# Ferrox Plan Review Convergence

> Replan against cross-AI review until the concerns are actually resolved, not just noted

- Skill: `ferroxlabs/ferrox-plan-review-convergence` (Agent Skill)
- Install (CLI): `npx skillmds@latest add ferroxlabs/ferrox-plan-review-convergence`
- Raw SKILL.md: https://api.skillmd.com/api/skills/ferroxlabs/ferrox-plan-review-convergence/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: FerroxLabs (https://skillmd.com/u/ferroxlabs)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/ferroxlabs/ferrox-plan-review-convergence

---



<objective>
Cross-AI plan convergence loop — an outer revision gate around ferrox-review and ferrox-planner.
Repeatedly: review plans with external AI CLIs → if HIGH or actionable non-HIGH concerns remain → replan with --reviews feedback → re-review. Stops when no unresolved HIGH concerns or actionable MEDIUM/LOW findings remain outside PLAN.md, or when max cycles is reached.

**Flow:** Skill("ferrox-plan-phase") → Agent→Skill("ferrox-review") → check unresolved HIGH + actionable non-HIGH → Skill("ferrox-plan-phase --reviews") → Agent→Skill("ferrox-review") → ... → Converge or escalate

Replaces ferrox-plan-phase's internal ferrox-plan-checker with external AI reviewers (codex, gemini, etc.). Plan-phase runs **inline** (bare Skill at depth 0) so it can spawn ferrox-planner/ferrox-plan-checker at depth 1. Review runs inside an isolated Agent (ferrox-review is a Bash leaf — no sub-agents needed). Orchestrator only does loop control.

**Orchestrator role:** Parse arguments, validate phase, run plan-phase inline (Skill at depth 0), spawn an Agent for ferrox-review, check unresolved HIGH and actionable non-HIGH counts, stall detection, escalation gate.
</objective>

<execution_context>
@$HOME/.claude/ferrox-core/workflows/plan-review-convergence.md
@$HOME/.claude/ferrox-core/references/revision-loop.md
@$HOME/.claude/ferrox-core/references/gates.md
@$HOME/.claude/ferrox-core/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>

<context>
Phase number: extracted from $ARGUMENTS (required)

**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 host `http://localhost:11434`; configure model via `review.models.ollama`)
- `--lm-studio` — Use local LM Studio server as reviewer (OpenAI-compatible, default host `http://localhost:1234`; configure model via `review.models.lm_studio`)
- `--llama-cpp` — Use local llama.cpp server as reviewer (OpenAI-compatible, default host `http://localhost:8080`; configure model via `review.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:
`ferrox config-set workflow.plan_review_convergence true`
</context>

<process>
Execute end-to-end.
Preserve all workflow gates (pre-flight, revision loop, stall detection, escalation).
</process>