# Ralplan

> Consensus architectural planning — a GPT-5.6 Sol/high planner drafts RALPLAN-DR, two parallel GPT-5.6 Sol/max auditors critique it, and a Sol/max reconciler produces the final verdict. Output saved to ~/.nexus/workspace/plans/{name}.md. Default SHORT mode; pass '--deliberate' for pre-mortem + expanded test plan. Auto-invoked by TECH when Source Plan is missing. Triggers: 'ralplan', 'consensus plan', 'plan this properly', 'architect this', 'plan with review', 'planifică asta', 'plan consensual'. NOT for: prompt optimization (promptforge-scope), research (delphi), Q&A.

- Skill: `cryptopafi/ralplan` (Agent Skill)
- Install (CLI): `npx skillmds@latest add cryptopafi/ralplan`
- Raw SKILL.md: https://api.skillmd.com/api/skills/cryptopafi/ralplan/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: cryptopafi (https://skillmd.com/u/cryptopafi)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/cryptopafi/ralplan

---


# RALPLAN — Consensus Architectural Planning

Produces a plan that three agents have reviewed before any code is written.

Codex executions inherit the host thread model. The supported default is `gpt-5.6-sol`
with `high` reasoning; use `max` for the two audit lanes and final reconciliation when
the available subagent/CLI surface supports a per-lane override.

## When to Use

- Architecture decisions involving ≥2 components or files
- Any task TECH will execute that has >1 Step (TECH requires Source Plan)
- When "ralplan", "architect this", or "planifică asta" is invoked

## Inputs

- `{name}` — plan slug (kebab-case, e.g., `auth-refactor`)
- `--deliberate` flag (optional) — adds pre-mortem + expanded test plan sections
- `{task}` — description of what needs to be planned

## Execution

### Step 1 — Draft Plan (general-purpose subagent, GPT-5.6 Sol/high)

Dispatch `subagent_type: "general-purpose"` with this system prompt embedded in the message:

```
You are a senior architect producing a RALPLAN-DR planning document.

TASK: {task_description}

Produce EXACTLY these sections, in this order:

## Principles
3–5 load-bearing architectural invariants that constrain all options.

## Decision Drivers
Top 3 forces that determine the right choice.

## Options
At least 2 viable options. For each:
- **Summary**: one-sentence description
- **Pros**: 2–3 concrete advantages
- **Cons**: 2–3 concrete drawbacks
- **Risk**: primary failure mode
If only 1 option is viable, document explicitly why alternatives were invalidated.

## ADR (Architecture Decision Record)
- **Decision**: which option was chosen
- **Rationale**: why (citing Decision Drivers)
- **Consequences**: what becomes easier, what becomes harder
- **Follow-ups**: what must be resolved next

## Implementation Sketch
3–6 actionable steps. No code — what to build/change/delete. Each step becomes a DISPATCH.md Step.

## Test Plan
How we will know this worked. Specific, verifiable conditions.

RULES:
- Anchor code references by grep pattern, NEVER line numbers.
- Be specific — no "consider X" recommendations.

Save to: {plan_path}
If file already exists: read existing, find max version N in filenames matching {name}-v*.md, save as {name}-v{N+1}.md
```

### Step 2 — Preflight Validation

```bash
~/.nexus/scripts/plan-preflight.sh {plan_path}
EXIT_CODE=$?
```

- `exit 0` (even with warnings printed): proceed — warnings are informational
- `exit ≥1`: STOP. Show the error output. Fix the plan (re-invoke Step 1 subagent with error as context). Re-run preflight. Do NOT proceed to audit with exit ≥1.

### Step 3 — Parallel Audit (single message, two GPT-5.6 Sol/max Task calls)

Launch BOTH in a single assistant message turn:

**Task A**: `subagent_type: "forge-auditor"`, prompt:
`FORGE-AUDIT plan at {plan_path}. Tier: DEEP. Focus: completeness of options, ADR rationale, verifiable test plan, actionable sketch. Return full NPLF report.`

**Task B**: `subagent_type: "forge-auditor-b"`, prompt:
`FORGE-AUDIT-B plan at {plan_path}. Tier: DEEP. Pragmatic lens: will this plan work in real NexusOS? Flag over-engineering, missing edge cases, integration risks with existing agents. Return full NPLF report.`

### Step 4 — Reconcile (GPT-5.6 Sol/max)

Dispatch `subagent_type: "audit-reconciler"` with both reports concatenated as input.

### Step 5 — Gate Decision

| Reconciled Score | Action |
|---|---|
| PASS (≥3.5) | Emit plan path + verdict. Done. |
| CONDITIONAL (2.5–3.4) | Revision cycle: dispatch Step 1 subagent with message `Revise plan at {plan_path}. Critical findings to fix:\n{reconciler_critical_findings}\nSave as new version.` Re-run Steps 2–4. Max 2 revision cycles. After 2 cycles still CONDITIONAL: emit plan + CONDITIONAL verdict + unfixed findings. |
| FAIL (<2.5) | STOP. Report findings. Ask user: scrap or refine? |

### Step 6 — Output

On success:
```
RALPLAN COMPLETE
Plan: {plan_path}
Score: {X}/4.0 — {PASS/CONDITIONAL}
Resolved conflicts: {from reconciler, or "none"}
Unfixed (if CONDITIONAL): {list}
Ready for TECH: YES — add as Source Plan in DISPATCH.md
```

## SHORT vs DELIBERATE

- **SHORT** (default): Principles + Drivers + Options + ADR + Sketch + Test Plan
- **DELIBERATE** (`--deliberate`): add to Step 1 prompt: also produce `## Pre-Mortem` (top 5 failure modes + mitigations) and `## Expanded Test Plan` (unit/integration/manual QA matrix)