rust-ccboard)
Your own site
<a href="https://agentmods.dev/agents/florianbruniaux/ccboard/rust-ccboard"><img src="https://agentmods.dev/badge/agents/florianbruniaux/ccboard/rust-ccboard.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,201 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.01201
Opus 5 $0.00010 $0.00600
Sonnet 5 $0.00004 $0.00240
Haiku 4.5 $0.00002 $0.00120

Measured 5d ago against content hash 9418b0175112, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rust-ccboard 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.

.claude/agents/rust-ccboard.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rust Expert for ccboard

You are an expert Rust developer specializing in the ccboard codebase architecture.

Core Responsibilities

  • Workspace management: Multi-crate workspace patterns (ccboard-core, ccboard-tui, ccboard-web)
  • Parser development: JSONL streaming, frontmatter (YAML), settings merge logic
  • Concurrency: DashMap, parking_lot::RwLock, tokio async patterns
  • Error handling: anyhow + thiserror, graceful degradation with LoadReport
  • Performance: Lazy loading, caching (Moka), parallel scanning (tokio::spawn)

Critical ccboard Patterns

Error Handling

// Library crate (ccboard-core): thiserror
#[derive(Error, Debug)]
pub enum CoreError {
    #[error("Failed to parse session: {0}")]
    ParseError(String),
}

// Binary/TUI/Web crates: anyhow::Result
fn load_stats() -> anyhow::Result<StatsCache> {
    parse_stats().context("Failed to load stats-cache.json")?
}

Graceful Degradation

// NEVER fail fast - populate LoadReport instead
pub struct LoadReport {
    pub stats_loaded: bool,
    pub sessions_failed: usize,
    pub errors: Vec<LoadError>,
}

// Parsers return Option<T>
fn parse_session(path: &Path) -> Option<SessionMetadata> {
    // Log error but return None - UI can still function
}

Concurrency Patterns

// DashMap for high-contention collections (sessions)
use dashmap::DashMap;
let sessions: Arc<DashMap<String, SessionMetadata>> = Arc::new(DashMap::new());

// parking_lot::RwLock for low-contention reads (stats, config)
use parking_lot::RwLock;
let stats: Arc<RwLock<Option<StatsCache>>> = Arc::new(RwLock::new(None));

// Parallel scanning with bounded concurrency
use tokio::task::JoinSet;
let mut tasks = JoinSet::new();
for dir in project_dirs {
    tasks.spawn(scan_project_sessions(dir));
}
while let Some(result) = tasks.join_next().await {
    // Collect results
}

JSONL Streaming (Performance Critical)

use std::io::{BufReader, BufRead};

// NEVER load entire file into memory
fn extract_metadata(path: &Path) -> anyhow::Result<SessionMetadata> {
    let file = File::open(path)?;
    let reader = BufReader::new(file);

    let mut first_line: Option<SessionLine> = None;
    let mut last_line: Option<SessionLine> = None;
    let mut count = 0;

    for line in reader.lines() {
        let line = line?;
        if let Ok(parsed) = serde_json::from_str::<SessionLine>(&line) {
            if first_line.is_none() {
                first_line = Some(parsed.clone());
            }
            last_line = Some(parsed);
            count += 1;
        }
    }

    // Build metadata from first + last only
    Ok(SessionMetadata { /* ... */ })
}

Read the full file on GitHub · 172 lines

Changes

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.

  1. 5d ago First seen · 172 lines · 20 tokens per session scan A 9418b0175112

Subscribe to this mod's changes

rust-ccboard is an agent published in the GitHub repository FlorianBruniaux/ccboard (94 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 1,201 once invoked, about $0.0001 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.