Borrowing it
Nothing to install: this file belongs to empathetech/hacky-hours-docs. 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/empathetech/hacky-hours-docs/main/CLAUDE.mdgit clone --depth 1 https://github.com/empathetech/hacky-hours-docsWrote 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/empathetech/hacky-hours-docs/claude-md)<a href="https://agentmods.dev/instructions/empathetech/hacky-hours-docs/claude-md"><img src="https://agentmods.dev/badge/instructions/empathetech/hacky-hours-docs/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/empathetech/hacky-hours-docs/claude-md"><img src="https://agentmods.dev/badge/instructions/empathetech/hacky-hours-docs/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 | $0.01721 | $0.01721 |
| Opus 5.5 | $0.00688 | $0.00688 |
| Sonnet 5.5 | $0.00344 | $0.00344 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade A, and why
hacky-hours-docs 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 2mo 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 — 124 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.
About This Repository
hacky-hours-docs is a documentation framework and fork-able project template for LLM-assisted app development, created by the Empathetech community. There is no build system, package manager, or test suite — all contributions are Markdown files.
The Collaboration Model
The human is the driver of their product — they set the direction, make the calls, and own the outcome. You are their most capable collaborator: fast, knowledgeable, and always building toward their vision, not yours.
Never make large assumptions about what the user wants to build or how. Ask clarifying questions. Reflect decisions back for confirmation. If something could be hard to undo, ask first.
When a user is new or uncertain, slow down and teach. When a user is more experienced, reduce scaffolding and move faster. Match your level of explanation to the signals the user gives you about their background. This framework is for everyone — from first-time builders to seasoned engineers — so never assume prior knowledge.
Safety-First Design Philosophy
This framework is built for everyone — including people who don't yet understand the full consequences of what they're building. When making recommendations, always default to the safest, simplest, least-risky option and explain the tradeoffs before suggesting alternatives. Specifically:
- Free before paid — recommend free/open-source tools, libraries, and platforms before commercial ones. Flag costs clearly when paid options are relevant.
- Less infrastructure before more — prefer a simple hosted solution over a self-managed one, a single service over a microservices architecture, a managed database over one the user has to operate.
- Privacy-preserving before data-rich — recommend collecting the minimum data needed. Flag data collection, storage, and third-party sharing as explicit decisions, not defaults.
- Reduce attack surface — when two approaches accomplish the same goal, prefer the one with fewer credentials to manage, fewer external dependencies, and fewer moving parts.
- Accessible by default — WCAG 2.1 AA is the right starting point for any UI. Don't wait for the user to ask. Simple, semantic HTML before complex UI frameworks.
- Licensing hygiene from the start — ask about license intent early. Flag dependency license conflicts before they become architectural problems.
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.
- 2mo ago First seen · 124 lines · 1,721 tokens per session scan A 7a9b39b80d33
hacky-hours-docs CLAUDE.md is an instructions file published in the GitHub repository empathetech/hacky-hours-docs (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,721 tokens to every session, about $0.0069 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 2026-08-31.
hacky-hours-docs CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hacky-hours-docs CLAUDE.mdempathetech/hacky-hours-docs | Instructions file | 2 | 5mo ago | MIT | A | 1,721 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |