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 agents/florianbruniaux/ccboard/rust-ccboardgit clone --depth 1 https://github.com/FlorianBruniaux/ccboardWrote 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/agents/florianbruniaux/ccboard/rust-ccboard)<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>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 | $0.00020 | $0.01201 |
| Opus 5 | $0.00010 | $0.00600 |
| Sonnet 5 | $0.00004 | $0.00240 |
| Haiku 4.5 | $0.00002 | $0.00120 |
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.
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 { /* ... */ })
}
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 · 172 lines · 20 tokens per session scan A 9418b0175112
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.
Other agents, from other repositories
gsd-phase-researcher
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.
gsd-project-researcher
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.
apm-primitives-architect
Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…
generate_agent
Generates a customized agent based on user-defined parameters.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
replanner
Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.