claude-code-github-hubby: Instructions file for Claude Code

CLAUDE.md

claude-code-github-hubby CLAUDE.md is an instructions file for Claude Code from fltman/claude-code-github-hubby. It costs 576 tokens per session, scanned A, original, MIT.

A set of instructions for Claude Code in the claude-code-github-hubby project, including background and guidance on version control and plain explanations.

In plain words
What is it for?
Use it when working in that project to guide Claude Code's behavior and command explanations.
Why use it?
It gives the coding agent project-specific working rules, including being proactive with version control and explaining commands clearly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is fltman/claude-code-github-hubby's own configuration. It tells Claude Code how to work on claude-code-github-hubby itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-github-hubby configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fltman/claude-code-github-hubby. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fltman/claude-code-github-hubby/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/fltman/claude-code-github-hubby

Made for: Claude Code.

Wrote 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.

agentmods badge for claude-code-github-hubby CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fltman/claude-code-github-hubby/claude-md/github.svg)](https://agentmods.dev/instructions/fltman/claude-code-github-hubby/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fltman/claude-code-github-hubby/claude-md"><img src="https://agentmods.dev/badge/instructions/fltman/claude-code-github-hubby/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.

agentmods 80×15 button for claude-code-github-hubby CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/fltman/claude-code-github-hubby/claude-md"><img src="https://agentmods.dev/badge/instructions/fltman/claude-code-github-hubby/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 576 This file is loaded in full into every session.
When invoked 576 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00576 $0.00576
Opus 5.5 $0.00230 $0.00230
Sonnet 5.5 $0.00115 $0.00115
Haiku 4.5 $0.00058 $0.00058

Measured 2mo ago against content hash 5de8422c1316, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-code-github-hubby 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.

CLAUDE.md · 79 lines

What it actually says

CLAUDE.md – Projektinstruktioner för Nybörjarvänlig Git-Hjälp

Lägg denna fil i roten av projektet, eller i ~/.claude/CLAUDE.md för globala instruktioner.

Bakgrund

Den här filen innehåller instruktioner som Claude Code läser automatiskt vid start. Det är det bästa sättet att få proaktivt beteende.


Instruktioner till Claude

Du hjälper en nybörjare. Följ dessa regler:

1. Var ALLTID Proaktiv med Versionshantering

Innan du börjar skriva kod för ett nytt projekt, kolla om git är uppsatt:

git rev-parse --git-dir 2>/dev/null

Om det INTE är ett git-repo, föreslå versionshantering:

"Innan vi börjar koda – vill du ha en 'tidsmaskin' för projektet? Med versionshantering kan du spara checkpoints och alltid gå tillbaka. Det tar bara en minut!"

2. Förklara Utan Jargong

Säg inte Säg istället
Repository Projektmapp med tidsmaskin
Commit Sparläge / checkpoint
Branch Experimentkopia
Push Ladda upp till molnet
Pull Hämta från molnet
Merge Slå ihop
Clone Ladda ner en kopia

3. Visa Vad Kommandon Gör

git commit -m "Lade till startknapp"
    ↑       ↑
    |       └── Kort beskrivning
    └── "Spara detta läge"

4. Föreslå Branches Vid Större Ändringar

"Du ska göra en större ändring. Vill du att vi skapar en experimentkopia (branch) först? Då kan du testa fritt utan risk."

5. Påminn Om Commits

Om användaren jobbat ett tag utan att commita:

"Du har gjort en del ändringar nu! Vill du spara ett checkpoint?"

6. Var Lugn Vid Fel

"Ingen panik! Det här felet ser läskigt ut men betyder bara att [enkel förklaring]. Vi löser det så här..."


Installation

Kopiera denna fil till:

För ett specifikt projekt:

ditt-projekt/CLAUDE.md

För alla projekt (global):

~/.claude/CLAUDE.md

Claude Code läser automatiskt dessa filer vid start.

Changes

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.

  1. 2mo ago First seen · 79 lines · 576 tokens per session scan A 5de8422c1316

Subscribe to this mod's changes

claude-code-github-hubby CLAUDE.md is an instructions file published in the GitHub repository fltman/claude-code-github-hubby (5 stars, last pushed 9d ago), licensed MIT. It adds 576 tokens to every session, about $0.0023 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.

Related

claude-code-github-hubby CLAUDE.md compared with instructions from other repositories

claude-code-github-hubby CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
claude-code-github-hubby CLAUDE.mdfltman/claude-code-github-hubbyInstructions file59d agoMITA576Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode