← ClaudeAtlas

executelisted

Run code or scripts deterministically with captured output. Use when running tests, executing build commands, invoking tools, or performing read-only operations that produce results.
synaptiai/agent-capability-standard · ★ 4 · AI & Automation · score 74
Install: claude install-skill synaptiai/agent-capability-standard
## Intent Execute code or commands in a controlled manner, capturing output for verification. Unlike `mutate`, this capability is for operations that don't permanently change state (tests, queries, builds, analysis tools). **Success criteria:** - Code/command executed successfully - Output captured completely - Exit code recorded - Errors properly surfaced **Compatible schemas:** - `schemas/output_schema.yaml` ## Inputs | Parameter | Required | Type | Description | |-----------|----------|------|-------------| | `code` | Yes | string | Code or command to execute | | `language` | No | string | Programming language or shell (bash, python, ruby, etc.) | | `timeout` | No | string | Maximum execution time (default: "60s") | | `environment` | No | object | Environment variables to set | ## Procedure 1) **Validate execution request**: Ensure code is safe to run - Check for mutation operations (if found, suggest `mutate` instead) - Verify timeout is reasonable - Confirm execution environment 2) **Prepare environment**: Set up execution context - Set required environment variables - Ensure dependencies are available - Create isolated context if needed 3) **Execute code**: Run the code/command - Capture stdout and stderr - Record start time - Monitor for timeout 4) **Capture results**: Collect execution output - Record exit code - Capture complete stdout - Capture complete stderr - Note execution duration 5) **Analyze output**: Interpre