MetalHexx/rad-approve-plan
greenfield/harness-files/skills/rad-approve-plan/SKILL.md
Open the post-approval, pre-execution router — delegates to /rad-execute or /rad-execute-parallel
$ install --global
skillsauthnpx skillsauth add MetalHexx/RadOrchestration rad-approve-planInstall 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: May 16, 2026, 2:05 AM142.0s1 file scanned
SKILL.md
- name:
- rad-approve-plan
- description:
- Open the post-approval, pre-execution router — delegates to /rad-execute or /rad-execute-parallel
- disable-model-invocation:
- true
- user-invocable:
- true
Inputs:
project_name: $0 — The name of the approved project to execute. (e.g., "DAG-PIPELINE-2")
Initialize
You are an orchestrator. The plan for project_name has already been approved upstream — this skill is a thin router that helps the user choose how to begin execution. You do not approve, mutate state.json, or create worktrees yourself; that work belongs to the downstream skills.
Workflow:
The plan for project_name has been approved. I'll help you start execution.
Step 1: Choose execution branch
- Greet the user briefly, confirming
project_name. - Use the
askQuestionstool to ask the user how they want to proceed and execute the plan: - Give them 2 options "Execute Plan in current branch / worktree" or "Execute the plan in a new branch / worktree".
- Current branch: Invoke the
/rad-executeskill and follow its workflow start-to-finish without skipping or improvising from this skill's context. Source Control Initialization (rad-execute Step 3) is mandatory for fresh projects and MUST prompt the user for anyauto_commitorauto_prvalue set to"ask"inorchestration.yml(the default). - New worktree: Follow the
rad-execute-parallelskill — set up the worktree and follow user's choices. Stop there. Do NOT begin execution and proceed with following the steps inrad-execute-parallel.
- Current branch: Invoke the
Related Skills
MetalHexx/rad-project
testing
VerifiedTrustedCommunity
Use this skill to understand, navigate, and organize the work-graph — the live map of projects in the system, what state each is in, how they relate to one another, and where their worktrees are. Use at brainstorm time when continuing a series or referencing existing work — orient on live state before exploring files.
7SKILL.mdUpdated Jun 9, 2026
MetalHexx/rad-source-control
development
VerifiedTrustedCommunity
Source control operations — commit code, open a PR, create a worktree, or clean up a worktree. All inputs for commit and PR come from the spawn prompt; worktree operations are interactive and driven from the main session.
7SKILL.mdUpdated May 21, 2026
MetalHexx/rad-orchestration
data-ai
VerifiedTrustedCommunity
This skill can be invoked when the user starts talking about planning or executing a project. Use this skill to run a team of subagents through an automated SDLC process that helps them get work done safely and effectively.
7SKILL.mdUpdated May 21, 2026
MetalHexx/rad-execute
testing
VerifiedTrustedCommunity
Continue a project through the orchestration pipeline. Ensures the Orchestrator runs as the primary agent — not as a subagent — so it retains full control of agent sequencing. Use for local, background, or cloud-based execution.
7SKILL.mdUpdated May 21, 2026