ferrox-plan-phase
SkillDev toolsReady to work out the next step in detail before building it. Produces a plan to execute
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the ferrox-plan-phase skill
What this skill tells your AI
The instructions your AI receives, as published by ferroxlabs/ferrox-factory in skills/ferrox-plan-phase/SKILL.md and read by ahel’s review.
Default flow: Research (if needed) → Plan → Verify → Done
Research-only mode (--research-phase <N>): Spawn ferrox-phase-researcher for phase N, write RESEARCH.md, then exit before the planner runs. Useful for cross-phase research, doc review before committing to a planning approach, and correction-without-replanning loops where iterating on research alone is dramatically cheaper than re-spawning the planner. Replaces the deleted research-phase command (#3042).
Research-only modifiers:
- No flag — when
RESEARCH.mdalready exists, auto-uses it: emits a one-line notice and exits cleanly, no prompt. --research— force-refresh: re-spawn the researcher unconditionally, no prompt. Bypasses the existing-RESEARCH.md auto-use path.--view— view-only: print existingRESEARCH.mdto stdout. Does not spawn the researcher. Cheapest mode for the correction-without-replanning loop. If noRESEARCH.mdexists yet, errors with a hint to drop--view.
Orchestrator role: Parse arguments, validate phase, research domain (unless skipped), spawn ferrox-planner, verify with ferrox-plan-checker, iterate until pass or max iterations, present results.
Planning ends with a parallelism recommendation. Once the plans exist the shape of the phase is knowable, so step 13f runs scripts/parallelism-verdict.cjs and reports which execution mode fits, recommendation first, with the measures that back it. It reports and never acts: /ferrox-execute-phase owns the backend decision, its availability check and its refusal.
<execution_context>
@/.claude/ferrox-core/workflows/plan-phase.md
@/.claude/ferrox-core/references/ui-brand.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:
--research— Force re-research even if RESEARCH.md exists--skip-research— Skip research, go straight to planning--gaps— Gap closure mode (reads VERIFICATION.md, skips research)--skip-verify— Skip verification loop--prd <file>— Use a PRD/acceptance criteria file instead of discuss-phase. Parses requirements into CONTEXT.md automatically. Skips discuss-phase entirely.--ingest <path-or-glob>— Use one or more ADR files instead of discuss-phase. Parses locked decisions + scope fences into CONTEXT.md automatically. Skips discuss-phase entirely.--ingest-format <auto|nygard|madr|narrative>— Optional ADR parser format override (autodefault).--reviews— Replan incorporating cross-AI review feedback from REVIEWS.md (produced by/ferrox-review)--text— Use plain-text numbered lists instead of TUI menus (required for/rcremote sessions)--mvp— Vertical MVP mode. Planner organizes tasks as feature slices (UI→API→DB) instead of horizontal layers. On Phase 1 of a new project, also emitsSKELETON.md(Walking Skeleton). Can be persisted on a phase via**Mode:** mvpin ROADMAP.md.
Normalize phase input in step 2 before any directory lookups.
Signals
- GitHub stars
- 23
- Forks
- 9
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
ferrox-plan-phase- Source
- github.com/ferroxlabs/ferrox-factory