agentmods.dev

sandbox-agent CLAUDE.md

An instruction file for Sandbox Agent, a server product that provides coding-agent features to client applications. It sets naming rules and explains which terms, protocols, and implementation details should appear in user-facing documentation.

In plain words
What is it for?
Use it when writing or reviewing Sandbox Agent documentation, SDK guides, HTTP or command-line examples, and pages about its client-facing features.
Why use it?
It prevents documentation from using the wrong product names, exposing internal protocol details, or breaking the project’s wording and style rules. It also identifies the accepted public interface as the source of truth for HTTP and command-line documentation.

Instructions file

1.6k +4 2mo ago A scan 1,291 tokens original Apache-2.0
View the source file rivet-dev/sandbox-agent
Install

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.

agentmods
npx agentmods add instructions/rivet-dev/sandbox-agent/claude-md
Clone the repo
git clone --depth 1 https://github.com/rivet-dev/sandbox-agent
Per session 1,291 This file is loaded in full into every session.
When invoked 1,291 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.01291 $0.01291
Opus 5 $0.00646 $0.00646
Sonnet 5 $0.00258 $0.00258
Haiku 4.5 $0.00129 $0.00129

Measured 2d ago against content hash a5fe3a309024, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sandbox-agent CLAUDE.md scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Sandbox Agent install/version references use a pinned minor channel `0.N.x` (for curl URLs and `sandbox-agent` / `@sandbox-agent/cli` npm/bun installs).
CLAUDE.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions

Naming and Ownership

  • This repository/product is Sandbox Agent.
  • Gigacode is a separate user-facing UI/client, not the server product name.
  • Gigacode integrates with Sandbox Agent via the OpenCode-compatible surface (/opencode/*) when that compatibility layer is enabled.
  • Canonical extension namespace/domain string is sandboxagent.dev (no hyphen).
  • Canonical custom ACP extension method prefix is _sandboxagent/... (no hyphen).

Docs Terminology

  • Never mention "ACP" in user-facing docs (docs/**/*.mdx) except in docs that are specifically about ACP itself (e.g. docs/acp-http-client.mdx).
  • Never expose underlying protocol method names (e.g. session/request_permission, session/create, _sandboxagent/session/detach) in non-ACP docs. Describe the behavior in user-facing terms instead.
  • Do not describe the underlying protocol implementation in docs. Only document the SDK surface (methods, types, options). ACP protocol details belong exclusively in ACP-specific pages.
  • Do not use em dashes (—) in docs. Use commas, periods, or parentheses instead.

Docs Source Of Truth (HTTP/CLI)

  • For HTTP/CLI docs/examples, source of truth is:
    • server/packages/sandbox-agent/src/router.rs
    • server/packages/sandbox-agent/src/cli.rs
  • Keep docs aligned to implemented endpoints/commands only (for example ACP under /v1/acp, not legacy session REST APIs).

Docs Styling

  • Docs styling is owned by the shared @rivet-dev/docs-theme repo (github.com/rivet-dev/docs-theme), consumed via github:rivet-dev/docs-theme#<tag> in frontend/packages/website. To change any docs styling (palette, header, sidebar, code blocks, fonts), edit that repo and follow its CLAUDE.md release workflow — never restyle docs here. This site owns only docs content + frontend/packages/website/docs.config.mjs (sidebar icons via each item's attrs['data-icon']).

Change Tracking

  • If the user asks to "push" changes, treat that as permission to commit and push all current workspace changes, not a hand-picked subset, unless the user explicitly scopes the push.
  • Keep CLI subcommands and HTTP endpoints in sync.
  • Update docs/cli.mdx when CLI behavior changes.
  • Regenerate docs/openapi.json when HTTP contracts change.
  • Keep docs/inspector.mdx and docs/sdks/typescript.mdx aligned with implementation.
  • Append blockers/decisions to research/acp/friction.md during ACP work.
  • docs/agent-capabilities.mdx lists models/modes/thought levels per agent. Update it when adding a new agent or changing fallback_config_options. If its "Last updated" date is >2 weeks old, re-run cd scripts/agent-configs && npx tsx dump.ts and update the doc to match. Source data: scripts/agent-configs/resources/*.json and hardcoded entries in server/packages/sandbox-agent/src/router/support.rs (fallback_config_options).
  • Some agent models are gated by subscription (e.g. Claude opus). The live report only shows models available to the current credentials. The static doc and JSON resource files should list all known models regardless of subscription tier.

Read the full file on GitHub · 85 lines

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. 2d ago First seen · 85 lines · 1,291 tokens per session scan A a5fe3a309024

Subscribe to this mod's changes

sandbox-agent CLAUDE.md is an instructions file published in the GitHub repository rivet-dev/sandbox-agent (1,555 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,291 tokens to every session, about $0.0065 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Writing and docsagentaiampclaudeclaude-codecodex
Related

Other instructions, from other repositories

waku AGENTS.md

AGENTS.md instructions for egoist/waku, covering waku development guidance, development runtime, performance, accessibility and product reference.

egoist/waku · 1,335 tokens

waku CLAUDE.md

Claude Code instructions for egoist/waku, a project described as: ⚡ A native app for all your coding agents.

egoist/waku · 3 tokens

intelligent-terminal rust.instructions.md

Concise Rust coding conventions for this repository.

microsoft/intelligent-terminal · 435 tokens

InvestSkill GEMINI.md

Instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).

yennanliu/InvestSkill · 3,074 tokens

she-love-me CLAUDE.md

Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.

863401402/she-love-me · 268 tokens

wayland-core copilot-instructions.md

Instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.

FerroxLabs/wayland-core · 823 tokens