gsd-plan-review-convergence
GitHub跨AI计划收敛循环，通过外部AI CLI反复审查并修正计划直至无HIGH级问题。支持Codex、Gemini等多种模型及本地服务，具备停滞检测与升级机制，适用于多阶段计划的自动化质量闭环。
Trigger Scenarios
Install
npx skills add AjayIrkal23/agentic-mercy-10x --skill gsd-plan-review-convergence -g -y
SKILL.md
Frontmatter
{
"name": "gsd-plan-review-convergence",
"description": "Cross-AI plan convergence loop — replan with review feedback until no HIGH concerns remain.",
"allowed-tools": [
"Read",
"Write",
"Bash",
"Glob",
"Grep",
"Agent",
"AskUserQuestion"
],
"argument-hint": "<phase> [--codex] [--gemini] [--claude] [--opencode] [--ollama] [--lm-studio] [--llama-cpp] [--text] [--ws <name>] [--all] [--max-cycles N]"
}
Flow: Agent→Skill("gsd-plan-phase") → Agent→Skill("gsd-review") → check HIGHs → Agent→Skill("gsd-plan-phase --reviews") → Agent→Skill("gsd-review") → ... → Converge or escalate
Replaces gsd-plan-phase's internal gsd-plan-checker with external AI reviewers (codex, gemini, etc.). Each step runs inside an isolated Agent that calls the corresponding existing Skill — orchestrator only does loop control.
Orchestrator role: Parse arguments, validate phase, spawn Agents for existing Skills, check HIGHs, stall detection, escalation gate.
<execution_context> @$HOME/.claude/get-shit-done/workflows/plan-review-convergence.md @$HOME/.claude/get-shit-done/references/revision-loop.md @$HOME/.claude/get-shit-done/references/gates.md @$HOME/.claude/get-shit-done/references/agent-contracts.md </execution_context>
<runtime_note>
Copilot (VS Code): Use vscode_askquestions wherever this workflow calls AskUserQuestion. They are equivalent — vscode_askquestions is the VS Code Copilot implementation of the same interactive question API. Do not skip questioning steps because AskUserQuestion appears unavailable; use vscode_askquestions instead.
</runtime_note>
Flags:
--codex— Use Codex CLI as reviewer (default if no reviewer specified)--gemini— Use Gemini CLI as reviewer--claude— Use Claude CLI as reviewer (separate session)--opencode— Use OpenCode as reviewer--ollama— Use local Ollama server as reviewer (OpenAI-compatible, default hosthttp://localhost:11434; configure model viareview.models.ollama)--lm-studio— Use local LM Studio server as reviewer (OpenAI-compatible, default hosthttp://localhost:1234; configure model viareview.models.lm_studio)--llama-cpp— Use local llama.cpp server as reviewer (OpenAI-compatible, default hosthttp://localhost:8080; configure model viareview.models.llama_cpp)--all— Use all available CLIs and running local model servers--max-cycles N— Maximum replan→review cycles (default: 3)
Feature gate: This command requires workflow.plan_review_convergence=true. Enable with:
gsd config-set workflow.plan_review_convergence true
Version History
- 581d130 Current 2026-07-19 09:10
