Pbi Challenge

Codex compatibility note:

• Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.
• Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
• User-question prompts mean to ask the user directly in Codex.
• Ignore Claude-specific mode-switch instructions when they appear.
• Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
• Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
• Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
• For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
• If a required step/tool cannot run in this environment, stop and ask the user before adapting.

Codex Project-Reference Loading (No Hooks)

Codex uses static project-reference loading instead of runtime-injected project docs. When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.

Always read:

• docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
• docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
• docs/project-reference/lessons.md (always-on guardrails and anti-patterns)

Missing/stale context route: If docs/project-config.json, the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any task-required reference doc is missing or stale, auto-run $project-init or the narrow setup route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $claude-md-init) before ordinary project-specific work. If Codex mirrors or AGENTS.md are missing/stale, ask the user to run $sync-codex; do not auto-run it.

Situation-based docs:

• Project structure/architecture/tech-stack/deployment/setup (any layer — backend, frontend, or infra): project-structure-reference.md
• Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md
• Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
• Spec authoring, docs/specs/ pathing, or TC format: feature-spec-reference.md, spec-system-reference.md, spec-principles.md
• Behavior/public-contract changes or spec-test-code sync: workflow-spec-test-code-cycle-reference.md plus the spec docs above
• Derived spec indexes/ERDs/reimplementation guides: spec-system-reference.md and source Feature Specs under docs/specs/
• Integration test implementation/review: integration-test-reference.md
• E2E test implementation/review: e2e-test-reference.md
• Code review/audit work: code-review-rules.md plus domain docs above based on changed files

Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.

[BLOCKING] Execute skill steps in declared order. NEVER skip, reorder, or merge steps without explicit user approval. [BLOCKING] Before each step or sub-skill call, update task tracking: set in_progress when step starts, set completed when step ends. [BLOCKING] Every completed/skipped step MUST include brief evidence or explicit skip reason. [BLOCKING] If Task tools are unavailable, create and maintain an equivalent step-by-step plan tracker with the same status transitions.

Quick Summary

Goal: Break drafter confirmation bias before grooming — by helping Dev BA PIC (Person In Charge — development Business Analyst responsible for technical review sign-off per squad) review BA drafters' PBI drafts with specific, actionable challenge prompts, surface every architectural-feasibility, vague-AC, missing-auth, cross-service, and M1-M7 gap so an INFEASIBLE or under-specified PBI never reaches grooming with a false APPROVE. AI provides analysis; human makes decision.

Summary:

• Main steps (8): (1) locate the BA drafter's PBI draft → (2) auto-detect module, confirm by asking the user directly BEFORE loading domain docs (domain-entities-reference + docs/specs/{App}/ + BR-{MOD} rules) → (3) Technical Feasibility analysis (architecture fit, entity conflicts, cross-service, complexity vs SP) → (4) AC Quality analysis (vagueness detector + M1-M7 checks) → (5) Cross-Cutting Concerns (auth matrix, seed data, migration, performance, UI Layout) → (6) generate SPECIFIC challenge prompts with suggested answers → (7) present Challenge Prompts FIRST, THEN AI Verdict (APPROVE / REQUEST_REVISION / ESCALATE_TO_LEAD) → (8) human records final decision by asking the user directly.
• CROSS-PERSON review, NOT self-review: a different reviewer (Dev BA PIC) challenges the BA drafter's PBI — NEVER your own draft (route self-review to $artifact-review --type=pbi). — why: external skepticism breaks blind spots that self-review rationalizes away.
• M1-M7 Compliance Gate is BLOCKING and drives the verdict (runs inside Steps 4-5): any M1-M5 or M7 mandate failure forces REQUEST_REVISION with a challenge prompt naming the violated mandate ID + exact section/line/AC; an APPROVE over an M1-M5 or M7 violation is itself defective.
• Order fights automation bias: Challenge Prompts FIRST so the Dev BA PIC forms their own view, THEN the AI Verdict; challenges must be SPECIFIC with suggested answers, never vague.
• AI provides ANALYSIS; the human makes the DECISION by asking the user directly — never auto-approve or auto-reject.

Key distinction: Collaborative review tool (drafter → reviewer flow), NOT self-review (use $artifact-review --type=pbi for AI self-review).

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Why This Skill Exists

PBI drafts routinely pass informal review unchallenged on architectural feasibility, vague AC, missing auth scenarios, cross-service impact. $refine generates PBIs but does not adversarially challenge them — creation tool, not review tool. $artifact-review --type=pbi provides AI self-review for drafter, but drafter has inherent blind spots about own assumptions. Separate reviewer (Dev BA PIC) applying AI-assisted challenge prompts breaks drafter confirmation bias before grooming — catches gaps drafter cannot catch themselves.

Why not just $artifact-review --type=pbi? Drafter runs it on own work; even with adversarial prompts, drafter rationalizes own choices. pbi-challenge invoked by different person with different mandate — external skepticism requires different author, not different tool on same author.

Alternatives Considered

Risk Assessment

Frontend/UI Context (if applicable)

When this task involves frontend or UI changes,

• Component patterns: docs/project-reference/frontend-patterns-reference.md
• Styling/BEM guide: docs/project-reference/scss-styling-guide.md
• Design system tokens: docs/project-reference/design-system/README.md

Workflow

1. Locate PBI draft — Find BA drafters' draft PBI in team-artifacts/pbis/ or path provided by user

2. Load domain context — Auto-detect module from PBI content. MANDATORY: Use ask the user directly to confirm detected module with Dev BA PIC before loading domain docs. Wrong module = wrong entity context = false APPROVE risk. Then load:

   • docs/project-reference/domain-entities-reference.md (entity definitions)
   • Relevant feature docs from docs/specs/{App}/
   • Existing business rules (BR-{MOD}-XXX) from feature docs

3. Technical Feasibility Analysis:

   • Can described features be built with the project's architecture?
   • Any domain entity conflicts? (cross-reference entity definitions)
   • Any cross-service implications? (message bus events, shared data between services)
   • Estimated complexity alignment (does scope match story points?)

4. AC Quality Analysis:

   • Vagueness detector: flag "should", "might", "TBD", "etc.", "various", "appropriate"
   • Coverage check: happy path + edge case + error case + authorization scenario
   • Missing scenarios: suggest specific additions based on feature type

5. Cross-Cutting Concerns Check:

   • Authorization section present and complete? (roles × CRUD matrix)
   • Seed data requirements addressed? (or explicit "N/A")
   • Data migration implications? (schema changes)
   • Performance considerations? (list/grid/export features)
   • UI Layout section present? If PBI involves UI: must have ## UI Layout per UI wireframe protocol with wireframe + components (with tiers) + states + design tokens. If backend-only: explicit "N/A". Flag missing UI visualization as a gap.

6. Generate Challenge Prompts — Output specific, actionable questions:

   • NOT vague: "needs work" or "improve AC"
   • SPECIFIC: "AC #2 says 'user can filter results' — which filters exactly? Suggest: status, date range, priority"

7. Present Challenge Prompts first, then AI Verdict — Output challenge prompts BEFORE the verdict to prevent automation bias. Dev BA PIC reads and forms their preliminary view, THEN sees: APPROVE / REQUEST_REVISION / ESCALATE_TO_LEAD

   • Technical decisions (feasibility, dependencies, cross-service impact, security): Dev BA PIC has unilateral veto power — no 2/3 vote needed
   • Non-technical decisions (UI/UX design, visual design, business value): 2/3 majority vote required (Dev BA PIC + UX BA + Designer BA per ba-team-decision-model)

8. ask the user directly — Dev BA PIC records their FINAL decision (APPROVE / REQUEST_REVISION / ESCALATE_TO_LEAD) in the Decision Record. This is the human decision step — NOT the workflow routing step (handled separately in Next Steps)

M1-M7 Compliance Gate (BLOCKING — drives the AI Verdict)

Contract: See .claude/skills/shared/sdd-artifact-contract.md → "AI-SDD Mandates (M1-M7)". This challenge enforces M6: a PBI draft that violates any of M1-M5 or M7 MUST produce an AI Verdict of REQUEST_REVISION with a challenge prompt that names the violated mandate ID and cites the exact PBI section + line/AC. An APPROVE over an M1-M5 or M7 violation is itself defective. (AI provides the analysis; the human still records the final decision.)

M1 governs vocabulary; M7 governs subject matter. A technical case written in impeccably tech-free prose satisfies M1 while violating M7 — that gap is the most common way business specs rot. A clean M1 pass is NEVER evidence of an M7 pass; challenge both.

Carriers are EXEMPT from M1/M2 — source identifiers are CORRECT inside [Source: ...], **Evidence**, CoveredBy: fields, legacy **IntegrationTest:** migration fields, YAML frontmatter, and ```mermaid ``` blocks. Only challenge leakage in PBI narrative prose (problem statement, AC text, scope, rule descriptions). Banned prose token list: docs/project-reference/spec-principles.md §3.2.

Run these six checks as part of Step 4 (AC Quality) and Step 5 (Cross-Cutting Concerns); any failure becomes a specific challenge prompt and forces REQUEST_REVISION:

• MUST ATTENTION M1 — Tech-agnostic prose. FAIL if problem statement, AC, or rule prose names framework/product, language-native type, or product/design-pattern class name (banned list spec-principles.md §3.2). Challenge: cite section + leaked token + business-term replacement. — why: stack-named prose locks the PBI to one implementation.
• MUST ATTENTION M2 — No source code in prose. FAIL if requirement expressed as class/method/file-path/namespace instead of business operation. Source identifiers belong only in evidence carriers. Challenge: cite section + line.
• MUST ATTENTION M3 — Abstract-IDs-first. FAIL if requirement/rule lacks logical ID (FR-/BR-/OP-), has logical ID but no [Source: namespace/service/id] abstract-anchor evidence, uses physical code coordinates or repository-root paths instead of abstract anchor, or makes anchor its primary citation. Evidence REQUIRED and KEPT, but SECONDARY to logical ID (physical coordinates live only in provenance sidecar).
• MUST ATTENTION M4 — Unambiguous AC. FAIL if any AC uses vague language ("should", "might", "appropriate", "various", "as needed"), two engineers could implement it differently while both claiming conformance, or no observable completion state / named error condition exists. (Extends Step-4 vagueness detector to M4 verdict.)
• MUST ATTENTION M5 — Implementable from artifact alone. FAIL if competent team with ZERO codebase knowledge could not build PBI on different stack from PBI alone (relies on reading source to understand it). Challenge: cite section + missing detail.
• MUST ATTENTION M7 — Business-visibility. Apply the demo test to each case's BODY: "what would a stakeholder SEE change?" — no answer → FAIL as TECHNICAL-ONLY and force REQUEST_REVISION. Every Given = a state a user could arrange; every When = an action a user could take; every Then = an outcome a user could see. FAIL a When that is an invocation (a handler runs, a consumer receives, a job fires, data syncs) or a Then asserting schema/type/nullability/call-count. Judge the BODY, never the title or ID. Challenge: cite section + the offending Given/When/Then + a demoable rewrite to consider. — why: a technical case in business clothing ships an un-demoable AC to grooming.

If ANY check fails → AI Verdict is REQUEST_REVISION; tag each violated mandate ID with its concrete section/line citation in the Challenge Prompts and the AI Verdict Reason.

Output

## PBI Challenge Review

**PBI:** {PBI filename}
**Reviewer:** Dev BA PIC
**Date:** {date}
**Module:** {detected module code}

### Technical Feasibility

**Status:** FEASIBLE | CONCERNS | INFEASIBLE
{Analysis with evidence — cite domain entities, service boundaries, architecture constraints}

### AC Quality

**Status:** GOOD | NEEDS_REVISION | POOR

| AC # | Issue            | Suggested Fix             |
| ---- | ---------------- | ------------------------- |
| {#}  | {specific issue} | {specific fix suggestion} |

### Cross-Cutting Concerns

| Concern        | Status    | Issue    |
| -------------- | --------- | -------- |
| Authorization  | ✅/❌     | {detail} |
| Seed Data      | ✅/❌/N/A | {detail} |
| Data Migration | ✅/❌/N/A | {detail} |
| Performance    | ✅/❌/N/A | {detail} |

### Challenge Prompts for BA Drafters

1. {Specific actionable question with suggested answer}
2. {Specific actionable question with suggested answer}
3. {Specific actionable question with suggested answer}

### AI Verdict

**{APPROVE | REQUEST_REVISION | ESCALATE_TO_LEAD}**
**Reason:** {evidence-based justification}
**Confidence:** {X%} — {what was verified vs. what needs more investigation}

### Decision Record

**Dev BA PIC Decision:** {filled after human review by asking the user directly}
**Vote:** {approve / request-revision / escalate}
**Conditions:** {if any}
**Drafter Response (on revision):** {drafter's response to each challenge prompt — filled when Dev BA PIC re-runs on revised PBI}
**Resolution:** {how each challenge prompt was addressed, deferred, or accepted as known risk}
**Stored at:** `plans/reports/pbi-challenge-{YYMMDD}-{pbi-id}.md` (save output there for audit trail)

Key Rules

• AI provides ANALYSIS, human makes DECISION — Never auto-approve or auto-reject
• Challenge prompts must be specific — Include suggested answers, not just questions
• Domain context required — Always load entity reference + feature docs before analysis
• Technical veto scope — Dev BA PIC CAN veto: architecture feasibility, dependency correctness, cross-service impact, performance, security. CANNOT veto: UI/UX design, visual design, business value (see ba-team-decision-model-protocol.md §2)
• Evidence-based — Every concern raised must cite source (protocol section, entity definition, feature doc)
• Constructive tone — Focus on improving the PBI, not criticizing the drafters

Next Steps

MANDATORY IMPORTANT MUST ATTENTION — NO EXCEPTIONS after completing this skill, you MUST ATTENTION use ask the user directly to present these options. Do NOT skip because the task seems "simple" or "obvious" — the user decides:

• "$dor-gate (Recommended)" — If APPROVE: validate DoR before grooming
• "$refine" — If REQUEST_REVISION: BA drafters revise, then re-run $pbi-challenge
• "Escalate to Engineering Manager" — If ESCALATE_TO_LEAD: document concern for technical consultation
• "Skip, continue manually" — user decides

[IMPORTANT] Use task tracking to break ALL work into small tasks BEFORE starting.

Evidence Gate: MANDATORY IMPORTANT MUST ATTENTION — every claim requires file:line proof or traced evidence with confidence percentage (>80% to act).

AI Mistake Prevention — Failure modes to avoid on every task:

Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting. Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect. Assume existing values are intentional — ask WHY before changing OR flagging one as a defect. Before changing or reporting a constant, limit, flag, cutoff, wording, or pattern, read nearby context and history, the CALLER's ordering, and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. Assert the outcome your system owns, not the intermediate state your infrastructure owns. When verifying async work, assert the final business state — never the delivery/retry bookkeeping held in shared infrastructure that any co-running process can write. Such a check passes when run alone and flakes the moment anything else shares that infrastructure. Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

UI System Context — For ANY task touching .ts, .html, .scss, or .css files:

MUST ATTENTION READ before implementing:

1. docs/project-reference/frontend-patterns-reference.md — component base classes, stores, forms
2. docs/project-reference/scss-styling-guide.md — BEM methodology, SCSS variables, mixins, responsive
3. docs/project-reference/design-system/README.md — design tokens, component inventory, icons

Reference docs/project-config.json for project-specific paths.

BA Team Decision Model — 2/3 majority vote: Dev BA PIC + UX BA + Designer BA per squad. 2 of 3 agree = decision final. 3-way split = escalate to full squad + Tech Leads + Engineering Manager.

Technical Veto: Dev BA PIC can unilaterally veto on: architecture feasibility, dependency correctness, cross-service impact, performance, security. CANNOT veto: UI/UX design, visual design, business value, user research.

Rules: Disagree-and-commit after vote. Grooming override requires >75% non-BA squad vote. Record decisions in PBI Validation Summary (member, role, vote, notes).

Escalation: Tech uncertainty → Engineering Manager. Business value → PO. Design feasibility → UX BA + Designer BA consensus.

Refinement DoR Checklist — ALL 7 criteria MUST ATTENTION pass before grooming:

1. User story template — "As a {role}, I want {goal}, so that {benefit}" format
2. AC testable & unambiguous — GIVEN/WHEN/THEN. No "should/might/TBD/various/appropriate". Min 3 scenarios (happy, edge, error) + 1 auth scenario
3. Wireframes attached — UI features: ## UI Layout with wireframe + components + states + tokens. Backend-only: explicit "N/A"
4. UI design ready — Visual design + component decomposition tree + design-spec linked ($design-spec artifact or inline UI specs in ## UI Layout) for any PBI with UI work. Backend-only: "N/A"
5. AI pre-review passed — $artifact-review --type=pbi or $pbi-challenge returned PASS or WARN (not FAIL)
6. Story points estimated — Fibonacci 1-21 + complexity (Low/Medium/High). >13 SP → recommend split
7. Dependencies table complete — Dependency, Type (must-before/can-parallel/blocked-by/independent), Status

Failure fixes: Vague AC → specify exact CRUD + roles. Missing auth → add roles × CRUD table. No wireframes → UX BA creates. TBD in AC → replace with decision.

Estimation Framework — Bottom-up first; SP DERIVED; output min-max range when likely ≥3d. Stack-agnostic. Baseline: 3-5yr dev, 6 productive hrs/day. AI estimate assumes Claude Code + project context.

Method:

1. Blast Radius pass (below) — drives code AND test cost
2. Decompose phases → hours/phase → bottom_up_hours = Σ phase_hours
3. likely_days = ceil(bottom_up_hours / 6) × productivity_factor
4. Sum Risk Margin (base + add-ons) → max_days = likely_days × (1 + margin)
5. min_days = likely_days × 0.9
6. Output as range when likely_days ≥3; single point allowed <3 (still record margin)
7. man_days_ai = same range × AI speedup
8. story_points DERIVED from likely_days via SP-Days — NEVER driver. Disagreement >50% → trust bottom-up

Productivity factor: 0.8 strong scaffolding+codegen+AI hooks · 1.0 mature default · 1.2 weak patterns · 1.5 greenfield

Cost Driver Heuristic (apply BEFORE work-type row):

• UI dominates in CRUD/business apps — 1.5-3x backend (states, validation, responsive, a11y, polish)
• Backend dominates ONLY: multi-aggregate invariants, cross-service contracts, schema migrations, heavy query/perf, new event flows

Reuse-vs-Create axis (PRIMARY lever, per layer):

UI tier	Cost
Reuse component on existing screen	0.1-0.3d
Add control/column to existing screen	0.3-0.8d
Compose components into NEW screen	1-2d
NEW screen, custom layout/states/validation	2-4d
NEW shared/common component (themed, tested)	3-6d+

Backend tier	Cost
Reuse query/handler from new place	0.1-0.3d
Small update existing handler/entity	0.3-0.8d
NEW query on existing repo/model	0.5-1d
NEW command/handler on existing aggregate (additive)	1-2d
NEW aggregate/entity (repo, validation, events)	2-4d
NEW cross-service contract OR schema migration	2-4d each
Multi-aggregate invariant / heavy domain rule	3-5d

Rule: Sum tiers across UI+backend+tests, apply productivity factor. Reuse short-circuits tiers — call out.

Test-Scope drivers (compute test_count EXPLICITLY — "+tests" hand-wave is #1 failure):

Driver	Count
Happy-path journeys	1 per story / AC main flow
State-machine transitions	reachable transitions × allowed actors
Multi-entity state combos	state(A) × state(B) — REACHABLE only, not Cartesian
Authorization matrix	(owner, non-owner, elevated, unauth) × each mutation
Validation rules	1 per required field / boundary / format / cross-field
UI states (per new screen/dialog)	happy, loading, empty, error, partial — present only
Negative paths / invariants	1 per violatable business rule

Test tier (Trad, incl. setup+assert+flake)	Cost
1-5 cases, fixtures reused	0.3-0.5d
6-12 cases, 1 new fixture	0.5-1d
13-25 cases, multi-entity setup	1-2d
26-50 cases OR new state-machine coverage	2-3d
>50 cases OR full E2E journey	3-5d

Test multipliers: new fixture/seed harness +0.5d · cross-service/bus assertion +0.3d each · UI E2E ×1.5 · each new role +1-2 cases

Blast Radius (mandatory pre-pass — affects code AND test):

1. Files/components directly modified — count
2. Of those, "complex" (>500 LOC, multi-handler, central, frequently-modified) — count
3. Downstream consumers (callers, event subscribers, cross-service) — list
4. Shared/common code touched (multi-app blast) — yes/no
5. Regression scope — areas needing re-test

Rule: Complex touch → add risk_factors. Each downstream consumer → +1-3 regression cases. Blast >5 areas OR >2 complex → re-evaluate SPLIT before estimating.

Risk Margin (drives max bound):

likely_days	Base margin
<1d trivial	+10%
1-2d small additive	+20%
3-4d real feature	+35%
5-7d large	+50%
8-10d very large	+75%
>10d	+100% AND flag SHOULD SPLIT

Risk-factor add-ons (additive — enumerate in risk_factors):

Factor	+margin
touches-complex-existing-feature (>500 LOC, multi-handler, central)	+20%
cross-service-contract change	+25%
schema-migration-on-populated-data	+25%
new-tech-or-unfamiliar-pattern	+30%
regression-fan-out (≥3 downstream areas re-test)	+20%
performance-or-latency-critical	+20%
concurrency-race-event-ordering	+25%
shared-common-code (multi-consumer/multi-app)	+25%
unclear-requirements-or-design	+30%

Collapse rule: total margin >100% → STOP, split (padding past 2x is dishonesty). Margin <15% on likely_days ≥5 → under-estimated, widen.

Work-Type Caps (hard ceilings on likely_days):

Work type	Max SP	Max likely
Single field / config flag / style fix	1	0.5d
Add property to existing model + bind to existing UI	2	1d
Additive endpoint + minor UI control (button/menu/column), reuses fixtures	3	2-3d
Additive endpoint + NEW UI surface OR additive multi-layer + new domain rule + 2+ test files	5	3-5d
NEW model/aggregate OR migration OR cross-module contract OR heavy test (>1.5d) OR NEW UI + non-trivial backend	8	5-7d
NEW UI surface + (NEW aggregate OR migration OR cross-service contract)	13	SHOULD split
Cross-service contract + migration combined	13	SHOULD split
Beyond	21	MUST split

SP→Days (validation only): 1=0.5d/0.25d · 2=1d/0.35d · 3=2d/0.65d · 5=4d/1.0d · 8=6d/1.5d · 13=10d/2.0d (Trad/AI likely) AI speedup: SP 1≈2x · 2-3≈3x · 5-8≈4x · 13+≈5x. AI cost = (code_gen × 1.3) + (test_gen × 1.3) (30% review overhead).

MANDATORY frontmatter:

story_points: <n>
complexity: low | medium | high | critical
man_days_traditional: '<min>-<max>d' # range when likely ≥3d; '<N>d' when <3d
man_days_ai: '<min>-<max>d'
risk_margin_pct: <n> # base + add-ons
risk_factors: [touches-complex-existing-feature, regression-fan-out] # closed-list from add-ons; [] if none
blast_radius:
    touched_areas: <n>
    complex_touched: <n>
    downstream_consumers: [list or count]
    shared_common_code: yes | no
estimate_scope_included: [code, integration-tests, frontend, i18n, docs]
estimate_scope_excluded: [unit-tests, e2e, perf, deployment, code-review-rounds]
estimate_reasoning: |
    5-7 lines covering:
    (a) UI tier — row applied
    (b) Backend tier — row applied
    (c) Test scope — case breakdown by driver, file count, fixtures, tier row
    (d) Cost driver — dominant tier + why
    (e) Blast radius — touched, complex, regression scope
    (f) Risk factors — list driving margin; why not larger/smaller
    Example: "UI: compose Form/Table/Dialog → NEW screen (~1.5d). Backend: NEW command on existing aggregate,
    reuses validation+repo (~1d). Tests: 4 transitions × 2 actors + 3 validation + 2 UI states = 13 cases,
    1 new fixture → tier 13-25 ~1.5d. Driver: UI composition + new states. Blast: 4 areas, 1 complex.
    Risk: base 35% + touches-complex +20% = 55% → max 3.9d → range 2.5-4d."

Sanity self-check:

• likely_days ≥3d and single-point? → reject, must be range
• Margin <15% on likely_days ≥5d? → under-estimated, widen
• Margin >100%? → STOP, split instead of buffer
• Complex existing feature touched, no regression budget in (c)? → reject
• Blast >5 areas OR >2 complex, no split discussion? → reject
• Purely additive on existing model AND existing UI? → cap SP 3 unless tests >1.5d
• NEW UI surface (page/complex form/dashboard)? → SP 5+ even if backend one endpoint
• Backend cross-service / migration / multi-aggregate? → SP 8+ regardless of UI
• bottom_up_hours / 6 vs SP-Days disagreement >50%? → trust bottom-up, downgrade SP
• Without tests, SP drops ≥1 bucket? → tests dominate; state explicitly
• Reasoning called out UI vs backend vs blast vs risk factors? → if missing, add

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

Sequential Thinking Protocol — Structured multi-step reasoning for complex/ambiguous work. Use when planning, reviewing, debugging, or refining ideas where one-shot reasoning is unsafe.

Trigger when: complex problem decomposition · adaptive plans needing revision · analysis with course correction · unclear/emerging scope · multi-step solutions · hypothesis-driven debugging · cross-cutting trade-off evaluation.

Format (explicit mode — visible thought trail):

1. Thought N/M: [aspect] — one aspect per thought, state assumptions/uncertainty
2. Thought N/M [REVISION of Thought K]: ... — when prior reasoning invalidated; state Original / Why revised / Impact
3. Thought N/M [BRANCH A from Thought K]: ... — explore alternative; converge with decision rationale
4. Thought N/M [HYPOTHESIS]: ... then [VERIFICATION]: ... — test before acting
5. Thought N/N [FINAL] — only when verified, all critical aspects addressed, confidence >80%

Mandatory closers: Confidence % stated · Assumptions listed · Open questions surfaced · Next action concrete.

Stop conditions: confidence <80% on any critical decision → escalate by asking the user directly · ≥3 revisions on same thought → re-frame the problem · branch count >3 → split into sub-task.

Implicit mode: apply methodology internally without visible markers when adding markers would clutter the response (routine work where reasoning aids accuracy).

Deep-dive: see $sequential-thinking skill (.claude/skills/sequential-thinking/SKILL.md) for worked examples (API design, debugging, architecture), advanced techniques (spiral refinement, hypothesis testing, convergence), and meta-strategies (uncertainty handling, revision cascades).

• MANDATORY IMPORTANT MUST ATTENTION read frontend-patterns-reference, scss-styling-guide, design-system/README before any UI change.

• MANDATORY MUST ATTENTION estimation: bottom-up phase hours drive man_days_traditional (Σh/6 × productivity_factor); SP DERIVED. UI cost usually dominates — bump SP one bucket if NEW UI surface (page/complex form/dashboard). Frontmatter MUST include story_points, complexity, man_days_traditional, man_days_ai, estimate_scope_included, estimate_scope_excluded, estimate_reasoning (UI vs backend cost driver). Cap SP 3 for additive-on-existing-model+existing-UI unless test scope >1.5d. SP 13 SHOULD split, SP 21 MUST split.

MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

MUST ATTENTION apply sequential-thinking — multi-step Thought N/M, REVISION/BRANCH/HYPOTHESIS markers, confidence % closer; see $sequential-thinking skill.

MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface am

…(truncated)