Borrowing it
Nothing to install: this file belongs to caspii/dinkydash. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/caspii/dinkydash/main/CLAUDE.mdgit clone --depth 1 https://github.com/caspii/dinkydashWrote 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/caspii/dinkydash/claude-md)<a href="https://agentmods.dev/instructions/caspii/dinkydash/claude-md"><img src="https://agentmods.dev/badge/instructions/caspii/dinkydash/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/caspii/dinkydash/claude-md"><img src="https://agentmods.dev/badge/instructions/caspii/dinkydash/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.07933 | $0.07933 |
| Opus 5.5 | $0.03173 | $0.03173 |
| Sonnet 5.5 | $0.01587 | $0.01587 |
| Haiku 4.5 | $0.00793 | $0.00793 |
Grade A, and why
dinkydash 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 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 — 491 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.
Overview
DinkyDash is a family dashboard for a screen on the wall. A daily cron job calls the Claude API to
write a headline; the Flask app renders that alongside today's agenda, whose
turn each chore is, and the countdowns — all recomputed from config.yaml at render time.
Three components:
- The engine (
dinkydash/) — pure functions plus the model call. No config file is read here, no clock consulted, nothing written to disk. - The web app (
web/) — the dashboard at/, a settings UI at/settingsthat writesconfig.yaml. - The marketing site (
website/) — dinkydash.co, a second Flask app rendering Markdown through Jinja on request. No build step and no committed HTML.
This repo is public and MIT-licensed, and the hosted multi-tenant SaaS is being built inside it, with self-hosting as the second mode of one codebase. Both facts constrain every change: see This is a public repo and Two modes, always below. Before making structural changes, read:
- the hosted MVP plan — settled decisions, phases and what is still open. A Linear document on the Dinky Dash team (DinkyDash Hosted MVP — Plan), because it tracks Linear issues; the engineering rules it rested on are in this file and the ones it points to.
- the strategy document — positioning, pricing, SEO. Not in the repo by policy: it is a Linear document on the Dinky Dash team. See Strategy and marketing live in Linear.
- design/ — mockups for the settings UI and the dashboard, with the reasoning
The other instruction files
This file is loaded on every task, so it holds only what applies to every change. The detail that matters in one place lives beside that place, and arrives when you open a file there:
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 Changed · -130 lines · -2,779 tokens per session scan C → A a88ca0dc5784
- 6d ago Changed · +3 lines · +54 tokens per session f3f3cc662f73
- 7d ago Changed · +9 tokens per session 20a687ef80af
- 22d ago Changed · +2 lines · +31 tokens per session f324ae96cfac
- 27d ago Changed · +12 lines · +285 tokens per session 3908a60ee038
- 1mo ago Changed · +2 lines · +31 tokens per session 7f9dbefa234b
- 1mo ago Changed · +25 lines · +476 tokens per session 19b326a4a0ed
- 1mo ago Changed · +13 lines · +326 tokens per session a56b7d70ba96
- 1mo ago Changed · +23 lines · +492 tokens per session e00164ba733e
- 1mo ago First seen · 541 lines · 9,008 tokens per session scan C 124ee5b5c418
dinkydash CLAUDE.md is an instructions file published in the GitHub repository caspii/dinkydash (99 stars, last pushed 2d ago), licensed MIT. It adds 7,933 tokens to every session, about $0.0317 per session on Opus 5.5. 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.
dinkydash CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dinkydash CLAUDE.mdcaspii/dinkydash | Instructions file | 99 | 2d ago | MIT | A | 7,933 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |