Borrowing it
Nothing to install: this file belongs to Ephemeral-AI-Lab/ephemeral-sandbox. 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/Ephemeral-AI-Lab/ephemeral-sandbox/main/CLAUDE.mdgit clone --depth 1 https://github.com/Ephemeral-AI-Lab/ephemeral-sandboxWrote 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/ephemeral-ai-lab/ephemeral-sandbox/claude-md)<a href="https://agentmods.dev/instructions/ephemeral-ai-lab/ephemeral-sandbox/claude-md"><img src="https://agentmods.dev/badge/instructions/ephemeral-ai-lab/ephemeral-sandbox/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/ephemeral-ai-lab/ephemeral-sandbox/claude-md"><img src="https://agentmods.dev/badge/instructions/ephemeral-ai-lab/ephemeral-sandbox/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 | $0.01203 | $0.01203 |
| Opus 5 | $0.00602 | $0.00602 |
| Sonnet 5 | $0.00241 | $0.00241 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
ephemeral-sandbox 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 11d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for working in this repository. Read
docs/maintainer-architecture.md for the component map and boundary law; this
file covers how to write and change code here.
Project
Rust workspace (edition 2021, rust-version 1.85) for the EphemeralOS sandbox.
Crates live under crates/; see the component table in
docs/maintainer-architecture.md for each crate's job and what it must never
do. Respect those boundaries — a change that crosses them is wrong even if it
compiles.
Engineering practice (required)
- SOLID, SRP first. Every type, module, and function owns one
responsibility. If you cannot name a unit's single job in one sentence, split
it. Keep crate boundaries from
docs/maintainer-architecture.mdintact; depend on the narrowest abstraction, not a concrete implementation crate. - Prefer less. Fewer fields, fewer types, fewer methods, fewer round trips. Before adding a field/struct/method, check whether an existing one already carries the responsibility. Collapse redundant indirection and avoid extra hops across the manager/daemon/runtime boundary when one suffices.
- No inline comments in production code. Names and types carry the meaning;
if code needs an inline comment to be understood, restructure it instead.
Doc comments (
//////!) on public items are fine. Inline comments are acceptable only in tests, where they explain intent of a scenario. - No test code in
src/. Keepsrc/production-only. Inline test modules (#[cfg(test)] mod tests), test support/helpers, and fakes/mocks/stubs belong in the crate'stests/directory, never undersrc/. Move any such code totests/; share fixtures through atests/support module, not asrcitem gated behindcfg(test). - Parallel workers. Other agents may be editing this repo concurrently. Only touch what your task requires, never revert or overwrite changes you did not make, and prefer additive, localized edits.
- Work on
main. Always work, commit, and push directly on themainbranch. Never create side branches (includingagent/*) or additional git worktrees. If another checkout ownsmain, use that existingmaincheckout instead of branching.
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.
- 11d ago First seen · 99 lines · 1,203 tokens per session scan A 977b3c00ee04
ephemeral-sandbox CLAUDE.md is an instructions file published in the GitHub repository Ephemeral-AI-Lab/ephemeral-sandbox (94 stars, last pushed 1mo ago), licensed MIT. It adds 1,203 tokens to every session, about $0.0060 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.
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.