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/superfly/sprites-ex/claude-mdgit clone --depth 1 https://github.com/superfly/sprites-exWrote 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/superfly/sprites-ex/claude-md)<a href="https://agentmods.dev/instructions/superfly/sprites-ex/claude-md"><img src="https://agentmods.dev/badge/instructions/superfly/sprites-ex/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 | $0.00504 | $0.00504 |
| Opus 5 | $0.00252 | $0.00252 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
sprites-ex 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 3d 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.
What it actually says
Sprites Elixir SDK
An Elixir SDK for the Sprites code container runtime - a remote code execution platform for interactive development.
Quick Reference
Common Commands
# Install dependencies
mix deps.get
# Compile
mix compile
# Run tests
mix test
# Format code (REQUIRED before committing)
mix format
# Generate docs
mix docs
Test CLI
cd test_cli
mix deps.get
mix escript.build
# Usage
export SPRITES_TOKEN=your-token
./test-cli create my-sprite
./test-cli -sprite my-sprite -output stdout echo hello
./test-cli destroy my-sprite
Integration Tests (with Go test harness)
export SPRITES_TEST_TOKEN=your-token
export SDK_TEST_COMMAND=/path/to/sprites-ex/test_cli/test-cli
# Run from the Go SDK directory
go test -v
Project Structure
lib/sprites/
├── sprites.ex # Main public API (entry point)
├── client.ex # HTTP client for REST API (uses Req)
├── sprite.ex # Sprite instance representation
├── command.ex # Command execution via WebSocket (GenServer, uses gun)
├── protocol.ex # Binary protocol codec for WebSocket messages
├── stream.ex # Lazy Stream interface for command output
└── errors.ex # Custom exceptions (APIError, CommandError, etc.)
Key Dependencies
- req - HTTP client for REST API calls
- gun - Erlang WebSocket/HTTP client for command execution
- jason - JSON encoding/decoding
Environment Variables
SPRITES_TOKEN- Authentication token for Sprites APISPRITES_TEST_TOKEN- Authentication token for testing
Version Requirements
- Elixir: 1.18.4-otp-27
- Erlang: 27.0.1
(See .tool-versions for asdf configuration)
API Defaults
- Base URL:
https://api.sprites.dev - HTTP timeout: 30 seconds
- Create sprite timeout: 120 seconds
- WebSocket upgrade timeout: 10 seconds
Code Style
- Always run
mix formatbefore committing - All public functions should have
@docand@spec - Follow standard Elixir conventions
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.
- 3d ago First seen · 92 lines · 504 tokens per session scan A 8daa33f8feed
sprites-ex CLAUDE.md is an instructions file published in the GitHub repository superfly/sprites-ex (22 stars, last pushed 7d ago), licensed MIT. It adds 504 tokens to every session, about $0.0025 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
axern AGENTS.md
Instructions for cofy-x/axern, covering axern agent contract, scope, minimum context, sources of truth and repository constraints.
nono AGENTS.md
AGENTS.md instructions for nolabs-ai/nono, covering nono - development guide, project overview, library vs cli boundary, build & test and build everything.
jido AGENTS.md
AGENTS.md instructions for agentjido/jido, covering agents.md - jido guide, intent, runtime baseline, commands and architecture snapshot.
zapcode CLAUDE.md
Instructions for TheUncharted/zapcode, covering claude.md, git, read agents.md first, codebase orientation and how to add a new language feature.
TakoVM CLAUDE.md
Instructions for Tako-Research/TakoVM, covering tako vm, why gvisor?, architecture, key concepts and build & test.
excessibility CLAUDE.md
Instructions for lessthanseventy/excessibility, covering claude.md, project overview, development commands, testing and run all tests.