Borrowing it
Nothing to install: this file belongs to Hainrixz/claude-banana. 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/Hainrixz/claude-banana/main/CLAUDE.mdgit clone --depth 1 https://github.com/Hainrixz/claude-bananaWrote 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/hainrixz/claude-banana/claude-md)<a href="https://agentmods.dev/instructions/hainrixz/claude-banana/claude-md"><img src="https://agentmods.dev/badge/instructions/hainrixz/claude-banana/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/hainrixz/claude-banana/claude-md"><img src="https://agentmods.dev/badge/instructions/hainrixz/claude-banana/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 | $0.00691 | $0.00691 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
claude-banana 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 12d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Banana
Claude Banana is an AI image prompt engineering agent. It helps users craft optimized prompts for image generation models — primarily Nano Banana Pro (Gemini image models) but compatible with any image generator.
How It Works
When a user provides a prompt idea, image reference, or existing prompt to refine, the prompt-architect agent:
- Intake — Classifies intent (new prompt, refinement, image reference, platform adaptation)
- Interview — Asks 2-4 targeted clarifying questions (mood, domain, must-have elements)
- Compose — Builds an optimized prompt using the 7-component formula with domain-specific weights
- Present — Outputs a copyable master prompt with rationale and variation suggestions
- Iterate — Accepts adjustments without starting from scratch
Using the Agent
Start Claude Code in this project directory. The prompt-architect agent and knowledge base are automatically available. Just describe what image you want to create:
"Help me create a prompt for a moody portrait of a jazz musician"
File Layout
knowledge/ — The brain: prompt engineering reference material
prompt-formula.md — 7-component formula with weights and construction template
prompt-engineering.md — Master reference: specificity, detail, anchoring, composition, lighting
domain-modes.md — 9 domain profiles with weight adjustments and routing
techniques-catalog.md — 70+ techniques organized by category
anti-patterns.md — Banned keywords, 10 critical mistakes to avoid
model-notes.md — Model routing, capabilities, limitations, pricing
safety-and-text.md — Text rendering rules, safety filter navigation
platform-adaptation.md — Converting prompts from Midjourney/DALL-E/SD
post-processing.md — ImageMagick/FFmpeg post-processing recipes
templates/examples/ — 25 parameterized prompt templates covering all domains
presets/ — Brand/style preset JSON files
scripts/ — Python utilities for generation, editing, batch processing
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.
- 12d ago First seen · 58 lines · 691 tokens per session scan A 050b37d882af
claude-banana CLAUDE.md is an instructions file published in the GitHub repository Hainrixz/claude-banana (96 stars, last pushed 5mo ago), licensed MIT. It adds 691 tokens to every session, about $0.0035 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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.
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).