Detects agent runtime (Claude Code, Vercel Sandbox, local dev) and adapts behavior to available tools like Skill(), bash, readFile. For cross-runtime agents and SOUL.md prompts.
From bopen-toolsnpx claudepluginhub b-open-io/claude-plugins --plugin bopen-toolsThis skill uses the workspace's default tool permissions.
README.mdscripts/detect.shSearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Executes pre-written implementation plans: critically reviews, follows bite-sized steps exactly, runs verifications, tracks progress with checkpoints, uses git worktrees, stops on blockers.
Agents run in different environments with different capabilities. This skill detects the current runtime so agents can use the right tools and fail clearly when a required capability is missing.
| Runtime | How to detect | Tools available | Skills via |
|---|---|---|---|
| Claude Code | CLAUDE_CODE=1 env var, or Skill()/Agent()/Read tools exist | Full suite: Read, Write, Edit, Bash, Grep, Glob, Agent, Skill, WebFetch, WebSearch | Skill() tool |
| Vercel Sandbox | /vercel/sandbox/ paths exist, VERCEL_SANDBOX_ID env var set | bash-tool trio: bash, readFile, writeFile, plus skill if configured | createSkillTool() from bash-tool |
| Local dev | Neither of the above, process.cwd() is in user home or project dir | Whatever the app provides (usually just HTTP + AI SDK) | Direct file reads or none |
Run scripts/detect.sh to get a JSON summary of the current environment:
bash skills/runtime-context/scripts/detect.sh
Returns:
{
"runtime": "sandbox",
"has_bash": true,
"has_skill_tool": true,
"sandbox_id": "sbx_abc123",
"working_dir": "/vercel/sandbox/bot",
"node_version": "v22.x.x",
"bun_version": "1.x.x"
}
When writing a system prompt that works across runtimes, structure it like this:
## Environment Awareness
Before taking action, check your environment:
1. If you have `Skill()` and `Agent()` tools, you are in Claude Code
- Use skills via `Skill(name)`, delegate via `Agent()`
- Full file access via Read/Write/Edit
2. If you have `bash`, `readFile`, `writeFile` tools, you are in a Sandbox
- Run scripts via `bash`, read context via `readFile`
- Skills available via the `skill` tool if configured
3. If you have no tools, you are text-only
- Answer from your training and system prompt context
- Tell the user what you would do if you had tools
Do not guess which tools exist. If a tool call fails, state what tool
was missing and what capability it would have provided.
The goal is NOT fallbacks. The goal is clarity.
Correct: "I'm in a Sandbox. I have bash and file tools but no Skill() tool. I'll read the skill instructions directly from ./skills/clawnet/SKILL.md."
Incorrect: Silently trying Skill() first, catching the error, then trying readFile, then trying fetch, then giving up without telling the user.
At the start of a conversation or task, state what tools are available:
I'm running in a Vercel Sandbox with bash, file, and skill tools.
I can: run scripts, read/write files, look up skill instructions.
I cannot: spawn subagents, use Claude Code tools, access the host filesystem.
This sets expectations immediately so users and orchestrators know what to ask for.
README.md — Three runtimes explained, capability matrix, bash-tool integration guide for SDK developers, skill declaration across runtimes