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/empathetech/hacky-hours-docs/claude-mdgit clone --depth 1 https://github.com/empathetech/hacky-hours-docsWhat 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 | $0.01721 | $0.01721 |
| Opus 5 | $0.00860 | $0.00860 |
| Sonnet 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 2d 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.
- 2d 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 3mo ago), licensed MIT. It adds 1,721 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.