universal-dev-standards 5.16.0 → 6.0.0

package/bundled/ai/standards/model-selection.ai.yaml

@@ -8,8 +8,8 @@ standard:
   description: AI 模型分級選擇策略
 
   meta:
-    version: "2.0.0"
-    updated: "2026-04-13"
+    version: "2.0.1"
+    updated: "2026-06-10"
     source: core/model-selection.md
     description: "三層模型分級選擇策略 + 多模型池能力管理（XSPEC-027）"
     inspired_by: superpowers/subagent-driven-development
@@ -176,6 +176,15 @@ standard:
         action: "自動切換備用模型，上報 P1 Issue"
         priority: critical
 
+  navigation_integration:
+    description: >
+      The ai-response-navigation standard (Rule R6, optional) allows next-step suggestion
+      options to carry a Tier annotation (〔model: Fast〕 / 〔model: Standard〕 / 〔model: Capable〕).
+      The complexity signals in this standard serve as the judgment basis for those annotations.
+    vendor_neutral_principle: >
+      Tier names (Fast / Standard / Capable) are vendor-agnostic labels.
+      Each platform independently maps these tiers to its available models.
+
 physical_spec:
   type: checklist
   validator:

package/bundled/ai/standards/observability-standards.ai.yaml

@@ -8,6 +8,16 @@ meta:
   source: core/observability-standards.md
   description: Three pillars observability framework (Logs, Metrics, Traces) with Golden Signals and maturity model
 
+# XSPEC-070 Phase 2 — skill↔standard content-coverage audit.
+# Consumed by scripts/check-skill-content-coverage.ts. The anchor skill
+# (observability-assistant) is a thin launcher; require it to carry at least 30%
+# of the standard's depth so a stale skeleton is flagged (CONTENT-003).
+audit:
+  min_skill_ratio: 0.30
+  mandatory_keywords:
+    - golden signals
+    - maturity
+
 three_pillars:
   logs: "Discrete events — debugging, audit, error details (see logging.ai.yaml)"
   metrics: "Numerical measurements over time — dashboards, alerting, capacity"

package/bundled/ai/standards/performance-standards.ai.yaml

@@ -1,7 +1,7 @@
 # Performance Standards (AI-Optimized)
 # Source: core/performance-standards.md
 # Guide: core/guides/performance-guide.md
-# Version: 1.0.0
+# Version: 1.2.0
 
 iso25010_efficiency:
   time_behavior: "Response time, throughput"
@@ -127,3 +127,48 @@ capacity_planning:
     cpu: "Plan at 70%"
     memory: "Plan at 80%"
     storage: "Plan at 70%"
+
+# XSPEC-286: Migration Non-Functional Parity (axis 6 of XSPEC-284 completeness matrix)
+# Covers "function correct, data correct, but RUNS differently" omissions in a legacy rewrite.
+# Differential oracle: legacy is the baseline, "no regression beyond declared tolerance" is pass.
+migration_non_functional_parity:
+  axis: "6 (non-functional) of XSPEC-284 migration completeness matrix"
+  principle: "Legacy is the baseline; declared tolerance, not absolute target. Divergence self-reports."
+  why_gap: "General baseline/drift compares a version to its OWN prior baseline, not new-vs-legacy. Per-request and behavior-snapshot parity both pass while the system silently runs slower / loses a lock semantic."
+  derive: # R3 mechanized baseline capture
+    sources:
+      key_routes: "p50/p95/p99 latency per critical path"
+      hot_queries: "per-query latency, rows scanned (slow-query log)"
+      background_jobs: "job duration, throughput records/min"
+      connection_pool: "min/max connections, idle/connection timeout"
+      timeout_ratelimit: "per-endpoint timeout, requests/min, burst"
+      transaction_config: "isolation level"
+    note: "Captured set is both the regression baseline AND the resource/limit parity checklist."
+  regression_gate: # R1 performance regression differential
+    oracle: "measure new-system path, compare vs legacy baseline within declared tolerance"
+    default_tolerance:
+      p50_latency: "<= +10% vs legacy"
+      p95_latency: "<= +15% vs legacy"
+      p99_latency: "<= +20% vs legacy"
+      throughput: "<= -10% decrease vs legacy"
+    per_path_configurable: true
+    rollout: "shadow (measure-only) first to calibrate per-path tolerance, then promote to blocking"
+    gate_timing: [pre-UAT, post-cutover]
+  concurrency_isolation: # R2
+    method: "drive a race with concurrent stress, then assert DOMAIN INVARIANTS (not one-at-a-time output checks)"
+    invariants:
+      conservation: "SUM(balance) unchanged after N concurrent transfers"
+      uniqueness: "no duplicate sequence number under concurrent allocation"
+      no_lost_update: "committed write not silently replaced"
+      ordering: "events applied in guaranteed order under concurrency"
+    blocks_on: "isolation downgrade (e.g. SERIALIZABLE -> READ COMMITTED, removed row lock)"
+    boundary: "state-transition legality and temporal invariants owned by XSPEC-287 (axis 8); concurrency race owned here (axis 6)"
+    gate_timing: [pre-UAT]
+  resource_limit_parity: # R4
+    checklist: [request_timeout, rate_limit, connection_pool, batch_size, transaction_isolation]
+    rule: "each item matched OR has a declared justified delta; undeclared delta blocks cutover"
+  completeness_declaration:
+    derive: "Step1 mechanized baseline"
+    oracle: "Step2 regression differential + Step3 invariant assertions"
+    gate_timing: "pre-UAT + post-cutover"
+    reuse: "general baseline/drift + observability-assistant measurement; adds only migration before/after + concurrency-isolation semantics"

package/bundled/ai/standards/pii-classification.ai.yaml

@@ -3,7 +3,7 @@
 
 id: pii-classification
 title: PII Classification and Handling Standards
-version: "1.0.0"
+version: "1.1.0"
 status: Active
 tags: [compliance, privacy, pii, gdpr, data-protection, security]
 summary: |
@@ -107,3 +107,17 @@ requirements:
       - "New feature: 'Save payment method' → PIA required (TIER-1 card data)"
       - "PIA template: docs/templates/privacy-impact-assessment.md"
       - "PIA outcome: fingerprint auth approved with biometric data stored only on-device"
+
+# Hand-off contract (XSPEC-292 T16): how a classification reaches its consumers
+hand_off:
+  trigger:
+    - "New feature design: REQ-006 PIA classifies new PII fields before implementation"
+    - "PR/scan time: a PII field with no tier is a blocking finding"
+    - "Data-dictionary change: tier added/removed -> re-notify consumers"
+  interface: "PII classification registry entry per field {field, tier, purpose, legal_basis, masking_rule, retention}; consumers register per data-contract REQ-005"
+  consumers:
+    - "logging-standards: applies masking_rule to TIER-1/2 in non-prod"
+    - "audit-trail: records access/export/erasure events"
+    - "security-standards: enforces encryption for TIER-1"
+    - "privacy/compliance owner: notified on new TIER-1 field or classification change"
+  state: "Found -> Classified -> Handled (masked/encrypted/retention) -> Verified; a field stuck in Found blocks release"

package/bundled/ai/standards/pipeline-security-gates.ai.yaml

@@ -13,6 +13,7 @@ standard:
     - "Secrets scan at pre-commit — block ALL commits containing secrets"
     - "SAST after build — block Critical/High findings"
     - "SCA + SBOM generation at package stage"
+    - "Attestation verification before deploy — verify artifact checksum, cosign signature, SLSA provenance (consume supply-chain-attestation output; never generate SBOM/signature without verifying it)"
     - "DAST after staging deploy — warn on findings, require approval for Critical"
     - "Never skip security gates with --force or emergency bypass without audit trail"
     - "Treat security gate failures as pipeline failures, not warnings"
@@ -51,6 +52,14 @@ gate_positions:
     block_on: ["Critical CVE with fix available"]
     warn_on: ["High CVE", "outdated dependencies"]
     sbom_format: ["spdx", "cyclonedx"]
+  pre_deploy_attestation:
+    type: attestation_verification
+    tools: ["cosign", "sha256sum", "slsa-verifier"]
+    scope: "packaged release artifact (archive / container image)"
+    block_on: ["signature verification failure", "checksum mismatch", "missing SLSA provenance"]
+    warn_on: ["SLSA level below target (>= L2 recommended for public release)"]
+    consumes: supply-chain-attestation
+    note: "Runs after package_stage, before deploy — closes the generate-but-never-verify gap"
 
 bypass_policy:
   allowed: false
@@ -66,6 +75,7 @@ failure_behavior:
 integration_points:
   secrets_vault: "Integrate with HashiCorp Vault or AWS Secrets Manager for secrets injection"
   sbom_registry: "Upload SBOM to dependency-track or grype-db for continuous monitoring"
+  artifact_signing: "Verify SBOM/provenance signatures and checksum with cosign before release (see supply-chain-attestation)"
   incident_response: "Critical findings automatically create incident tickets"
 
 physical_spec:

package/bundled/ai/standards/privacy-standards.ai.yaml

@@ -1,5 +1,5 @@
 id: privacy-standards
 meta:
-  version: "1.0.0"
-  updated: "2026-04-01"
+  version: "1.1.0"
+  updated: "2026-06-18"
   source: core/privacy-standards.md

package/bundled/ai/standards/project-context-memory.ai.yaml

@@ -12,8 +12,8 @@ standard:
     - "Use identified paths and specific names (unlike Developer Memory)"
 
   meta:
-    version: "1.0.0"
-    updated: "2026-02-09"
+    version: "1.2.0"
+    updated: "2026-06-18"
     source: core/project-context-memory.md
     description: System for capturing, retrieving, and enforcing project-specific context, architectural decisions, and domain knowledge
 

package/bundled/ai/standards/refactoring-standards.ai.yaml

@@ -3,8 +3,8 @@
 
 id: refactoring-standards
 meta:
-  version: "2.0.0"
-  updated: "2026-01-21"
+  version: "2.2.0"
+  updated: "2026-07-01"
   source: core/refactoring-standards.md
   guide: core/guides/refactoring-guide.md
   description: Refactoring guidelines with tactical, strategic, and safety strategies including decision matrix
@@ -292,9 +292,14 @@ metrics:
     - metric: Coupling
       measurement: Module dependencies count
       target: Reduce dependencies
-    - metric: Code Duplication
+    - metric: Code Duplication (textual)
       measurement: Duplicate percentage
       target: "< 3%"
+      note: Detects textual duplication only; cannot detect semantic duplication (see semantic_duplication)
+    - metric: Semantic Duplication
+      measurement: Golden / architecture test
+      target: 0 unmanaged domain facts
+      note: Static analysis cannot detect the same domain fact re-implemented across call sites
 
   test_quality:
     - metric: Test Coverage
@@ -314,6 +319,40 @@ metrics:
       source: Rollback count
       expected: Should decrease
 
+# Semantic Duplication & Copy-Drift (issue #142)
+semantic_duplication:
+  anti_pattern:
+    id: copy-drift
+    name: Copy-Drift
+    definition: Same domain fact implemented in multiple places, OR a derived value persisted without an enforced binding to its source, so the copies drift apart independently
+    why_undetected: Copies are not byte-identical (paraphrased logic, formula right in one place and wrong in another), so textual-duplication metrics report nothing
+    symptoms:
+      - List view disagrees with detail view
+      - Stored counter double-counts because one update path's decrement/rollback branch was skipped or commented out
+      - Same formula gives different answers in different modules
+      - Scope over-reach where one path adjusts an aggregate others also touch
+
+  pattern:
+    id: single-source-of-truth
+    name: Single Source of Truth / Derive-Don't-Duplicate
+    rules:
+      - one_unit_per_fact: Extract each domain fact into a single classifier/calculator/resolver; every call site calls it, no re-implementations or paraphrases
+      - derive_dont_store: Prefer computing on read over persisting a second copy; a value always derived cannot drift
+      - aggregate_as_projection: If an aggregate must be stored, treat it as a projection of its detail rows and recompute it at a single choke point (e.g. SaveChanges interceptor or one shared recompute() function) so every write path (incl. async jobs and failure write-backs) stays consistent
+      - never_incremental_adjust: Never let an individual path apply incremental "col = col + delta" to a stored aggregate; that is how decrement/rollback branches get skipped and counters diverge
+      - lock_with_tests: Use a golden test to pin the single source of truth, and an architecture test that fails if the rule is redefined anywhere else
+
+  intentional_divergence_registry:
+    when: New system intentionally diverges from legacy behavior (e.g. legacy function returns X but legacy pipeline reconciles it to Y; the port folds that reconciliation into the single unit so it returns Y directly)
+    actions:
+      - Register each intentional divergence (legacy behavior, new behavior, rationale, owning fact)
+      - Pin the new behavior with a golden test so a future "correction" back to legacy fails the build
+      - Feed the registry into any differential test against legacy so the divergence is treated as expected, not a regression
+
+  adopter_notes:
+    - Per-function legacy-vs-new diffing produces candidates, not verdicts; adjudicate each against the ENTIRE legacy pipeline (which may already reconcile the difference downstream) before calling it a bug
+    - Extract legacy function bodies programmatically / token-based (not by hand) to avoid reintroducing transcription errors
+
 # Team Collaboration
 team_collaboration:
   pr_size_limits:
@@ -456,8 +495,34 @@ rules:
     instruction: Keep PRs under 200 lines; split larger refactorings
     priority: recommended
 
+  - id: single-source-of-truth
+    trigger: same domain fact (classification, rule, calculation) needed at multiple call sites
+    instruction: Extract one shared classifier/calculator/resolver and call it everywhere; never re-implement or paraphrase the fact
+    priority: required
+
+  - id: derive-dont-duplicate
+    trigger: a derived value (aggregate, counter, denormalized field) is being persisted
+    instruction: Prefer deriving on read; if it must be stored, recompute it as a projection at a single choke point and never apply incremental col = col + delta adjustments per write path
+    priority: required
+
+  - id: lock-single-source-with-tests
+    trigger: after establishing a single source of truth for a domain fact
+    instruction: Add a golden test to pin it and an architecture test that fails if the rule is redefined elsewhere
+    priority: recommended
+
+  - id: register-intentional-divergence
+    trigger: new system intentionally diverges from legacy behavior during a port/migration
+    instruction: Record it in an intentional-divergence registry, pin with a golden test, and feed differential tests so it is treated as expected not a regression
+    priority: required
+
+  - id: adjudicate-diff-against-pipeline
+    trigger: reviewing per-function legacy-vs-new diffs
+    instruction: Treat diffs as candidates only; adjudicate each against the entire legacy pipeline before calling it a bug, and extract legacy bodies programmatically to avoid transcription errors
+    priority: recommended
+
 related_standards:
   - test-driven-development.md
   - testing-standards.md
+  - test-governance.md
   - code-review-checklist.md
   - checkin-standards.md

package/bundled/ai/standards/resource-cost-boundary.ai.yaml

@@ -0,0 +1,279 @@
+# Resource / Cost Boundary Declaration Standards - AI Optimized
+# Sources:
+#   v1.0.0 — XSPEC-277 Resource / Cost Boundary Declaration (cost burn as a declared, fail-closed boundary)
+#            XSPEC-276 (parent boundary-materialization lens; cost is the split-out dimension)
+#            XSPEC-285 (VibeOps proactive cost governance — the enforcement/executor face)
+
+id: resource-cost-boundary
+title: Resource / Cost Boundary Declaration Standards (Explicit, Machine-Readable, Fail-Closed Budgets)
+version: "1.0.0"
+status: Active
+tags: [cost-boundary, resource-budget, token-budget, cost-burn, fail-closed, governance-gate, llm-native, budget-declaration, runaway-loop]
+created: 2026-06-17
+updated: 2026-06-17
+
+spec_ref: XSPEC-277   # Resource / Cost Boundary Declaration complete spec
+
+references:
+  - XSPEC-277   # v1.0.0 source — Resource / Cost Boundary Declaration
+  - XSPEC-276   # Parent boundary-materialization lens (cost = split-out dimension)
+  - XSPEC-285   # VibeOps proactive cost governance — enforcement/executor face
+  - XSPEC-191   # Unit-economics PoC / BudgetGuard (reference implementation)
+  - XSPEC-270   # Model right-sizing router (cost-driven downgrade)
+  - XSPEC-037   # Capability declaration (fail-closed posture mirrored)
+  - DEC-024     # Pareto evolution token-cost gate (reference implementation)
+
+summary: |
+  The resource consumption of an agentic / LLM execution unit (pipeline run, agent, role) is
+  often implicit: token usage, loop/iteration count, retry count, per-run cost ceiling,
+  wall-clock, call rate. When those bounds are not explicitly declared and enforced, runaway
+  loops and token burn are a known LLM-native failure mode (cost burn).
+
+  This standard makes the resource/cost boundary a first-class, machine-readable, fail-closed
+  declaration. Any LLM execution unit MUST declare its resource budget; a runtime breach MUST
+  fail-closed per the declared behaviour. It is the COST dimension of boundary materialization
+  (XSPEC-276) — the one dimension UDS has no existing standard for, and concrete enough to be
+  AI-executable, so it is split out as a narrow standard.
+
+  REQ-001~005: a resource budget taxonomy (token/iteration/retry/cost_usd/wallclock/rate); a
+  machine-readable resource_budget: declaration (kind + limit + breach behaviour); a
+  fail-closed check-resource-budget gate (undeclared -> warn/block; runtime breach -> abort);
+  convergence of existing point mechanisms as reference implementations; and budget value
+  sovereignty (mechanism standardized, ceiling values owned by the adopter). This standard is
+  the "declare what bounds" half; XSPEC-285 is the "enforce/govern" half.
+
+scope:
+  applies_to:
+    - Any LLM execution unit (pipeline run, agent, role) whose resource consumption must be bounded
+    - Plans / agent configs / role configs that carry a resource_budget declaration
+    - Budget-breach run reports used as cost-governance / audit evidence
+  excludes:
+    - The budget VALUES themselves (actual ceilings) — owned by the adopter/customer (a project/economics decision)
+    - Enforcement-engine wiring (e.g. the VibeOps proactive cost-governance executor, XSPEC-285) — downstream
+    - Latency/throughput performance targets — that is performance-standards (adjacent, distinct)
+
+budget_taxonomy:
+  description: |
+    A standard set of resource budget kinds. A unit need not declare every kind, but a kind
+    it relies on for safety MUST be declared (an unbounded relied-upon kind is a violation).
+  kinds:
+    - kind: token
+      bound: input / output / total token ceiling
+      typical_breach: prompt/output explosion
+    - kind: iteration
+      bound: loop / iteration / tool-round upper bound
+      typical_breach: runaway loop
+    - kind: retry
+      bound: retry upper bound
+      typical_breach: unbounded re-attempt
+    - kind: cost_usd
+      bound: per-call / per-run / per-session cost ceiling
+      typical_breach: silent budget burn
+    - kind: wallclock
+      bound: timeout
+      typical_breach: hung run
+    - kind: rate
+      bound: call frequency
+      typical_breach: call storm
+
+declaration_format:
+  description: |
+    A first-class resource_budget: block embedded in a plan / agent / role config. Each entry
+    carries a kind + (optional) scope + limit value + on_breach behaviour.
+  example: |
+    resource_budget:
+      - kind: cost_usd
+        scope: per_run
+        limit: 3.00
+        on_breach: abort
+      - kind: iteration
+        limit: 60
+        on_breach: abort
+      - kind: retry
+        limit: 3
+        on_breach: warn
+      - kind: token
+        scope: total
+        limit: 400000
+        on_breach: abort
+  on_breach_values: [warn, abort]
+
+reference_implementations:
+  description: |
+    Existing VibeOps point mechanisms converge onto this standard as reference implementations
+    (REQ-004) — unified, not re-invented.
+  mappings:
+    - mechanism: "orchestrator quality profile max_retries / max_retry_budget_usd"
+      budget_kind: "retry / cost_usd (per-task fix-loop)"
+    - mechanism: "BudgetGuard / PoC abort max_cost_per_session_usd / min_cache_hit_ratio (XSPEC-191)"
+      budget_kind: "cost_usd / rate"
+    - mechanism: "Pareto Evolution Gate token-cost dimension (DEC-024)"
+      budget_kind: "token / cost_usd"
+    - mechanism: "agent-loop maxToolRounds / maxTotalTokens"
+      budget_kind: "iteration / token"
+
+principles:
+  - id: P-1
+    name: Bounds are Explicit
+    description: |
+      Resource budgets MUST be declared, not implicit in a developer's head or scattered
+      settings. An undeclared relied-upon bound is a violation, not an omission.
+
+  - id: P-2
+    name: Machine-Readable
+    description: |
+      The resource_budget: block is a first-class artifact a generator/runtime can read at
+      generation/execution time — so a unit knows its bounds up front, not after review.
+
+  - id: P-3
+    name: Fail-Closed
+    description: |
+      An undeclared relied-upon bound, or a runtime breach, MUST block/abort per declaration.
+      Never a silent unbounded pass — mirroring capability-declaration (XSPEC-037) fail-closed.
+
+  - id: P-4
+    name: No Re-Invention
+    description: |
+      Existing point mechanisms converge as reference implementations. New units inherit the
+      declaration habit rather than re-inventing a budget knob.
+
+  - id: P-5
+    name: Value Sovereignty
+    description: |
+      The declaration mechanism is standardized; the ceiling values are owned by the adopter
+      (a project/economics decision). The standard mandates that bounds are declared, not which.
+
+requirements:
+  - id: REQ-001
+    title: Resource Budget Taxonomy
+    description: |
+      Every LLM execution unit's resource bounds MUST be expressible from a standard set of
+      kinds: token, iteration, retry, cost_usd, wallclock, rate. A unit need not declare every
+      kind, but kinds it relies on for safety MUST be declared.
+    level: MUST
+    examples:
+      - "agent-loop declares iteration:60 + token(total):400000"
+      - "pipeline run declares cost_usd(per_run):3.00 + retry:3"
+
+  - id: REQ-002
+    title: Machine-Readable Declaration
+    description: |
+      A resource_budget: block MUST be declarable (embedded in plan / agent / role config),
+      each entry carrying kind + limit value + breach behaviour (warn / abort). It is a
+      first-class artifact, not a scattered setting or after-the-fact note.
+    level: MUST
+    schema_fields:
+      - "kind: token | iteration | retry | cost_usd | wallclock | rate"
+      - "scope (optional): per_call | per_run | per_session | total"
+      - "limit: numeric ceiling"
+      - "on_breach: warn | abort"
+
+  - id: REQ-003
+    title: Fail-Closed Enforcement Gate (check-resource-budget)
+    description: |
+      A quality gate check-resource-budget MUST (a) flag any LLM execution unit that does not
+      declare a budget (warn by default, block in strict mode); and (b) on a runtime breach
+      fail-closed per the declared on_breach (abort halts the unit, warn records and continues).
+      Mirrors capability-declaration (XSPEC-037) and the governance-gate family — never silent.
+    level: MUST
+    checks:
+      - "Unit with no resource_budget -> gate warns (strict mode: blocks)"
+      - "Runtime cost_usd exceeds declared limit with on_breach:abort -> unit aborts, breach recorded"
+      - "Runtime breach with on_breach:warn -> recorded and continues"
+
+  - id: REQ-004
+    title: Converge Existing Mechanisms (reference implementations)
+    description: |
+      Existing point mechanisms (orchestrator max_retries / max_retry_budget_usd, XSPEC-191
+      BudgetGuard, DEC-024 Pareto token gate, XSPEC-270 right-sizing router) SHOULD be mapped
+      to this standard as reference implementations — unified, not re-implemented.
+    level: SHOULD
+    checks:
+      - "Each existing budget mechanism maps to a taxonomy kind + on_breach behaviour"
+      - "A new agent/role adopts a resource_budget block rather than a bespoke budget knob"
+
+  - id: REQ-005
+    title: Budget Value Sovereignty
+    description: |
+      The declaration mechanism is standardized; the budget values (ceilings) are owned by the
+      adopter/customer (a project/economics decision). The standard mandates that bounds are
+      declared and enforced, not which numbers.
+    level: SHOULD
+    checks:
+      - "Ceiling values are adopter-configurable; the standard does not hard-code numbers"
+      - "The gate enforces presence + fail-closed behaviour, not a specific limit value"
+
+# ─────────────────────────────────────────────────────────────
+# GWT scenarios (admission condition 4 — AI-executable)
+# ─────────────────────────────────────────────────────────────
+
+scenarios:
+  - id: GWT-1
+    given: "a pipeline / agent unit with no token or cost_usd budget declared"
+    when: "check-resource-budget runs"
+    then: "it warns 'undeclared resource budget' (and blocks in strict mode)"
+  - id: GWT-2
+    given: "a unit declares cost_usd per_run limit 3.00 with on_breach: abort"
+    when: "the run's accumulated cost exceeds 3.00 at runtime"
+    then: "the unit fail-closed aborts and the breach is recorded for audit / cost governance"
+
+# ─────────────────────────────────────────────────────────────
+# Boundaries with adjacent standards (admission condition 3, <30% overlap)
+# ─────────────────────────────────────────────────────────────
+
+adjacent_boundaries:
+  - standard: performance-standards
+    its_angle: latency / throughput targets
+    distinct: targets, not a fail-closed cost ceiling
+  - standard: model-selection
+    its_angle: choose a model tier
+    distinct: tier selection, not budget enforcement
+  - standard: capability-declaration (XSPEC-037)
+    its_angle: explicit capability + fail-closed
+    distinct: capability surface, not resource budget
+
+# ─────────────────────────────────────────────────────────────
+# Gate timing
+# ─────────────────────────────────────────────────────────────
+
+gate_timing:
+  pre_run: REQ-003(a) check-resource-budget declaration check (undeclared -> warn / strict block)
+  on_runtime_breach: REQ-003(b) fail-closed per on_breach (abort / warn)
+  after_breach: record breach for audit / cost-governance executor (XSPEC-285)
+
+# ─────────────────────────────────────────────────────────────
+# Telemetry (DEC-066 / XSPEC-189 v2 envelope)
+# ─────────────────────────────────────────────────────────────
+
+telemetry:
+  required_events:
+    - resource_budget_undeclared   # unit missing a relied-upon budget (REQ-003a)
+    - resource_budget_breach       # runtime breach detail (kind, limit, actual)
+    - resource_budget_abort        # fail-closed abort on breach (on_breach:abort)
+  envelope_reference: XSPEC-189    # Telemetry Schema v2 envelope
+  event_type: quality
+  event_subtype_examples:
+    - resource_budget_breach
+    - gate_pass / gate_fail        # when check-resource-budget acts as a ship/run gate
+
+# ─────────────────────────────────────────────────────────────
+# Integration with existing standards
+# ─────────────────────────────────────────────────────────────
+
+integration:
+  performance-standards: performance sets latency/throughput targets; this sets fail-closed resource ceilings (adjacent, distinct)
+  model-selection: right-sizing picks a model tier; a cost_usd breach can drive a downgrade (XSPEC-270), but the budget declaration is this standard's concern
+  test-governance: check-resource-budget is a governed gate; budget declarations are governed policy
+  verification-evidence: a breach/no-breach run report is a kind of verification evidence (budgets honoured + trace)
+
+# ─────────────────────────────────────────────────────────────
+# Adoption guidance
+# ─────────────────────────────────────────────────────────────
+
+adoption_guidance:
+  uds_install_path: ai/standards/resource-cost-boundary.ai.yaml
+  notes:
+    - "v1.0.0 defines the budget declaration mechanism and a fail-closed gate. Budget values are adopter-owned."
+    - "This standard is the 'declare what bounds' half; XSPEC-285 (VibeOps proactive cost governance) is the 'enforce/govern' half."
+    - "Map existing budget knobs (max_retries, BudgetGuard, Pareto token gate, right-sizing router) to taxonomy kinds rather than re-inventing."
+    - "Collect only the cost/resource dimension — do not expand into a vague 'resource governance' (XSPEC-276 over-design guardrail)."

package/bundled/ai/standards/reverse-engineering-standards.ai.yaml

@@ -3,8 +3,8 @@
 
 id: reverse-engineering
 meta:
-  version: "1.0.0"
-  updated: "2026-01-19"
+  version: "1.2.0"
+  updated: "2026-06-27"
   source: core/reverse-engineering-standards.md
   description: Standards for reverse engineering code into structured specifications
 
@@ -32,6 +32,28 @@ workflow:
         - Identify boundary conditions
         - Note coverage gaps
 
+    - stage: IMPLICIT_RULE_SCAN
+      description: Scan non-HTTP persistence write paths for undocumented business rules
+      output: Implicit-rule inventory locked as behavior-snapshot scenarios or reconciliation invariants
+      certainty: "[Confirmed]/[Inferred]/[Unknown]"
+      position: after CODE_SCAN/TEST_ANALYSIS, before GAP_IDENTIFICATION
+      derive:
+        - "Scheduled: crontab / scheduler config / @Scheduled-style annotations / batch jobs"
+        - "Queue: queue consumers / job handlers / background workers / message listeners"
+        - "DB-layer: triggers / computed-generated columns / DEFAULT expressions / check constraints"
+        - "ORM lifecycle: beforeSave/afterSave/observer/model-event hooks / state-mutating middleware"
+      oracle_three_questions:
+        - "When is the field SET? (first-assign condition/trigger)"
+        - "When is it OVERWRITTEN? (every later write, INCLUDING async overwrites)"
+        - "When is it RESET / zeroed? (clear/default-back conditions)"
+      actions:
+        - Derive every non-HTTP persistence write path across the four categories
+        - Answer the three questions per persisted field and lock answers as snapshot scenarios or reconciliation invariants
+        - Extend Devil's Advocate (5 categories) from HTTP layer to non-HTTP paths
+        - Tag each rule [Confirmed] (with file:line) / [Inferred] / [Unknown]; route [Unknown] to GAP_IDENTIFICATION
+        - "PHP-specific: flag loose-comparison / type-juggling (==, truthy/falsy of \"0\"/\"\"/null/0, string-to-number coercion) — no equivalent under strongly-typed targets"
+      gate: pre-flight; unanswered three-question field marked not_implemented and blocks cutover
+
     - stage: GAP_IDENTIFICATION
       description: List unknowns requiring human input
       output: Gap analysis document
@@ -139,6 +161,19 @@ extraction_capability:
       reason: Often implicit
       required_action: Discuss with architects
 
+# Failure handling (failure -> escalate -> re-verify)
+failure_handling:
+  description: Inputs that cannot be analyzed safely must escalate, never ship as authoritative
+  matrix:
+    - condition: Parse failure (unsupported language / broken syntax tree)
+      action: Mark [Unknown], report language/file, escalate to a human domain expert, emit no inferred behavior
+    - condition: High unknown ratio (> 50% of behaviors [Unknown])
+      action: Halt spec finalization, require SME interview to fill [Unknown] first; never ship a majority-guessed spec
+    - condition: Contradicted inference (code contradicts an inferred behavior)
+      action: Downgrade to [Assumption], escalate to code owner; never record as [Confirmed]
+    - condition: Test-analysis failure (tests cannot be run/parsed)
+      action: Fall back to static analysis; mark behaviors [Inferred], never [Confirmed]
+
 # Anti-Patterns
 anti_patterns:
   code_analysis:
@@ -202,6 +237,10 @@ integration:
 
 # Rules for AI
 rules:
+  - id: re-fail-escalate-low-confidence
+    trigger: parse failure or above-threshold [Unknown] ratio
+    instruction: Block spec finalization and escalate to a human; never present a sub-threshold-confidence spec as authoritative
+    priority: required
   - id: read-before-claim
     trigger: starting reverse engineering
     instruction: Read ALL relevant files before making any claims about code behavior
@@ -232,6 +271,19 @@ rules:
     instruction: Map test cases to acceptance criteria with [Confirmed] tag and line references
     priority: required
 
+  - id: implicit-rule-scan-non-http
+    trigger: reverse engineering a system for refactor/migration where persisted fields may be written off the HTTP path
+    instruction: >
+      Run an IMPLICIT_RULE_SCAN after CODE_SCAN/TEST_ANALYSIS and before GAP_IDENTIFICATION. Mechanically derive
+      every non-HTTP persistence write path across four categories (scheduled, queue, DB-layer trigger/computed-column/
+      DEFAULT/check, ORM lifecycle hooks/middleware). For each persisted field answer three questions — when SET, when
+      OVERWRITTEN (including async overwrites), when RESET/zeroed — and lock each answer as a behavior-snapshot scenario
+      or reconciliation invariant. Extend Devil's Advocate to non-HTTP paths. Tag every rule [Confirmed] (with file:line)
+      / [Inferred] / [Unknown]; route [Unknown] to gap analysis. For PHP sources, additionally flag loose-comparison /
+      type-juggling dependencies that have no strongly-typed equivalent. Any field whose three questions are unanswered
+      is marked not_implemented and blocks cutover.
+    priority: required
+
   - id: human-review-required
     trigger: completing spec generation
     instruction: Always mark specification as requiring human review; [Unknown] sections MUST be filled by humans
@@ -267,6 +319,7 @@ quick_reference:
     rows:
       - [Code Scan, Technical inventory, "[Confirmed]"]
       - [Test Analysis, Draft AC, "[Confirmed]/[Inferred]"]
+      - [Implicit Rule Scan, Non-HTTP implicit-rule inventory, "[Confirmed]/[Inferred]/[Unknown]"]
       - [Gap ID, Gap analysis, "[Unknown] items"]
       - [Spec Gen, Draft SPEC, Mixed]
       - [Human Review, Validated spec, "[Confirmed]"]