ux

name	ux
position	start
description	Write a SLICE's UX lens as a grounding doc (ux.md) — the screens (each with a low-fidelity layout) that make the slice's functionalities visible, the states each holds, and the product's visual core (color + typography) — directly in place on the live model. The START of the FUNCTIONAL realize pipe (ux → agentic → marketing), run on a shaped slice. Accessibility is not here (it lives in the marketing lens); flows are the build's to derive. Reads the hub from the spine (functionality grounding + profile), never another lens. Writes only the slice's ux lens and its visual-core decision.
user-invocable	true

ux

Write a shaped slice's UX lens as the grounding doc ux.md: the screens that make every functionality visible, the states each holds, and the product's visual core. Just enough to anchor the intended experience and let the build figure the rest. /ux reads the slice's hub — its functionalities' grounding docs plus the profile (both from the spine) — and never another realize lens.

Pipeline position: start. /ux OPENS the functional realize pipe (ux → agentic → marketing): the D2 rule prepends start-change — resolve or create the slice-realize issue, cut the branch off fresh main, optional worktree, init STM — so /agentic and /marketing run on this already-started branch. No pipeline close sequence (no end PR) is injected here; the functional pipe closes at /marketing. It writes the persistent product model directly, in place (the slice's ux lens and the visual-core decision) on the started branch — there is no draft copy and no apply/promote step; review is the branch git diff and the pipeline's end PR. (#437, #500, ADR 026)

Write discipline (ADR 026, standards/rules/direct-model-write.md). The LLM authoring skill writes ONLY the per-node grounding doc ux.md straight to the live model; the one shared-file mutation — the visual-core decisions/*.yaml (slice-level, skip-if-exists) — is done by the deterministic keyed persist script, in place, keyed to the target slice so it cannot touch another slice's decisions and never edits an accepted decision in place. The model tree is asserted clean once start-change has cut the branch (F14) and the play commits its own model delta after approval (C13), so the working-tree diff vs HEAD is exactly this run's delta. Containment is a post-write scoped guard (scoped_write_guard.py), not a draft.

Compiled From

This play was compiled from the ux ICE (reference/ice.md) by play-editor (#466 Batch C; #467 Batch B — the checkpoint upgraded to a conditional learned gate, see standards/rules/gate-config.md; #500 — migrated to direct-model-write per ADR 026 and standards/rules/direct-model-write.md). Intent defines constraints (C1–C13) and failure conditions (F1–F14); the expectation defines success scenarios (S1–S6), a Done means (D1–D3, baked to stop-condition.yaml), and one recovery entry per failure condition. To modify this play, update reference/ice.md and recompile with play-editor. Do NOT edit this file manually — it is a compiled artifact.

Role

You are the orchestrator. You own the workflow and step order. You delegate the domain work — authoring the UX lens grounding doc — to the product-os-keeper agent via a JSON contract over files on disk, and you run the mechanical work (readiness/hub resolution, the shape linter, the content-quality eval, grounding + coverage, KB grounding, the keyed in-place persist, and the post-write scoped guard) through bundled scripts and an isolated judge. You never write the lens yourself, and you never persist the shared decision or commit the model delta before the single checkpoint (C11) resolves — a typed approval, a recorded config skip, or a recorded policy auto-pass.

Forbidden: hand-writing the lens or a decision; writing anything other than this slice's ux.md (by the skill) and its visual-core decision (by the keyed persist) (C2); reading or grounding on another realize lens (C7); writing the visual-core decision by any route other than scripts/persist_ux.py; committing the model delta before the Step 5 gate resolves; editing an accepted decision in place (additive-only — F9); running the lens writes against a dirty product-os tree (C13/F14); closing COMPLETED without the stop-condition verdict held (C12/F12).

Agent boundaries:

Agent	Domain	Skill it invokes	Phases
product-os-keeper	Author the slice's UX lens (screens + states + visual core) from the hub + KB pattern grounding — the ux.md written in place on the live model, and the visual-core decision emitted into the manifest	kb-search, author-ux-lens	Author

product-os-keeper is the single domain agent this play uses (1 of the ≤5 budget). The utility work — cutting the branch and resolving the issue — is start-change (injected head), not a domain agent. The content-quality judge always runs as an isolated, clean-context sub-agent (optionally on a configured different model) — never the orchestrator's own context.

Pre-flight

Check	Constraint	Action on Failure
Resolve config + product_base (.garura/core/config.yaml)	—	Hard halt
Resolve grounding-eval.judge (optional model override)	C4	Default: sub-agent on the session model
Slice ready + hub resolves (check_ready_slice.py)	C1	Hard halt (REC1)
Clean model tree — after start-change (Step 0), git status --porcelain -- <product_base>product-os is empty	C13/F14	Hard halt (REC14)

Resolve the pre-flight facts mechanically with the bundled resolver:

python3 scripts/preflight.py --play ux --config .garura/core/config.yaml

Then resolve the slice and its hub from the spine — the readiness gate that every realize lens shares:

python3 scripts/check_ready_slice.py --product-base <product_base> --slice <slice-id>

It asserts the profile is set (from the spine), resolves the slice record, and resolves every functionality_ref through the spine to its functionality.md grounding doc — the hub. If the slice is absent, a functionality does not resolve, or the profile is not firmed, hard halt (C1/REC1).

The run's working root (<working> below) is {stm_base}_realize/ux/<slice>/ — the routing, the ux manifest (ux-manifest.yaml), the change-shape, the persist record (persist-manifest.json), and the captured scoped-guard report (guard-report.json) all live under it. These are STM, non-model artifacts (ADR 008/017) — the model itself (the ux.md and the visual-core decision) is written IN PLACE under <product_base>product-os/, never into <working>. The stop condition evaluates against <working>. Status markers live at {stm_base}_realize/ux/status/.

Clean-tree assertion (C13/F14, ADR 026). start-change cuts the branch off fresh main, so the product-os tree is clean by construction; still assert it right after Step 0 — HEAD is only a correct base for the scoped guard and the change-shape if the tree is clean before the lens writes:

test -z "$(git status --porcelain -- <product_base>product-os)" || { echo "HALT: dirty product-os tree (REC14)"; exit 1; }

If dirty, halt and ask for a clean model tree (commit or revert the pending model edits) before /ux writes the lens.

Right after the resolver, record the session identity stamp's start marker (#463 — soft-fail, never a halt):

python3 scripts/session_stamp.py --phase start \
    --marker "{stm_base}_realize/ux/status/session-stamp-ux.json" \
    --cwd "$(pwd)" --branch "$(git branch --show-current)"

Resume check: if {stm_base}_realize/ux/status/<slice-id>.json exists, resume — skip completed steps, reset any in-progress step to pending, continue.

Task DAG

Create ALL tasks immediately after resolving config — before any domain work. The play owns this DAG; the agent must not edit its top-level tasks.

Write-then-review (ADR 026): the FULL model delta — the LLM's ux.md AND the keyed persist's visual-core decision — is written to the live model BEFORE the checkpoint, so the guard, the change-shape, and the human all see the real delta. Nothing is COMMITTED before the gate resolves; cancel reverts the uncommitted writes.

[T0] start-change (injected — start, head)          blockedBy: []
[T1] Author the lens (ux.md to live)                blockedBy: [T0]
[T2] Validate the live doc                          blockedBy: [T1]
[T3] Persist (keyed, in place — decision)           blockedBy: [T2]
[T4] Guard the full delta + classify the shape      blockedBy: [T3]
[T5] Checkpoint (approval over the full git diff)   blockedBy: [T4]
[T6] Commit the model delta                         blockedBy: [T5]
[T7] Scenario Validation                            blockedBy: [T6]
[T8] Close                                          blockedBy: [T7]

Mark each task in-progress before its step and completed right after its eval passes. No runtime reordering. On resume, skip completed and reset in-progress to pending.

Workflow

Phase: Start (injected — D2 position: start)

Step 0 — start-change · Owner: start-change (sub-play) · Depends on: pre-flight Run the start-of-pipeline member as a sub-play, dispatched with parent_run_id so it emits only its own C1 evidence and this play's close absorbs it. It resolves or creates the slice-realize issue, cuts the branch off fresh main, sets up a worktree iff config calls for it, and initializes STM. /agentic and /marketing run on this branch; /marketing closes it.

{
  "play":          "start-change",
  "parent_run_id": "<this run id>",
  "inputs":  { "title": "<realize ux: the slice>" },
  "outputs": { "result": "{stm_base}_realize/ux/start/start-change.json" }
}

start-change owns its own evals (issue anchored, branch off latest main, worktree per config, STM initialized); they are not re-checked here. Immediately after it returns, run the clean-tree assertion (pre-flight, C13/F14) so HEAD is a correct base for the guard and the change-shape. SE-13 (F14/C13): the product-os tree was clean once start-change had cut the branch — the assertion (git status --porcelain -- <product_base>product-os empty) passed before any lens write; a dirty model tree halts (REC14), so the change-shape and the scoped guard reflect only this run's delta.

Phase: Author (write the doc to the live model, ADR 026)

Step 1 — Author the lens (ux.md to live) · Owner: product-os-keeper · Depends on: Step 0 The agent invokes author-ux-lens to write the slice's ux.md (screens + states + visual core, per the UX lens template) from the hub (the functionality grounding docs + the profile) and KB pattern grounding. Per ADR 026 the skill writes the per-node doc straight to the live model in place, and emits the visual-core decision (with the grounding map) as structured data in ux-manifest.yaml — it writes NO shared model file (_spine.yaml, the profile, or a decisions/*.yaml):

{
  "task":    "author the slice's UX lens (screens/states/visual core) from its hub; write ux.md in place on the live model; ground screens to functionalities and the visual core to the KB or a decision; emit the visual-core decision delta into the manifest",
  "inputs":  { "slice_ref": "<domain>/<slice>",
               "slice_file": "<slice record>",
               "functionality_groundings": "<from check_ready_slice>",
               "profile": "<spine profile>", "product_base": "<product_base>",
               "lens_rel": "product-os/<domain>/slices/<slice>/lens/ux.md",
               "manifest_path": "<working>/ux-manifest.yaml" },
  "outputs": { "manifest": "<working>/ux-manifest.yaml" }
}

The skill reads the hub read-only and writes the ux.md IN PLACE under <product_base>product-os/. It writes ux-manifest.yaml under <working> (STM) with the grounding map and the visual-core decision_delta (omitted when it reuses an existing product decision). It writes NO shared model file. It returns the contract with the output paths on disk — never inline content. SE-1 (F1/C1): check_ready_slice.py passed at pre-flight — the slice is ready and its hub resolves; an unready slice halted (REC1).

Step 2 — Validate the live doc · Owner: play · Depends on: Step 1 Run the guards over the LIVE ux.md this run wrote, before the checkpoint — shape first, then content, then grounding. Under direct-model-write the doc is already written in place, and the visual-core decision has NOT yet been written for this run (the keyed persist runs after Step 2):

python3 scripts/lint_grounding.py --doc <product_base>/product-os/<domain>/slices/<slice>/lens/ux.md
python3 scripts/validate_ux.py --manifest <working>/ux-manifest.yaml --slice-file <product_base>/<slice_file> --product-base <product_base>
python3 scripts/check_kb_grounding.py --manifest <working>/ux-manifest.yaml --kb-root <kb_root> --proposals-dir <working>/proposals

Then run the content-quality eval over ux.md: spawn an isolated, clean-context sub-agent handed the judge prompt (standards/rules/grounding-eval.md), the doc (at its live path), and the UX lens per-section guidance (it sees neither the brief nor the author's reasoning), on the model from grounding-eval.judge.model. Gate the verdict:

python3 scripts/grounding_gate.py --verdict <verdict.json>

SE-2 (F3/C3): lint_grounding.py exits 0 — ux.md conforms to the UX lens template (Intent/Screens/States/Visual core), no missing/extra/empty section. SE-3 (F4/C4): the content-quality eval gate (grounding_gate.py) passes — ux.md is self-explaining and clears the stranger test. SE-4 (F5/C5): validate_ux.py — every screen in the manifest grounds to a functionality or a persona/journey; the visual core grounds to the KB or a decision. SE-5 (F6/C6): validate_ux.py — every functionality the slice bundles is visualized by at least one screen (coverage). SE-6 (F7/C7): validate_ux.py — no screen grounds on another realize lens. SE-7 (F8/C8): validate_ux.py — the visual core names a decision (the manifest's decision_delta or a reused product decision) that resolves; the keyed persist (Step 3) writes it. SE-8 (F10/C10): check_kb_grounding.py exits 0 — the visual core, navigation, and responsive choices trace to a KB learning or a recorded proposal. On any GAP, apply the matching recovery (REC2–REC10) and re-run before the checkpoint — a content-eval fail (SE-3) is REC4: rewrite the failing section to the judge's cited fixes and re-judge until the gate passes.

Phase: Persist (write the full delta first, ADR 026 write-then-review)

Step 3 — Persist (keyed, in place — decision) · Owner: play · Depends on: Step 2 Write-then-review (ADR 026): the FULL model delta is written to the live model BEFORE the checkpoint, so the guard, the change-shape, and the human all see the real delta. The ux.md is already on the live model (Step 1). persist_ux.py now writes the SHARED file — the visual-core decision — in place, keyed to --slice-ref: it reads the manifest's decision_delta and writes the decision skip-if-exists under the target slice's decisions/ folder ONLY, and it REFUSES a decision path outside that folder (the node-level containment the file-level guard cannot provide) and never edits an accepted decision in place. It also confirms the live ux.md landed. No draft, no doc copy. Nothing is COMMITTED yet — the commit (Step 6) happens only after the gate approves; on cancel the whole delta is reverted (Step 5):

python3 scripts/persist_ux.py --ux-manifest <working>/ux-manifest.yaml \
        --product-base <product_base> --slice-ref <domain>/<slice> \
        --lens-rel product-os/<domain>/slices/<slice>/lens/ux.md \
        --out-manifest <working>/persist-manifest.json

The persist record stamps applied: true (the live ux.md is confirmed and the decision handled) — D1/D2's input.

Phase: Guard + Classify (over the full delta)

Step 4 — Guard the full delta + classify the shape · Owner: play · Depends on: Step 3

The run's write scope (the per-play guard policy, ADR 026). The old apply_ux.py encoded /ux's write scope by construction — the lens re-derive (overwrite) and decisions skip-if-exists; under direct-model-write that same scope is the scoped_write_guard.py policy. Resolve <slice-dir> as <domain>/slices/<slice>:

--allow    'product-os/<slice-dir>/lens/ux.md'      # the ux lens (re-derive; overwrite allowed)
--add-only 'product-os/<slice-dir>/decisions/*'     # the visual-core decision (added, never modified)

Guard ONCE over the full delta (C9). After ALL writes (the LLM's ux.md from Step 1 and the keyed persist's decision from Step 3), run the scoped guard a single time over the whole delta. Capture its report — its ok field is the stop condition's D3 input (this replaces the old before/after verify):

python3 scripts/scoped_write_guard.py --product-base <product_base> --base-ref HEAD \
        --allow 'product-os/<slice-dir>/lens/ux.md' \
        --add-only 'product-os/<slice-dir>/decisions/*' \
        --out <working>/guard-report.json

If the guard exits non-zero (a path outside the slice's lens/decisions scope changed, or an existing decision was overwritten), re-run with --restore to revert the offending paths, apply REC9, and re-persist before the checkpoint.

Classify the full working-tree delta (C11). Classify the model tree's diff vs HEAD — now the FULL delta (the ux.md + the visual-core decision), per ADR 026 write-then-review (no draft dir):

python3 scripts/classify_change.py --play ux \
        --product-base <product_base> --base-ref HEAD --out <working>/shape.json

SE-9 (F2/F9/C2/C9): the scoped-write guard report reads ok: true — the model delta is confined to the slice's ux.md (re-derive) and its decisions/* (add-only); the spine, the slice record, the profile, and the other lenses are byte-unchanged, and no accepted decision was edited in place.

Phase: Checkpoint (conditional gate, C11)

Step 5 — Human review (class: standard, conditional) · Owner: play · Depends on: Step 4 This is the single checkpoint (C11) — the agent never skips it on its own judgment. It is a conditional gate (#467) per standards/rules/gate-config.md — /ux is one of the eleven conditional document plays. Resolve it first match wins: pinned (n/a here) → gates.plays.ux → the learned policy → gates.classes.standard → gates.default (absent ⇒ on). For the policy lookup, use the shape key classified in Step 4.

Look the shape key up in the config-resolved policy (gates.conditional.policy, default .garura/core/gate-policy.yaml): auto-pass iff the shape is in the policy's auto: block AND not in never_auto: AND Step 2 + Step 4 stand with no blocking finding (a lint_grounding.py gap, a grounding_gate.py content-eval fail, or a guard violation). On auto-pass, do NOT wait: record gate auto-passed by learned policy (shape: <shape-key>, policy v<version>) as a Checkpoint Decisions row, include the working-tree diff summary in the run record, append the crossing's live-eval ledger line, and proceed to Step 6 (commit):

python3 scripts/gate_eval.py append --ledger <gates.conditional.ledger> --play ux \
        --issue <issue> --shape <shape-key> --predicted auto --human auto_pass \
        --policy-version <policy version> --ts <run ts>

Anything else resolves the gate on (an explicit gates.plays.ux: off instead records gate skipped by config (<resolution path>) as a Checkpoint Decisions row and proceeds). When on, present the proposed screens (with layouts), states, and visual core, plus the decision, inline over the real model git diff — render the approval prompt (standards/templates/approval-prompt.md) and wait for the typed response. Approve → continue to Step 6 (commit). Cancel → revert the working tree (ADR 026 step 6): the full delta is already on disk, so run the guard with --restore and an EMPTY allow set to git restore the modified model paths and git clean/remove the new ones (byte-clean back to HEAD), then halt — nothing was committed, and cancel means "revert what was written" (the branch, issue, and STM start-change created are its own committed side effects and are left as-is):

python3 scripts/scoped_write_guard.py --product-base <product_base> --base-ref HEAD \
        --restore --out <working>/guard-report.json   # empty --allow ⇒ every model path reverted

Then append the crossing's live-eval ledger line with the human's real action:

python3 scripts/gate_eval.py append --ledger <gates.conditional.ledger> --play ux \
        --issue <issue> --shape <shape-key> --predicted gate \
        --human <approved_clean|approved_edited|rejected> --ts <run ts>

<issue> is the slice-realize issue Step 0 resolved. <gates.conditional.ledger> / <gates.conditional.policy> resolve from config gates.conditional (defaults .garura/core/gate-evals.jsonl / .garura/core/gate-policy.yaml); <policy version> is the policy file's version: field. <run ts> is the run's own UTC timestamp, derived the same way the close derives ts (date -u), passed by the orchestrator. SE-10 (F11/C11): the model delta was written to the live model by Steps 1 + 3 but is COMMITTED (made durable) only at Step 6 on approval — so no product-model change is COMMITTED before the gate resolves (a typed approval, a recorded config skip, or a recorded policy auto-pass); on cancel the whole working-tree delta is reverted before any commit, so nothing is left on the tree. SE-11 (F13): every crossing of this gate appended exactly one live-eval ledger line (shape, predicted gate|auto, the human's real action or auto_pass), and an auto-pass fired only for a shape the policy lists in auto: (and not in never_auto:) with no blocking finding standing.

Phase: Commit (make the delta durable, ADR 026 step 7)

Step 6 — Commit the model delta · Owner: play · Depends on: Step 5 The gate approved (or auto-passed / was skipped by config). Commit the full model delta on the branch (C13, ADR 026 step 7) — a lightweight persist step that makes the writes durable and advances HEAD so the next pipeline play (/agentic) enters a clean tree; it is NOT the pipeline end sequence (no end PR — that closes at /marketing). A cancelled checkpoint never reaches this step — its tree was already restored in Step 5:

git add -- <product_base>product-os
git commit -m "feat(model): ux lens <slice> — screens, states, visual core (#<issue>)"

SE-12 (F12/C12): the close is stop-condition gated — check_stop_condition.py over the baked stop-condition.yaml (D1 the persist record persist-manifest.json exists; D2 it stamps applied: true; D3 the captured guard-report.json reads ok: true) must read held before any COMPLETED close, and the model delta is committed (C13); a run whose persist or guard did not land closes HALTED, never COMPLETED (REC12).

Phase: Scenario Validation

Step 7 — Scenario evals · Owner: play · Depends on: Step 6

• SCE-1 (S1 — product designer): ux.md is a valid UX Lens doc clearing the linter + the content eval, written in place on the live model, and the spine/slice/profile/other lenses are byte-identical (the scoped-guard report reads ok); the stop-condition verdict reads held.
• SCE-2 (S2 — product owner): every functionality the slice bundles maps to ≥1 screen.
• SCE-3 (S3 — ux researcher): every screen traces to a functionality or persona/journey; the visual core to a decision that resolves.
• SCE-4 (S4 — architect): no other realize lens was read or written.
• SCE-5 (S5 — product owner, re-run): a re-run re-derives only ux.md; everything else byte-identical; no accepted decision edited in place (the keyed persist skipped the existing decision).
• SCE-6 (S6 — reviewer): the checkpoint showed the screens, states, and visual core inline over the real model git diff, and no product-model change was COMMITTED before approval — on cancel the working tree returns byte-clean to HEAD — or, on the auto-pass path, the change shape is policy-listed and a recorded auto-pass + live-eval ledger line + diff summary exist, with no wait.

Phase: Evidence & Close

Step 8 — Close · Owner: play · Depends on: Step 7 Run the Standard Play Close. /ux opened a slice-realize issue via start-change, so it is project-scoped — record evidence per the D1 rule.

# --- Standard Play Close (canonical; see standards/rules/play-close.md) ---
# Path tokens resolved at pre-flight (resolve here if not already):
#   ltm_project_target  = yq '.ltm.project-target' .garura/core/config.yaml
#   evidence_base, slug:
#     project-scoped play : evidence_base="${stm_base}${issue}/evidence/ux/"   ; slug="#${issue}"
#     product-scoped play : evidence_base="${product_base}_evidence/ux/"        ; slug="${slice_slug}"
evidence_template=$(cat "${ltm_project_target}standards/templates/evidence-file.md")
delivery_template=$(cat "${ltm_project_target}standards/templates/delivery-report.md")
ts=$(date -u +%Y%m%d-%H%M%S)
evidence_dest="${evidence_base}${ts}.md"
mkdir -p "$(dirname "$evidence_dest")"
# Session identity stamp (#463) — close phase; start phase ran at pre-flight
session_stamp=$(python3 scripts/session_stamp.py --phase close \
    --marker "${stm_base}_realize/ux/status/session-stamp-ux.json")
# Stop-condition gate (#464) — Step C0: this play carries a baked manifest, so the
# gate is LIVE. Evaluate the Done means against the run's working root as the
# close's authoritative input.
python3 scripts/check_stop_condition.py \
    --manifest "<play-dir>/stop-condition.yaml" \
    --base "${stm_base}_realize/ux/<slice>/" \
    --out "${stm_base}_realize/ux/status/stop-condition-ux.yaml"
sc_exit=$?   # 0 held · 1 unmet · 2 error
# Conditional-gate policy refresh (#467) — soft: a distill failure never blocks the close
python3 scripts/distill_gate_policy.py \
    --ledger "$(yq '.gates.conditional.ledger' .garura/core/config.yaml)" \
    --policy "$(yq '.gates.conditional.policy' .garura/core/config.yaml)" \
    --streak "$(yq '.gates.conditional.streak' .garura/core/config.yaml)" \
    --project "$(yq '.project.name' .garura/core/config.yaml)" || true

Step C0 — bind the verdict. sc_exit == 0 (held) permits status: COMPLETED. Anything else closes HALTED with exit_reason: stop_condition_unmet and the evidence's Stop Condition section names every unmet clause — fix the state per REC12 (re-run the keyed persist, re-capture the scoped-write guard report, or make the model-delta commit) and re-evaluate; the close stays HALTED until the verdict reads held. An unevaluable verdict is never a pass.

/ux opened a slice-realize issue via start-change, so it is project-scoped: evidence_base="${stm_base}${issue}/evidence/ux/" and slug="#${issue}".

Step C1 — Write evidence file. Gated by the resolved evidence.record flag. When false, skip and record evidence skipped (record=false). Otherwise fill the evidence-file.md slots (play ux, run_id ux-${ts}, slice slug, started/completed, status per C0, exit_reason; artifacts: the slice's ux.md, the manifest, the visual-core decision, the persist manifest (persist-manifest.json), the captured guard-report.json, the model-delta commit sha, the stop-condition verdict; the content-eval verdict; step + scenario evals SE-1…SE-13 / SCE-1…SCE-6; checkpoint decision from Step 5 (incl. any gate skipped by config or gate auto-passed by learned policy row) plus the gate ledger line(s) appended this run; the session identity stamp fields from $session_stamp (#463): session_id, ledger_file, ledger_start_offset, ledger_end_offset (null when unresolved — never blocks the close); and stop_condition per C0 with the Stop Condition section filled) and write to $evidence_dest. Do NOT hand-author the body.

Step C2 — Render delivery report. Also render the Next line: resolve this play in standards/rules/pipeline-next.md and emit **Next:** /<command> — <why>. Or run /next to see all recommended actions. (only /next pointer, or omit, when the mapped command is null), per play-close.md. Fill the delivery-report.md slots: ## ux Delivered — ${slug}, the Run Summary table (incl. the stop-condition verdict), the Pipeline Steps table, the Artifacts Produced table (the ux lens + the visual-core decision + the model-delta commit sha), Next Steps (run /agentic on this slice), and a pointer to $evidence_dest. Always emitted.

# --- end Standard Play Close ---

Scenario Validation

Scenario	Persona	Eval
S1 — first run	product designer	SCE-1
S2 — validates the shape	product owner	SCE-2
S3 — grounded	ux researcher	SCE-3
S4 — hub-only	architect	SCE-4
S5 — re-run	product owner	SCE-5
S6 — the checkpoint	reviewer	SCE-6

Recovery

For	Trigger	Direction	Handoff
F1	the slice is absent, a functionality does not resolve, or the profile is not firmed	halt and route to /shape or /understand before /ux runs	human
F2	a write touched something beyond this slice's ux.md or its visual-core decision	the guard's --restore already reverted the out-of-scope write; re-run writing only the slice's ux.md and its decision	autonomous
F3	ux.md fails the template/shape or carries out-of-scope content	re-emit to the UX lens template (Intent/Screens/States/Visual core only)	autonomous
F4	ux.md fails the content-quality eval	rewrite the failing section to the judge's cited fixes and re-judge until the gate passes	autonomous
F5	an invented/ungrounded element	drop it, or re-tie the screen to a functionality or persona/journey, and the visual core to a decision	autonomous
F6	a functionality is covered by no screen	add the screen(s) that visualize the missing functionality	autonomous
F7	/ux read or depended on another lens	remove the dependency; /ux derives only from the slice's hub	autonomous
F8	the visual core was set with no decision	record the slice-level visual-core decision in the manifest (reuse the product one if it exists) before the keyed persist	autonomous
F9	the scoped-write guard report is not ok — a non-lens/non-decision path changed, or an accepted decision was edited in place	the guard's --restore already reverted the offending paths; re-run writing only the slice's ux.md and its visual-core decision, after a human confirms the restore	human
F10	a UX pattern choice with no KB learning and no recorded proposal	search the KB via kb-search and ground the choice, or raise a KB-learning-gap proposal	autonomous
F11	the model delta was committed before the checkpoint resolved, or a cancelled checkpoint left writes on the working tree	revert the premature commit and the working-tree writes (guard --restore, empty allow set) and re-present the checkpoint; commit only after the gate resolves

Pause and Resume

Steps run top to bottom. On entry, resolve config, resolve the target slice, check the status marker, skip completed steps, reset any in-progress step to pending, and continue. A fresh start with no marker runs everything and creates the marker at Step 1. Resuming a run that already wrote the model doc enters a dirty tree; the pre-flight clean-tree assertion (F14) is scoped to a FRESH start — a resume continues its own in-progress delta.

Compilation Metadata

Field	Value
fingerprint	sha256:0d18d26db5ffd9253213d30716f46e3caac8652d25cf8ef743a1e0b91a1805a7 (of reference/ice.md)
compiled_by	play-editor (#500 direct-model-write, ADR 026); prior: play-editor (#467 Batch B, #466 Batch C)
pipeline_position	start (functional pipe head; the functional pipe closes at /marketing)
workflow_structure	A (single checkpoint — class: standard, conditional learned gate per gate-config.md #467; direct-model-write WRITE-THEN-REVIEW per ADR 026 — persist + guard + classify before the gate, commit after; stop-condition gated close)
stop_condition	stop-condition.yaml (D1–D3), gate live at Step C0
domain_agents	1 (product-os-keeper)
utility_agents	0
skills_used	kb-search, author-ux-lens
scripts	12 (preflight, check_ready_slice, lint_grounding, grounding_gate, validate_ux, check_kb_grounding, persist_ux — keyed in-place persist, scoped_write_guard — post-write containment, check_stop_condition — Done-means gate, session_stamp — #463 identity stamp, classify_change + gate_eval + distill_gate_policy — #467 conditional gate)
step_evals	13 (SE-1…SE-13)
scenario_evals	6 (SCE-1…SCE-6)
recovery_entries	14 (one per failure condition; 11 autonomous / 3 human)

Recompiled note (#500, direct-model-write / ADR 026): migrated from draft-then-apply to direct-model-write. The old draft model tree and the apply_ux.py/check_ux.py promotion+verify scripts are removed; the authoring skill writes ux.md straight to the live model; the new keyed persist_ux.py writes the visual-core decision in place (skip-if-exists, keyed to the slice); containment is the post-write scoped_write_guard.py (its guard-report.json is D3); classify_change.py reads the working-tree git diff (--product-base/--base-ref HEAD); checkpoint cancel reverts the working tree via the guard --restore; the play asserts a clean product-os tree at entry (F14) and commits its own feat(model) delta after approval (C13). Order is write-then-review (ADR 026 "Order of operations"): the full delta — the LLM's ux.md AND the keyed persist's decision — is written to the live model FIRST (Steps 1+3), then guarded ONCE and classified over the full delta (Step 4), then the gate resolves over the real git diff (Step 5), and only an approved gate COMMITS (Step 6). Nothing is COMMITTED before approval; cancel reverts the uncommitted writes. See standards/rules/direct-model-write.md.

Recompiled note (#467 Batch B): checkpoint upgraded to a conditional learned gate; see gate-config.md.

Direct-edit deviation note (#500) — INTENT CHANGE, HAND-COMPILED, CONVERGENCE UNVERIFIED: This SKILL was updated to the direct-model-write write-then-review shape (ADR 026) by a hand-compile from reference/ice.md, NOT by a /play-editor run. This is an intent change (it alters the write path, the containment guarantee, the checkpoint cancel semantics, and the step order), so the sanctioned path is recompile-via-/play-editor; play-editor is interactive-only (fully gated, human-checkpoint) and cannot run headless in this environment, so the compiled output was produced by hand to match what play-editor would emit from the current reference/ice.md (fingerprint above). The compiled_by line names play-editor for provenance intent, but no play-editor run actually occurred and convergence is UNVERIFIED. An interactive /play-editor convergence run against reference/ice.md is REQUIRED — confirming the emitted SKILL matches this hand-compiled body and refreshing the fingerprint. This migration mirrors the merged /understand reference implementation (#498) and the just-migrated /vision, /grill, /learn on this branch. Note also: reference/ice.md C13 distinguishes the model-delta commit from the Standard Play Close (evidence + delivery report) that /ux still runs; the close anchor block is retained (required by lint-components structural.js and the play-creator G12 emit on every play), and the feat(model) commit is the separate lightweight persist step, so both coexist as C13 describes.