Ralplan Consensus Planning

Ralplan (Consensus Planning Alias)

Ralplan is the consensus planning workflow. It triggers iterative planning with Planner, Architect, and Critic agents until consensus is reached, with RALPLAN-DR structured deliberation (short mode by default, deliberate mode for high-risk work).

Usage

/skill:ralplan "task description"

Flags

• --interactive: Adds draft-review prompts and one-at-a-time reconciliation. When the final receipt resolves auto_handoff.effectiveTarget to off without degradationReason: "planning_stuck", final approval uses an ask workflow gate; a configured automatic admission is handled by step 8.
• --deliberate: Forces high-risk deliberation: pre-mortem plus expanded test planning. It may also auto-enable for explicit auth/security, migration, destructive, incident, compliance/PII, or public-API-breakage risk.
• --architect openai-code / --critic openai-code: Use OpenAI code for that review pass when available; otherwise note the fallback and use default GJC review.
• gjc.ralplan.autoHandoff: Selects final-plan admission: off (default), ultragoal, or autoresearch. An autoresearch target admits /skill:autoresearch to continue research from the approved plan rather than implement it; it needs no availability probe. PLANNING-STUCK also resolves every target to off. Invalid settings reject the final write before any final artifact is persisted. The final receipt's ledger-backed runtime-owned auto_handoff.effectiveTarget is authoritative across state loss and run switching.
• --write --stage <type> --stage_n <N> --artifact <markdown file path or markdown string>: Native writer for Planner/Architect/Critic/revision/ADR/final pending-approval markdown under .gjc/_session-{sessionid}/plans/ralplan/<run-id>/; do not edit .gjc/ directly.

Corrupt current-session state recovery

For corrupt, tampered, unreadable, or stale current-session ralplan state, run gjc state clear --force --mode ralplan scoped by --session-id, command payload, or GJC_SESSION_ID; it clears only ralplan state for that session.

Behavior

Planning/Execution Boundary

Ralplan is planning only. It may inspect context and draft plan/spec/proposal artifacts, but those remain pending approval until tagged structured-UI execution approval for the current final artifact, or a valid non-off final receipt's runtime-owned auto_handoff.effectiveTarget admits the existing handoff chain. Before either admission, do not mutate product source, run mutation-oriented shell, commit, push, open PRs, invoke execution skills, or delegate implementation.

Explicitly naming ultragoal (including /skill: and gjc forms) selects the desired execution target; it does not replace structured approval for the current final artifact when auto_handoff.effectiveTarget is off. Never invent a direct approval record or infer execution consent from the skill name.

Persist planning artifacts and handoffs through the ralplan CLI writer, never direct .gjc/ edits: Direct write, edit, or ast_edit calls against .gjc/_session-{sessionid}/specs, .gjc/_session-{sessionid}/plans, .gjc/_session-{sessionid}/state, or any other .gjc/ path are forbidden unless an explicit force override is active.

gjc ralplan --write --worktree-root <repository_binding.worktreeRoot> --session-id <owner-session-id> --run-id <run-id> --stage <type> --stage_n <N> --artifact "markdown file path or markdown string"
# restricted role agents use:
gjc ralplan --write --worktree-root <repository_binding.worktreeRoot> --session-id <owner-session-id> --run-id <run-id> --stage <type> --stage_n <N> --artifact-env GJC_RALPLAN_ARTIFACT

Use stages planner, intent, architect, critic, disposition, revision, post-interview, adr, or final; increment --stage_n each consensus pass. The writer accepts inline markdown (or JSON for disposition), an artifact path prepared outside .gjc/, or --artifact-env GJC_RALPLAN_ARTIFACT, persists stage-<NN>-<stage>.md plus index.jsonl under .gjc/_session-{sessionid}/plans/ralplan/<run-id>/, and copies final to pending-approval.md. Ralplan mutation blocking is enforced in code; use temp directories (os.tmpdir()/$TMPDIR, /tmp, /var/tmp) only for oversized scratch artifacts, never the repo or .gjc/. Staging via the write tool or a quoted-delimiter bash heredoc (cat > /tmp/plan.md <<'EOF' … EOF) into those temp roots is tolerated by the planning-phase guard.

Restricted read-only role agents (planner, architect, critic) must pass markdown through GJC_RALPLAN_ARTIFACT with --artifact-env GJC_RALPLAN_ARTIFACT; their restricted bash environment disables artifact file-path ingestion.

RECEIPT-ONLY guideline: role agents (planner, architect, and critic) persist durable outputs via gjc ralplan --write and return ONLY the receipt fields (session_id, run_id, path, sha256) plus verdict/status routing fields; include stage and stage_n when available, and never return the full persisted body.

The ralplan seed/write receipt's session_id is the immutable workflow owner session and run_id is the run identity. Include both in every Planner/Architect/Critic assignment and every parent-side revision/post-interview/ADR/final write. A role subagent's own session id is transcript/resume identity only and MUST NOT own ralplan state or artifacts. The seed/write receipt's repository_binding.worktreeRoot is the canonical artifact root for the run. Whenever a writer's cwd can differ from that root — a dispatcher directory, a linked branch worktree, or a role subagent runtime cwd — propagate the seed receipt's repository_binding.worktreeRoot as --worktree-root <repository_binding.worktreeRoot> on every gjc ralplan seed/write (Planner, Architect, Critic, revision, disposition, post-interview, ADR, and final). Explicit-target mode routes all run state, stage artifacts, index.jsonl, HUD state, stuck markers, and review-budget accounting to that exact worktree regardless of the writer's cwd; it fails before any write when the target is missing, not a directory, not a git worktree root, when no seeded run state exists there, or when the target is not exactly the run's bound worktreeRoot (a linked worktree that merely shares commonDir is rejected). A relative --artifact file is still resolved from the invoking cwd. Without --worktree-root, legacy cwd-based behavior is unchanged. Never scan the filesystem for runs or merge artifact trees by hand.

This skill runs GJC planning in consensus mode for the provided arguments.

The consensus workflow:

1. Planner creates the initial plan and a compact RALPLAN-DR summary before review. Launch the Planner ONCE per run as a detached, resumable subagent (await it before the Architect) and record its returned subagent id as the run's persisted Planner id; persist the stage with gjc ralplan --write --worktree-root <repository_binding.worktreeRoot> --stage planner --stage_n 1 --artifact-env GJC_RALPLAN_ARTIFACT --planner-id <id> --planner-resumable <true|false> (see Persisted role agents below):

   • After persistence, return only the receipt/path plus compact planning status; do not paste the full plan markdown back to the caller unless explicitly requested.
   • Principles (3-5)
   • Decision Drivers (top 3)
   • Viable Options (>=2) with bounded pros/cons
   • If only one viable option remains, explicit invalidation rationale for alternatives
   • Deliberate mode only: pre-mortem (3 scenarios) + expanded test plan (unit/integration/e2e/observability)

2. Pre-consensus material-intent reconciliation (always before Architect/Critic): Reconcile material scope and intent before paying for consensus review. This is a bounded contract check, not a second planning loop. a. Read the persisted Planner artifact plus relevant .gjc/_session-{sessionid}/specs/deep-interview-*.md, prior plans, and current user constraints. Extract only material unresolved decisions, assumptions that could change architecture/scope/acceptance criteria, and conflicts with an explicit prior non-goal. Cosmetic wording and implementation details that do not alter the contract are not material. b. When material open items exist, use the ask tool one at a time, highest-impact first, with concrete options. When none exist, proceed without an empty ceremony or user prompt. c. Persist the check with gjc ralplan --write --worktree-root <repository_binding.worktreeRoot> --stage intent --stage_n <N> --artifact-env GJC_RALPLAN_ARTIFACT --json. The artifact must list evidence inspected, resolved material decisions, retained non-goals, and either material-open-items: none or the still-open items. d. If reconciliation changes objective, scope, non-goals, acceptance criteria, or verification obligations, resume the persisted Planner and persist a revision before review. Architect and Critic receive the reconciled Planner/revision receipt plus the intent receipt; they never review the superseded pre-reconciliation draft. e. With --interactive, also present the reconciled draft plus Principles / Drivers / Options summary (Proceed to review / Request changes / Skip review). Without --interactive, proceed automatically once material intent is resolved.

3. Review fan-out after Planner persistence: launch the Architect and Critic ONCE per run as detached, resumable review lanes against the same immutable Planner receipt/path/sha/stage_n. Their pass-1 fan-out remains parallel when Critic is plan-only and does not consume Architect output (see Persisted role agents below).

   • Architect lane: challenge architecture, surface tradeoff tensions, and enrich thin plans with synthesis or missed sub-scope. Persist with gjc ralplan --write --worktree-root <repository_binding.worktreeRoot> --stage architect --stage_n <N> --artifact-env GJC_RALPLAN_ARTIFACT --architect-id <id> --architect-resumable <true|false> --lane-verdict <token> --json, then return receipt/path plus CLEAR/WATCH/BLOCK and APPROVE/COMMENT/REQUEST CHANGES.
   • Plan-only Critic lane: independently check quality, principle-option consistency, alternatives, risks, acceptance criteria, and verification; when the plan is thin, request concrete expansion rather than only defects. Persist with gjc ralplan --write --worktree-root <repository_binding.worktreeRoot> --stage critic --stage_n <N> --artifact-env GJC_RALPLAN_ARTIFACT --critic-id <id> --critic-resumable <true|false> --lane-verdict <token> --json, then return receipt/path plus OKAY/ITERATE/REJECT.
   • Sequential fallback: if Critic must evaluate Architect findings, verdict, antithesis, tradeoffs, synthesis, status, or any Architect-produced artifact, await the Architect result before issuing that Architect-dependent Critic pass.
   • Every Architect/Critic assignment, including each pass-2+ re-review assignment in step 5, MUST instruct the reviewer to include --lane-verdict <token> on its existing gjc ralplan --write: Architect passes its Architectural Status token (CLEAR/WATCH/BLOCK), and Critic passes its verdict token (OKAY/ITERATE/REJECT). The flag is optional so legacy invocations stay valid.

4. Review join gate: before consensus, revision, reconciliation, finalization, or approval, verify both Architect and Critic receipts/verdicts exist for the same Planner artifact/pass (path, sha256, stage_n). A non-CLEAR Architect verdict, non-APPROVE Architect decision, or any non-OKAY Critic verdict routes back to Planner revision; do not finalize from only one review lane.

   • Typed conflict gate (#2902): when Architect and Critic findings prescribe incompatible actions (add vs remove, or remove vs change) against the same stable plan target id, do not treat the join as clean and do not start revision until a disposition stage is persisted for that pass. Collect typed findings (stable findingId, targetId, action, severity, evidence, sourceRole, source receipt) from both review artifacts, derive conflicts, and require one explicit disposition per conflict (accept_architect | accept_critic | synthesize | defer_user | reject_both) with rationale, decisionOwner, and affectedSections. Persist via gjc ralplan --write --worktree-root <repository_binding.worktreeRoot> --stage disposition --stage_n <N> --artifact-env GJC_RALPLAN_ARTIFACT --json using schema ralplan.review_conflicts.v1. Source receipts must be authoritative same-pass attestations: plannerStageN equals CLI --stage_n, each finding's sourceReceipt.stage equals sourceRole, sourceReceipt.stageN equals plannerStageN, and path/sha256 resolve against the run's persisted Architect/Critic index.jsonl rows. The writer fails closed if any conflict remains open, a disposition references an unknown conflict, or provenance is mismatched/spoofed. Product intent/scope remains owned by the user + approval gate; the ralplan leader owns reconciliation; reviewers advise and block.

5. Re-review loop (max 5 iterations; runtime-enforced): Any non-OKAY Critic verdict (ITERATE or REJECT) or Architect result that is not CLEAR/APPROVE MUST run the same full closed loop. Pass 2+ resumes the SAME persisted Architect and Critic lane subagents with the mandatory re-review context bundle and runs sequentially Architect -> Critic: await the Architect result and its receipt/path before assigning Critic; Critic receives the current-pass Architect receipt/path and performs the rule-5 counter-review before consolidated feedback routes to Planner revision. From pass 2, both reviewers are bound by the five-rule ratchet: delta-only review, novelty justification, verdict monotonicity, severity scoping, and Critic counter-review of Architect scope inflation; unjustified inflation does not force a revision. a. Collect Architect + Critic feedback b. When typed conflicts exist, persist dispositions (step 4 typed conflict gate) before revision so the Planner receives a machine-checkable conflict set, not prose alone c. Revise the plan by resuming the SAME persisted Planner subagent with consolidated Architect + Critic feedback and any disposition receipts (see Persisted role agents below); fall back to a fresh Planner spawn only per the fallback routing table

   Re-review context bundle (pass 2+; mandatory): Every pass-2+ Architect or Critic assignment MUST include:

   1. the explicit review pass number N for that lane, stated literally as review pass N in the assignment text, where N is the ordinal review pass for that lane across the entire ralplan run/re-review loop (equivalently the opener-iteration ordinal): the review of the initial Planner artifact is review pass 1, the review of the first revised Planner artifact is review pass 2, and so on; N never resets within an opener iteration and never resets when a new revision opener begins in the same run — it increments monotonically with every review the lane performs in the run. This ordinal is a workflow counter distinct from the runtime lane budget (which counts lane writes per opener iteration, WI-5): at the default budget the two coincide numerically, but the ratchet ("from pass 2") always keys off the run-level N so normal post-revision re-reviews activate delta-only review, monotonicity, and the sequential cadence;
   2. the current revision receipt under review (path, sha256, stage_n);
   3. the prior Planner/revision artifact path that the previous pass reviewed;
   4. the prior same-lane review artifact path (stage-NN-architect.md / stage-NN-critic.md) with its receipt fields;
   5. the consolidated prior blockers and the revision's claimed resolutions, as orchestrator-collected pointers into those artifacts (never pasted bodies);
   6. Critic pass-2+ only: the current-pass Architect receipt/path, awaited first per the sequential cadence, so the rule-5 counter-review is evaluable.

   The re-review context bundle remains mandatory regardless of whether a reviewer is resumed or uses a fresh-spawn fallback. A fresh-spawn fallback always receives everything required to apply delta-only review (rule 1), novelty justification (rule 2), monotonicity (rule 3), severity scoping (rule 4), and counter-review (rule 5). d. For pass 2+, resume (or fresh-spawn only per the routing table) Architect -> Critic sequentially: await the Architect result and receipt/path, then issue Critic with the mandatory context bundle, including the current-pass Architect receipt/path. Critic performs the rule-5 counter-review before consolidated feedback routes to Planner revision.

   • Persist each Planner revision with gjc ralplan --write --worktree-root <repository_binding.worktreeRoot> --stage revision --stage_n <N> --artifact-env GJC_RALPLAN_ARTIFACT --json before re-review, then pass the receipt/path forward instead of duplicating the full revision markdown in the parent conversation. e. Re-join Architect and Critic verdicts for the same revised Planner artifact/pass (including a fresh disposition stage if new conflicts appear) f. Repeat this loop until Critic returns OKAY and Architect is CLEAR/APPROVE for the same Planner artifact/pass, or 5 iterations are reached g. If 5 iterations are reached without Critic OKAY plus Architect CLEAR/APPROVE, stop opening further planner/revision passes. Preserve the best version as a terminal PLANNING-STUCK result; do not route it to automatic or explicit execution. h. Runtime budget (#3165): native gjc ralplan --write refuses a new planner/revision that would open consensus iteration > max (default 5, overridable via gjc.ralplan.maxIterations, integer 1..20, using the workflow-settings precedence below). Cap uses the same iteration definition as the HUD (planner/revision openers in index.jsonl). Overflow exits 3, prints operator-visible PLANNING-STUCK on stdout (and stderr detail; JSON includes planning_stuck: true), and still allows architect/critic within an already-opened pass plus post-interview/adr/final so the best plan can be escalated to pending approval without dispatch. A new --run-id starts a fresh budget.

6. Final intent verification (post-consensus delta gate): After the review join gate has both Critic OKAY and Architect CLEAR/APPROVE for the same Planner artifact/pass, verify only intent deltas introduced or newly exposed by consensus. The pre-consensus intent receipt is the baseline; do not re-ask decisions already settled there. a. Collect new open items from the run: assumptions or conflicts introduced after the latest intent receipt, plus any material ambiguity first exposed by Architect/Critic. Source these from persisted artifacts, not memory. b. Cross-check prior context for conflicts: glob .gjc/_session-{sessionid}/specs/deep-interview-*.md and other prior specs/plans/context relevant by topic. For each, list points where the consensus plan contradicts, weakens, or expands beyond a previously crystallized decision, constraint, or non-goal. Cite the conflicting artifact and line/section. c. Reconcile with the user via the ask tool (always, regardless of --interactive): Never stop idle with plain-text prose after the consensus loop. Every reconciliation question MUST go through the ask tool with contextual options plus free-text.

   • If open items exist, confirm the open assumptions and conflicts one at a time with the ask tool, weakest/highest-impact first, polishing intent. If any confirmation reveals that the plan diverges from user intent, route the consolidated correction back into the re-review loop (step 5b Planner revision) and re-run Architect + Critic before returning here. Cap at the same 5-iteration ceiling.
   • If the plan is crystal clear (no open assumptions or prior-context conflicts), continue to final persistence in step 7; do not choose an approval or handoff path before its final receipt exists.
   • For every confirmed open item, embed the resolved outcome into the final plan under an ## Intent Reconciliation section so the pending approval artifact records each decision; record any item the user explicitly defers as an open confirmation under that same section. d. Persist the reconciliation with gjc ralplan --write --worktree-root <repository_binding.worktreeRoot> --stage post-interview --stage_n <N> --artifact-env GJC_RALPLAN_ARTIFACT --json, then return the receipt/path plus a compact status (reconciled-clean / reconciled-with-revision / open-confirmations-pending) instead of pasting the full body.

7. On reconciliation completion, re-check the review join gate (Critic OKAY plus Architect CLEAR/APPROVE for the same Planner artifact/pass), mark the plan pending approval unless execution is already authorized by the resolved handoff admission, then persist the ADR/final plan via gjc ralplan --write --worktree-root <repository_binding.worktreeRoot> --stage final --stage_n <N> --artifact-env GJC_RALPLAN_ARTIFACT --json. Read the successful receipt's auto_handoff object; its ledger-backed effectiveTarget is runtime-owned and is the only automatic-routing decision; do not directly edit .gjc/_session-{sessionid}/plans. Final plan must include ADR (Decision, Drivers, Alternatives considered, Why chosen, Consequences, Follow-ups) and, when present, the ## Intent Reconciliation section.

8. Final admission and approval gate: Reconciliation must first reach the successful final receipt from step 7. If that receipt has auto_handoff.degradationReason: "planning_stuck", it is terminal: retain the pending approval artifact and never dispatch, including for an explicitly named execution skill; do not issue an approval ask. Otherwise, if its runtime-owned auto_handoff.effectiveTarget is ultragoal, that valid non-off receipt is explicit operator admission for same-turn execution through that target; proceed to step 9 without an ask. If it is off, including ordinary off, require an accepted tagged structured approval for the current final artifact even if the user already named an execution skill. Unless that current final artifact already has that approval, present the finalized plan via the ask tool (regardless of --interactive) with workflowGate: { stage: "ralplan", kind: "approval" } on the final question so RPC/headless clients receive a ralplan/approval workflow gate, not a deep-interview question gate. Identify the current final receipt/path in the question. A revised final artifact requires a fresh structured approval; approval of a previous final artifact does not carry over. Use these options:

   • Refine further — re-run the consensus loop / request changes, then return here
   • Approve execution via ultragoal (Recommended) — goal-tracked autonomous execution
   • Stop here — keep the plan as pending approval and make no further changes

   Always include a free-text option for the ordinary off approval flow. Do not stop with plain text and no ask in that flow; its terminal action is this ask.

   Example: a request to "plan this, then use /skill:ultragoal" still requires the tagged final approval ask after step 7 when the receipt resolves to off. Only an accepted Approve execution via ultragoal choice for that current final artifact admits step 9. Free text, refinement, cancellation, timeout, and Stop here do not authorize execution.

9. On valid automatic admission or explicit approval, invoke the admitted/approved /skill:ultragoal target by default. On Refine further, return to the step 5 re-review loop. On Stop here, leave the pending approval artifact and stop. A planning_stuck final receipt never reaches this step. Never implement directly.

   Before invoking /skill:ultragoal, mark ralplan ready for handoff so the skill tool's chain guard permits the transition:

   gjc state ralplan write --input '{"current_phase":"handoff"}' --json

   The skill tool then dispatches the execution skill same-turn and runs gjc state ralplan handoff --to ultragoal --json in-process to atomically demote ralplan, promote the callee, and sync .gjc/_session-{sessionid}/state/skill-active-state.json. You do not need to run the handoff verb yourself.