r3dlex/oh-my-githubcopilot/ralplan
Claude Code and agent skill by r3dlex/oh-my-githubcopilot
- community
Checking that the SKILL.md file is still in the repository.
Consensus planning with Planner/Architect/Critic iterative loop. Activate when user says: ralplan, consensus plan, consensus planning.
Install
npx vskill@latest install r3dlex/oh-my-githubcopilot/ralplanSKILL.md
Ralplan (Consensus Planning)
Shorthand for /plan --consensus. Triggers iterative planning with Planner, Architect, and Critic agents until consensus is reached.
Flags
--deliberate: Forces deliberate mode for high-risk work. Adds pre-mortem (3 scenarios) and expanded test planning.
Interactive Hook Protocol
MANDATORY: Use vscode_askQuestions at every decision gate in this skill (when available). If vscode_askQuestions is NOT available (e.g., Copilot CLI), present numbered options in markdown and ask the user to respond with a number or freeform text.
When to Fire Hooks
| Trigger Point | Question Type | |
|---|---|---|
| Options presentation | Present viable options with pros/cons for user selection | |
| Architect concerns | Surface architectural trade-offs for user decision | |
| Critic rejection | Show rejection reasons, ask user for direction | |
| Consensus reached | Final plan approval before execution | |
--deliberate pre-mortem | Present risk scenarios for user prioritization |
Workflow
- @planner creates initial plan with RALPLAN-DR summary:
- Principles (3-5)
- Decision Drivers (top 3)
- Viable Options (>=2) with pros/cons
- HOOK: Present options via
vscode_askQuestionswhen options have significant trade-offs:
`` header: "ralplan-options" question: "Planner identified [N] viable approaches. Select preferred direction:" options: [ { label: "Option A: [name]", description: "Pros: X, Y. Cons: Z" }, { label: "Option B: [name]", description: "Pros: A, B. Cons: C" }, { label: "Let agents decide based on technical merit", recommended: true } ] allowFreeformInput: true ``
- @architect reviews for architectural soundness
- If architect raises concerns: HOOK — present trade-offs for user decision
- @critic validates quality and testability
- If critic rejects: HOOK — show issues and ask for direction:
`` header: "ralplan-critic-feedback" question: "Critic identified [N] issues: [summary]. How to proceed?" options: [ { label: "Address all issues", recommended: true }, { label: "Address critical issues only, skip minor" }, { label: "Override — I accept the trade-offs" }, { label: "Restart with different constraints" } ] ``
- Loop until critic approves (max 5 iterations)
- Final plan includes ADR (Decision, Drivers, Alternatives, Why chosen, Consequences)
- HOOK: Final approval via
vscode_askQuestions:
`` header: "ralplan-approval" question: "Consensus reached after [N] iterations. Execute?" options: [ { label: "Execute with team (parallel)", recommended: true }, { label: "Execute with ralph (sequential + verification)" }, { label: "Execute with omg-autopilot (full pipeline)" }, { label: "Save plan — don't execute yet" } ] ``
Deliberate Mode Hooks
When --deliberate is active, add:
- HOOK: Pre-mortem scenarios — present 3 risk scenarios, ask user to rank priority
- HOOK: Test strategy — present expanded test plan for user approval
Pre-Execution Gate
Vague execution requests (e.g., "ralph improve the app") are redirected through ralplan first to ensure explicit scope, testable criteria, and multi-agent consensus.
Passes gate (specific enough): prompts with file paths, function names, issue numbers, numbered steps, or acceptance criteria.
Gated (needs scoping): prompts with only vague descriptions and no concrete anchors.
After Approval
- Execute via
/team(parallel agents, recommended) or/ralph(sequential with verification)
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingvscode-omg/resources/templates/skills/ralplan/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/r3dlex/oh-my-githubcopilot/ralplan)