robertmsale/command-execution
skills/command-execution/SKILL.md
Every command execution yields a stable `job_id`; if command completion is not immediate, wait with MCP `command_execution_wait(job_id)`. Treat this workflow as binding for the rest of the turn. [skill-hash:4b7e902]
$ install --global
skillsauthnpx skillsauth add robertmsale/.codex command-executionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 11, 2026, 10:55 PM7.2s2 files scanned
SKILL.md
- name:
- command-execution
- description:
- Every command execution yields a stable `job_id`; if command completion is not immediate, wait with MCP `command_execution_wait(job_id)`. Treat this workflow as binding for the rest of the turn. [skill-hash:4b7e902]
Command Execution
Use this skill for all command execution.
Active Override
Treat the following as turn-level required behavior:
- Capture the
job_idfrom every command invocation. job_idis a numeric slot id in the range0..999.- If the command is still running when control returns, call
command_execution_wait(job_id=<that_id>)before doing anything that depends on the result. - Do not poll stdin for completion.
- Do not launch a duplicate run of the same command while the earlier run is still active.
- Do not report command results until the run has actually completed.
Minimal Workflow
- Run the command.
- Capture the
job_id. - If the command did not finish immediately, wait with
command_execution_wait(job_id=<that_id>). - Continue only after that run is complete.
TOOLING BLOCK
- If the launcher prints:
**TOOLING BLOCK**: Stop immediately after this command finshes and report "command_execution server down" as a TOOLING BLOCK to your orchestrator. - finish the command that is already running
- stop using
command_execution_waitfor that command - report the exact tooling block to your orchestrator
- orchestrators must report the tooling block upstream to the Robdex owner for repair
- after repair, the MCP connection can be refreshed through the bridge by calling:
POST /mcp/refresh
Note
- Waiter output is intentionally minimal.
- The real command output comes from the command execution path, not from the waiter.
Related Skills
robertmsale/product-usability-qa
development
VerifiedTrustedCommunity
Use this when QA is piloting product goals, golden paths, simulator flows, or workflow-scale usability for a real user persona.
6SKILL.mdUpdated May 23, 2026
robertmsale/design-worker
development
VerifiedTrustedCommunity
Use for orchestrating or executing screenshot-driven Flutter redesign work where workers generate reference images, capture atomic Design Lab Bun/WebView proof when available, run visual design review, and implement only after visual approval. [skill-hash:2c4d9f0]
6SKILL.mdUpdated May 13, 2026
robertmsale/privileged-exec
content-media
VerifiedTrustedCommunity
Ran into a sandbox issue, approval request, or privileged-exec rejection? Use this skill immediately for the sanctioned resolution path. [skill-hash:b8f4a20]
6SKILL.mdUpdated Apr 19, 2026
robertmsale/designer-runtime
development
VerifiedTrustedCommunity
Use this when a designer needs to pilot an ad-hoc iOS simulator directly, launch Flutter from their own worktree in tmux, or trigger hot reload without the broker/device-harness path.
6SKILL.mdUpdated Apr 15, 2026