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 instructions/antjanus/cc-dash/claude-mdgit clone --depth 1 https://github.com/AntJanus/cc-dashWrote 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/antjanus/cc-dash/claude-md)<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>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 | $0.01725 | $0.01725 |
| Opus 5 | $0.00863 | $0.00863 |
| Sonnet 5 | $0.00345 | $0.00345 |
| Haiku 4.5 | $0.00172 | $0.00172 |
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.
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,
.envvalues, real emails (beyond intended author attribution), internal/employer identifiers, or absolute paths containing a username (/Users/<user>/...). - When in doubt, run the
/publish-checkprivacy 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
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.
- 3d ago First seen · 121 lines · 1,725 tokens per session scan A b1c4de57444b
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.
Other instructions, from other repositories
ESAA-Core AGENTS.md
Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.
Kanvas AGENTS.md
Instructions for XMihura/Kanvas, covering canvas workflow — agent instructions, critical rule, session protocol, 1. start of session — read the board and 2. pick a task.
delivery-loop CLAUDE.md
Instructions for blakemartz/delivery-loop, covering claude.md, what this is, the cardinal rule: everything must stay repo-agnostic, layout and config: the one seam.
taskcenter AGENTS.md
AGENTS.md instructions for xiaogezi/taskcenter, covering taskcenter agent rules, safety boundaries, required workflow and verification.
idd-skill idd-resume.instructions.md
Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.
codecrucible AGENTS.md
Instructions for block/codecrucible, covering agent instructions, quick reference and landing the plane (session completion).