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/baradusov/pochem/claude-mdgit clone --depth 1 https://github.com/baradusov/pochemWrote 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/baradusov/pochem/claude-md)<a href="https://agentmods.dev/instructions/baradusov/pochem/claude-md"><img src="https://agentmods.dev/badge/instructions/baradusov/pochem/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 5.1 | $0.00987 | $0.00987 |
| Opus 5 | $0.00494 | $0.00494 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
pochem 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 6d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Instructions
Philosophy
This codebase will outlive you. Every shortcut becomes someone else's burden. Every hack compounds into technical debt that slows the whole team down.
You are not just writing code. You are shaping the future of this project. The patterns you establish will be copied. The corners you cut will be cut again.
Fight entropy. Leave the codebase better than you found it.
Architecture
┌─────────────────────────────────────────────────────────┐
│ UI Layer (screens/, components/) │
│ - Screens and UI components │
│ - Only renders, no business logic │
│ - Calls store methods, observes state │
├─────────────────────────────────────────────────────────┤
│ Adapters (hooks/, controllers/) │
│ - Thin adapters between UI framework and stores │
│ - useAuth(), useProfile(), etc. │
├─────────────────────────────────────────────────────────┤
│ Core (core/) │
│ - Business logic lives here │
│ - Stores orchestrate everything │
│ - MUST be framework-agnostic │
│ - Could be extracted to CLI/API without changes │
├─────────────────────────────────────────────────────────┤
│ Infrastructure (infrastructure/) │
│ - Implements ports (interfaces) from core │
│ - Database adapters, external API adapters │
│ - Can be swapped without touching business logic │
└─────────────────────────────────────────────────────────┘
Rules
-
core/ imports nothing from UI framework or infrastructure/
- Business logic must be portable
- Use dependency injection via ports
-
UI layer has no business logic
- Components only render and call store methods
- No data transformations in components
- No API calls in components
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.
- 6d ago First seen · 147 lines · 987 tokens per session scan A 7b193d227936
pochem CLAUDE.md is an instructions file published in the GitHub repository baradusov/pochem (5 stars, last pushed 4mo ago), licensed MIT. It adds 987 tokens to every session, about $0.0049 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
frankfurter AGENTS.md
AGENTS.md instructions for lineofflight/frankfurter, covering frankfurter, before you write code, architecture, project structure and key components.
frankfurter CLAUDE.md
Claude Code instructions for lineofflight/frankfurter, a project described as: 💱 Currency data API.
karakeep AGENTS.md
AGENTS.md instructions for karakeep-app/karakeep, covering karakeep project overview, project overview, project structure, applications (apps/) and packages (packages/).
rozenite AGENTS.md
AGENTS.md instructions for callstackincubator/rozenite, a project described as: Plug-and-play panels for React Native DevTools. Install, enable, and start debugging in minutes.
react-native-restart AGENTS.md
Instructions for avishayil/react-native-restart: This project keeps its agent/AI onboarding guidance in a single canonical file.
karakeep CLAUDE.md
Claude Code instructions for karakeep-app/karakeep, a project described as: A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search.