Spec the project before a line of code exists. Routed to at greenfield startup, or by /decompose.
Run these ordered checks. Each passes silently or hard-stops with a routing action — never guess:
\n{{PROJECT_DIR}}/.codearbiter/CONTEXT.md. If it already carries the <!--INITIALIZED--> body marker on its own line, STOP — context exists. Route to normal operation..git/, .codearbiter/, .claude/, arbiter.md, AGENTS.md, CLAUDE.md, README.md, LICENSE, .gitignore, .gitmodules, and standard tooling dotfiles. If any exist, STOP and route to /create-context.{{PROJECT_DIR}}/.codearbiter/ exists and is writable. If not, surface the gap and STOP.All three pass → proceed to Phase 1. Later phases consume this pass-status; they do not re-run it.
\nAnnounce the role switch to the user, verbatim:
\n\n\n\"Switching to decomposition mode. For this session I operate as a senior software architect and technical lead, decomposing your project vision into a complete, unambiguous specification before any code is written. Vague language will be challenged, hidden complexity surfaced, and trade-offs forced. This is a thorough interview — typically 60–110 questions across six layers; every layer persists to disk, so you can stop at any point and resume in a later session. Orchestrator mode resumes when this decomposition is locked.\"
\n
State the Rules of Engagement, verbatim:
\n\n\nRules of Engagement
\n\n
\n- Pacing: ONE LAYER AT A TIME. One focused question at a time within a layer (cluster only when tightly coupled). Never advance until the current layer is solid — no hand-wavy answers, no deferred decisions, no unchallenged vague language.
\n- Three lenses on every answer:\n
\n\n
\n- Vague requirements — Challenge hand-wavy language. Force concrete nouns, numbers, and verbs. \"Manage\" is not a verb. \"We'll figure that out later\" is not acceptable; every \"later\" becomes a
\n[CONFIRM-NN]placeholder.- Hidden complexity — After each layer, name what the user assumes is easy but is hard: state management, real-time sync, edge cases, data migration, multi-tenancy, role matrices, offline behavior, failure modes — anything that grows non-linearly with scale.
\n- Trade-off forcing — When a real architectural or product decision exists, frame it: \"X gives you A but costs B; Y gives you C but costs D — choose.\" Record every forced choice as a DRAFT ADR.
\n- Suggestions calibrated to confidence: HIGH → recommend one option, one-line justification. MEDIUM → present 2–3 options with trade-offs, ask the deciding question. LOW → flag the gap, explain why it matters, ask the unlocking question. Never skip a gap silently; never suggest an integration without stating why.
\n
No interview question is asked yet — the Layer 1 question is asked at the end of Phase 2, after draft persistence exists, so the first answer lands on disk.
\nGate: persona and Rules of Engagement stated. Advance to Phase 2, never directly to Phase 3.
\nThe Phase 3 interview accumulates 60–110 Q/A turns across six layers. Without per-layer disk persistence, an auto-compaction event silently destroys earlier reasoning and any DRAFT ADRs. This phase plus the per-layer write rule in Phase 3 plus the disk re-read in Phase 4/5 make the skill compaction-resilient: every layer is durable the moment its gate clears.
\nCheck for an existing draft directory at {{PROJECT_DIR}}/.codearbiter/.decompose-draft/.
If it exists with _session.md and one or more layer-N-*.md files — Resume mode:
_session.md and every layer-*.md present. Read every {{PROJECT_DIR}}/.codearbiter/decisions/*.md with status: draft (prior-session draft ADRs to carry forward).status: draft ADR, begin fresh; (c) Abort — exit the skill, leave draft directory and DRAFT ADRs intact..decompose-draft/ and every DRAFT ADR, then fresh-init below. On Abort: exit cleanly; never silently delete.If no draft directory exists (or after Restart) — fresh init:
\n{{PROJECT_DIR}}/.codearbiter/.decompose-draft/._session.md recording the ISO-8601 start timestamp, the invoking identity (git config user.email), Status: in-progress, and a note that this directory is session state, auto-deleted on Phase 6 completion, and that re-invoking /decompose after interruption enters Resume mode..codearbiter/.decompose-draft/ is gitignored — append the entry to {{PROJECT_DIR}}/.gitignore if absent.Then ask the first Layer 1 question to open the interview:
\n\n\n\"Describe your solution vision in your own words. What problem does it solve, and for whom?\"
\n
Gate: Phase 3 does not begin until either (a) the draft directory exists with _session.md and is otherwise empty (fresh start), or (b) prior layers are replayed and the user explicitly chose Resume.
Run the six layers in strict sequence. Never skip a layer. Never advance until the current layer is solid — no open \"later\" items unless recorded as [CONFIRM-NN], no unchallenged vague language, no forced trade-off left unresolved.
Per-layer disk write (compaction contract): when a layer's \"advance when\" checklist is satisfied, BEFORE the first question of the next layer, write the completed layer's full Q/A record to disk:
\n| Layer | \nDraft file | \n
|---|---|
| 1 — Vision & Problem | \n.decompose-draft/layer-1-vision.md | \n
| 2 — Users & Flows | \n.decompose-draft/layer-2-flows.md | \n
| 3 — Functional Scope | \n.decompose-draft/layer-3-functional-scope.md | \n
| 4 — Technical Shape | \n.decompose-draft/layer-4-tech-shape.md | \n
| 5 — Integrations & Infrastructure | \n.decompose-draft/layer-5-integrations.md | \n
| 6 — Risks & Unknowns | \n.decompose-draft/layer-6-risks.md | \n
(All under {{PROJECT_DIR}}/.codearbiter/.) Each file holds every question asked, the user's verbatim answer (or a faithful paraphrase), every challenge made under the three lenses, every [CONFIRM-NN] raised, and every DRAFT-ADR title generated. These files are the authoritative record — Phases 4 and 5 read from them, not from conversation context. The next layer does not begin until the prior layer's file exists on disk and is non-empty; if a write fails, surface the error and do not advance.
Layer 4 immediate ADR drafts: each forced architectural choice in Layer 4 is written at the moment it is made as {{PROJECT_DIR}}/.codearbiter/decisions/NNNN-<slug>.md, numbered sequentially across the existing decisions/ directory. Do not batch the writes. Author each using the canonical ADR template — {{PLUGIN_ROOT}}/skills/decision-lifecycle/references/adr-template.md (the single source of truth, shared with decision-lifecycle) — with frontmatter status: draft and decided-by: set to the user (or \"user\" if anonymous). Fill ## Context, ## Decision, and ## Consequences from the forced choice; leave ## Alternatives considered and ## Risks populated where the interview surfaced them, or as <none recorded>. Phase 5 promotes each to status: accepted.
Layer 1 — Vision & Problem. Unlock: the specific problem and the evidence it is real (not assumed); the primary user and any conflicting user types (name and resolve the conflict, or flag it); the demo-to-a-skeptic definition of \"working\"; what this project explicitly is NOT building. Advance when: problem concrete, primary user named, \"working\" demonstrable, NOT-building list explicit.
\nLayer 2 — Users & Flows. Unlock: the core user journey from first touch to value delivered, in specific steps; every non-human actor at MVP (scheduled jobs, webhooks, callbacks, external triggers); failure-mode UX (concrete, not \"we'll show an error\"); admin/ops/internal privilege model. Advance when: end-to-end journey specific, non-human actors named, failure UX defined, privilege model sketched.
\nLayer 3 — Functional Scope. Unlock: every capability, challenged individually — what it does (concrete verbs), who initiates it, inputs and outputs; each capability classified MVP / v1 / later; the hardest user-facing problem (the one that invalidates the product if wrong); every \"later\" forced to closure or recorded as [CONFIRM-NN]. Advance when: capability list complete and every item classified; no unresolved \"later\" except as [CONFIRM-NN].
Layer 4 — Technical Shape. Unlock: components and ownership (what each owns, where the boundaries are); core data entities, relationships, cardinality; where state lives and how it changes (write paths); the hardest technical problem; hard constraints (stack, runtime, cloud, compliance, budget, team size and skill); the copyright holder for new-file headers (record in coding-standards.md; if undecided, record as [CONFIRM-NN]); a forced trade-off for every major architectural decision (e.g. monolith vs. services, sync vs. async); release intent — the tag prefix the user wants (e.g. v), and whether a CHANGELOG.md is kept at all. Each forced choice is written immediately as a status: draft ADR per the rule above. Advance when: all components named, all entities sketched, all hard constraints recorded, every major trade-off resolved or deferred as [CONFIRM-NN], release intent captured, AND layer-4-tech-shape.md is on disk with one DRAFT ADR per forced choice.
Release intent is elicited here, but no .codearbiter/release-targets.md row is ever written by this skill. This lane runs before any manifest or tag exists — greenfield has no package.json version field, no Cargo.toml, no committed tag to anchor a prefix against — so there is nothing yet to substantiate a full row (manifest, payload, an actual declared file load_targets could parse). Record the two answers (tag prefix preference; changelog kept y/n) in layer-4-tech-shape.md alongside the rest of the layer's Q/A, for context-creation's back-fill (once source exists) or /release's own back-fill lane (once a manifest and tag exist) to substantiate later. Writing a guessed row now, ahead of anything to check it against, is exactly the invented-shape failure both of those later lanes exist to refuse.
Layer 5 — Integrations & Infrastructure. Unlock: every external dependency (APIs, services, data sources, auth providers, payment processors, notification services), each named; commodity vs. differentiator for each; actual API contracts, data formats, and auth mechanisms for any system being integrated with; integration risks per dependency (rate limits, reliability and fallback, data ownership and portability, cost at scale). Advance when: all dependencies named, commodity/differentiator classified, integration risks surfaced for each.
\nLayer 6 — Risks & Unknowns. Unlock: the top three build-killing risks, each with probability, impact, mitigation; the lowest-confidence areas; spike candidates (what question each answers, cost of being wrong, time-box); the signals and decision points that would force a major architecture change mid-build. Advance when: top three risks named with mitigations, spike candidates identified, architecture-change triggers named.
\nGate: all six layers complete (no open \"later\" except as [CONFIRM-NN]); all six layer-*-*.md files on disk and non-empty; at least one status: draft ADR present if any Layer 4 trade-off was forced — a Layer 4 with zero forced trade-offs is suspicious and is re-examined before advancing.
Begin by re-reading every layer-*-*.md and every status: draft ADR from disk. Do NOT rely on conversation context — by now an auto-compaction may have erased the original Q/A. The on-disk drafts are authoritative; this re-read makes the phase idempotent across compaction. If any expected layer file is missing, BLOCK and surface the gap rather than synthesizing from incomplete context.
Produce three artifacts and write each to disk under {{PROJECT_DIR}}/.codearbiter/plans/ BEFORE asking for review (the user reviews from disk, which survives a session restart):
01-architecture-breakdown.md — every component with responsibility and connections; a text/ASCII system diagram; every integration with its type (sync/async), protocol, and owner; every open architectural decision flagged with a [CONFIRM-NN] marker (numbered sequentially with open-questions.md).02-phased-build-plan.md — MVP → v1 → v2 phases; per phase a one-sentence goal, what is included, what is deferred and why (explicit rationale), key risks, and a measurable definition of done.03-task-backlog.md — a flat prioritized task list; each task estimable (1–5 days), assignable to one role (frontend/backend/infra/etc.), phase-grouped (MVP first), with dependencies flagged and spikes time-boxed.Present all three. Request explicit review:
\n\n\n\"These three artifacts are written to
\n.codearbiter/plans/. Open and review each one. Tell me what is wrong, incomplete, or misrepresents your intent. They are on disk now and survive a session restart, but Phase 5 will not run until you confirm they are correct.\"
Iterate on the on-disk files in place until the user explicitly approves.
\nGate: all three artifact files on disk AND the user explicitly approves all three, with no unresolved objections.
\nRe-read every input from disk — the three approved artifacts, all six layer-*-*.md files, and every status: draft ADR. This makes population idempotent across compaction: a user may approve Phase 4, suffer a compaction, re-invoke /decompose (Phase 2 enters Resume, Phase 4 sees its artifacts already approved on disk), and Phase 5 proceeds from disk.
Promote each status: draft ADR to status: accepted — an in-place edit of the frontmatter status: line (and its ## Status body mirror) only; do not duplicate or rewrite the ADR body.
Then write the surviving project-state docs. Every file holds actual content derived from the interview — no template boilerplate left unfilled:
\n| Source | \nDestination | \n
|---|---|
Layer 1 problem + users + NOT-building, with arbiter: enabled and stage: frontmatter | \nCONTEXT.md | \n
Layer 4 stack + hard constraints + tracker command (e.g. gh issue create) | \ntech-stack.md | \n
| Layer 4 lint, format, naming + copyright holder | \ncoding-standards.md | \n
| Layer 4 compliance + crypto + trust-boundary notes (thin — banned-primitive posture only) | \nsecurity-controls.md | \n
| Layer 6 unknowns + spike candidates | \nopen-questions.md ([CONFIRM-NN] format) | \n
| Task backlog | \nopen-tasks.md | \n
Carried from the {{CMD:init}} scaffold — confirm present, create empty if absent | \noverrides.log (append-only audit sink, with its audit header), last-checkpoint (0) | \n
| Each Layer 4 forced choice | \ndecisions/000N-<slug>.md — already written in Layer 4; Phase 5 only promotes Status to Accepted | \n
| The three Phase 4 artifacts | \nplans/01-…, plans/02-…, plans/03-… — already written and approved; Phase 5 only verifies they exist | \n
(All under {{PROJECT_DIR}}/.codearbiter/.) Set the stage: frontmatter value in CONTEXT.md to the maturity number for the MVP phase of the build plan (a single number — there is no promotion ladder).
Provenance stubs and code-map stub: once the project-state docs above are on disk, write a provenance stub per derived doc to .codearbiter/.provenance/<doc>.json via _provenancelib.write_stub (interview_derived: true, empty entries) — one stub for each scout/source-derived doc (CONTEXT, tech-stack, coding-standards, security-controls). Also write a .codearbiter/code-map.md stub — a placeholder empty coarse map. WHY: greenfield has no source code yet, so real provenance entries and code-map contents populate on the first commit-gate auto-heal (or {{CMD:context-check}}) once code exists.
Gate: every project-state doc written with real content; no status: draft ADRs remain in decisions/; [CONFIRM-NN] items are acceptable in open-questions.md for genuinely unresolved items; provenance stubs and code-map stub written.
Write the <!--INITIALIZED--> body marker on its own line in {{PROJECT_DIR}}/.codearbiter/CONTEXT.md. A marker embedded in a template instruction comment does not satisfy the gate.
List {{PROJECT_DIR}}/.codearbiter/ and show the populated tree to the user.
Confirm each required file is present and non-empty: CONTEXT.md (with arbiter: enabled + stage: frontmatter and <!--INITIALIZED--> body), tech-stack.md, coding-standards.md, security-controls.md, open-questions.md, open-tasks.md, overrides.log (append-only audit sink — create with its audit header if the scaffold left it absent), last-checkpoint, decisions/ (at least one ADR, all status: accepted, none status: draft), and plans/01-…, plans/02-…, plans/03-….
Delete {{PROJECT_DIR}}/.codearbiter/.decompose-draft/ and all its contents. This is mandatory — a leftover draft directory signals a still-in-progress decomposition to Phase 2 of any future /decompose.
Announce return to normal operation:
\n\n\n\"Decomposition complete. Project state is initialized and locked, draft directory removed. Returning to codeArbiter orchestrator mode. Use
\n{{CMD:feature}}to begin implementation, or any other command. Open questions are recorded in.codearbiter/open-questions.md.\"
Gate: <!--INITIALIZED--> present on its own line in CONTEXT.md; all required files present and non-empty; no status: draft ADRs in decisions/; .decompose-draft/ no longer exists on disk.
{{PLUGIN_ROOT}}/includes/cut-docs.md for the canonical never-scaffold list. Maturity is the single stage: value in CONTEXT.md frontmatter.[CONFIRM-NN].[CONFIRM-NN] by guessing — surface the question and record it in open-questions.md.status: draft ADR in decisions/ after Phase 5..decompose-draft/ still exists, or while CONTEXT.md lacks the <!--INITIALIZED--> body marker on its own line.