cc-dash CLAUDE.md

cc-dash CLAUDE.md is an instructions file for coding agents from AntJanus/cc-dash. It costs 1,725 tokens per session, scanned A, original, MIT.

A set of instructions for working on cc-dash, a local web dashboard that combines project planning files into one board. It also describes the project’s commands, technologies, and privacy requirements.

In plain words
What is it for?
Use it when changing cc-dash, running its development, build, lint, or test commands, or checking changes for secrets and personal information before publishing.
Why use it?
It gives an agent the project context and rules needed to develop safely, especially because the repository is public and committed information cannot be kept private.

Instructions file

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 instructions/antjanus/cc-dash/claude-md
Clone the repo
git clone --depth 1 https://github.com/AntJanus/cc-dash

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 cc-dash CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/antjanus/cc-dash/claude-md.svg)](https://agentmods.dev/instructions/antjanus/cc-dash/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/antjanus/cc-dash/claude-md"><img src="https://agentmods.dev/badge/instructions/antjanus/cc-dash/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,725 This file is loaded in full into every session.
When invoked 1,725 The same file — it is already loaded in full.
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 $0.01725 $0.01725
Opus 5 $0.00863 $0.00863
Sonnet 5 $0.00345 $0.00345
Haiku 4.5 $0.00172 $0.00172

Measured 3d ago against content hash b1c4de57444b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cc-dash 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 3d 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.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — cc-dash

Repository Visibility: PUBLIC

This repo is PUBLIC on GitHub (AntJanus/cc-dash). Everything committed here is world-readable and permanent.

  • Before every commit, scrub PII and secrets: no API keys, tokens, .env values, real emails (beyond intended author attribution), internal/employer identifiers, or absolute paths containing a username (/Users/<user>/...).
  • When in doubt, run the /publish-check privacy scan over the diff before pushing.

Project Overview

cc-dash is a local Next.js web dashboard that aggregates ROADMAP.md and SESSION_PROGRESS.md files across 20+ projects into a single Kanban/CRUD interface. All project state lives in markdown files; the dashboard is a lens, not a database.

Status: v3.0 shipped (1247 tests). v2.0 complete (14 phases), v3.0 adds AI integration and portfolio intelligence.

Stack: Next.js 15 (App Router) + TypeScript + Tailwind CSS v4 + Zod v4 + Vitest 4.x

Development Commands

npm install              # Install dependencies
npm run dev              # Next.js dev server at localhost:3737
npm run build            # Production build
npm run lint             # ESLint
npm run test:run         # Run all tests (1247 tests)
npm test                 # Watch mode
npm run format:check     # Prettier check

Architecture

src/
├── app/                         # Next.js App Router pages
│   ├── layout.tsx               # Root layout with sidebar nav + auto-refresh provider
│   ├── page.tsx                 # Dashboard home (project grid)
│   ├── activity/page.tsx        # Milestone timeline
│   ├── agents/page.tsx          # Agent activity feed (Co-Authored-By parsing)
│   ├── api/watch/route.ts       # File change detection API (mtime fingerprint)
│   ├── ideas/                   # Ideas system pages
│   ├── metrics/page.tsx         # Portfolio metrics dashboard
│   ├── settings/page.tsx        # Settings page
│   ├── today/page.tsx           # Today screen (directions panel + Up Next + pulse lanes)
│   └── project/[slug]/
│       ├── layout.tsx           # Project layout with tabs
│       ├── roadmap/page.tsx     # Roadmap board/list view
│       └── session/page.tsx     # Session progress view
├── components/
│   ├── agents/                  # Agent activity feed, commit list, filters
│   ├── ideas/                   # Idea cards, grid, wizard, forms
│   ├── metrics/                 # Status chart, velocity, progress, stale list
│   ├── projects/                # Dashboard home cards, grid, filters
│   ├── prompt/                  # Prompt generation modal/buttons
│   ├── roadmap/                 # Board columns, cards, list view, editor
│   ├── session/                 # Task list, status, decisions, verification
│   ├── today/                   # Directions panel, recommended lane, QA checkboxes, copyable commands
│   ├── shared/                  # Status badges, refresh button, auto-refresh provider
│   └── ui/                      # Base UI primitives (accordion, button, etc.)
└── lib/
    ├── actions/                 # Next.js Server Actions for CRUD
    ├── activity/                # Milestone timeline + agent activity (git log parsing)
    ├── config.ts                # Config loading (~/.config/cc-dash/config.json)
    ├── fs/
    │   ├── parser.ts            # Markdown parsing (gray-matter + regex)
    │   ├── serializer.ts        # Markdown generation (preserves unrecognized content)
    │   ├── discovery.ts         # Project scanning with slug generation
    │   ├── atomic-write.ts      # Safe writes (write .tmp then rename)
    │   ├── discovery-cache.ts   # In-memory discovery cache
    │   ├── file-fingerprint.ts  # File mtime fingerprinting for auto-refresh
    │   └── portfolio.ts         # Portfolio metadata (.cc-dash/portfolio.json)
    ├── metrics/                 # Portfolio-level aggregate metrics computation
    ├── prompt/                  # Prompt assembly for Claude Code
    ├── schemas/                 # Zod schemas (roadmap, session, ideas, config, portfolio)
    └── utils/                   # ID generation, helpers

Read the full file on GitHub · 121 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. 3d ago First seen · 121 lines · 1,725 tokens per session scan A b1c4de57444b

Subscribe to this mod's changes

cc-dash CLAUDE.md is an instructions file published in the GitHub repository AntJanus/cc-dash (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,725 tokens to every session, about $0.0086 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 2026-08-31.