Borrowing it
Nothing to install: this file belongs to juliandickie/creators-studio. 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/juliandickie/creators-studio/main/CLAUDE.mdgit clone --depth 1 https://github.com/juliandickie/creators-studioWrote 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/juliandickie/creators-studio/claude-md)<a href="https://agentmods.dev/instructions/juliandickie/creators-studio/claude-md"><img src="https://agentmods.dev/badge/instructions/juliandickie/creators-studio/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 | $0.19740 | $0.19740 |
| Opus 5 | $0.09870 | $0.09870 |
| Sonnet 5 | $0.03948 | $0.03948 |
| Haiku 4.5 | $0.01974 | $0.01974 |
Grade C, and why
creators-studio CLAUDE.md scanned grade C with 3 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 8d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **v4.2.2 config dir auto-migration** (`~/.banana/` → `~/.creators-studio/`): the user state directory now matches the v4.0.0 plugin rebrand. Single source of truth: `scripts/paths.py::creators_studio_dir()`. On first c Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `skills/create-image/scripts/generate.py` | Direct Gemini API fallback for generation. Uses urllib.request (stdlib). | Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **v3.8.4 Replicate video cost-tracking dispatch**: `cost_tracker.py::_lookup_cost()` now branches on which key is present in the model's PRICING entry - `per_second` (Replicate video models: Kling $0.02/s, DreamActor $ How it starts
The opening of the file, as written. The whole thing — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md -- Development context for creators-studio
This file is read by Claude Code when working inside this repository.
Start every session by reading PROGRESS.md -- it has full development
history, design decisions, and next steps.
Third-party API reference (workspace-level)
Full LLMS documentation for integrated and evaluated third-party APIs lives at
../dev-docs/ (workspace root, one level above this repo). Always check
../CLAUDE.md's dev-docs inventory BEFORE updating prompt-engineering
references, answering model-capability questions, or planning an empirical
spike - the authoritative answer is often already pinned locally.
Specifically:
../dev-docs/nano-banana-image-generation.mdis the official Google Gemini 3.1 Flash Image prompting guide. Consult it before editingskills/create-image/references/prompt-engineering.mdor making any claim about Gemini 3.1 behaviour. Spike 6 in v3.7.3 would have been unnecessary if this file had been read first - the "describe the scene, don't list keywords" rule was already in the official guide.../dev-docs/google-nano-banana-2-llms.mdis the Replicate model card confirming the Replicategoogle/nano-banana-2is the samegemini-3.1-flash-image-previewmodel as the direct Gemini API path.../dev-docs/elevenlabs-best-practices.mdis the condensed ElevenLabs prompt-engineering guide - consult before tuning narration tags or voice design prompts.
Other files in dev-docs/ cover ElevenLabs (full API), Google ADK (reference
only - not adopted), Replicate (OpenAPI schema + MCP server install guide),
and ByteDance Seedance 2.0 (v3.8.0 bake-off candidate). Most are large - query
via Explore subagent, not Read. The full inventory and when-to-consult table
is the single source of truth in ../CLAUDE.md - do not duplicate it here.
What this repo is
creators-studio is a Claude Code plugin that enables AI image generation
using Google's Gemini Nano Banana models via MCP. Claude acts as a Creative
Director: it interprets intent, selects domain expertise, constructs
optimized prompts, and orchestrates Gemini API calls.
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.
- 8d ago First seen · 497 lines · 19,740 tokens per session scan C 226a2396da11
creators-studio CLAUDE.md is an instructions file published in the GitHub repository juliandickie/creators-studio (2 stars, last pushed 1mo ago), licensed MIT. It adds 19,740 tokens to every session, about $0.0987 per session on Opus 5. A static security scan graded it C with 3 findings (recursive force delete, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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).
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).
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.
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.