docs: refresh Abaqus subroutine guidance

.codex/agents/formulation-agent.toml

@@ -13,7 +13,7 @@ Mission:
 
 Skill references:
 - Use $abaqus-subroutine-formulation when drafting or revising finite element formulation specs, stress update algorithms, consistent tangent terms, state variables, weak forms, element equations, numerical integration, or output recovery contracts.
-- Use $fem-theory-query when formulation needs wiki-grounded FEM theory, constitutive integration, tangent, or benchmark context.
+- Must use $fem-theory-query when formulation needs FEM theory, constitutive integration, tangent, or benchmark context.
 
 Hard boundaries:
 - Do not implement code.

.codex/agents/implementation-planning-agent.toml

@@ -15,7 +15,7 @@ Skill references:
 - Use $abaqus-subroutine-formulation when checking formulation inputs, output recovery contracts, stress update, consistent tangent, or state variable handoff items.
 - Use $abaqus-subroutine-test-models when checking no-Abaqus test order, tests/fortran/manifest.json, artifact contracts, source hash needs, or reference model coverage.
 - Use $abaqus-fortran-tdd when creating TDD-first Fortran implementation plans, test order, validation commands, or correction handoffs.
-- Use $fem-theory-query when planning needs wiki-grounded formulation, verification design, benchmark, or numerical-risk context.
+- Must use $fem-theory-query when planning needs formulation theory, verification design, benchmark, or numerical-risk context.
 
 Hard boundaries:
 - Do not implement code.

.codex/agents/io-definition-agent.toml

@@ -13,7 +13,8 @@ Mission:
 
 Skill references:
 - Use $abaqus-subroutine-interface when defining Abaqus ABI parameters, input/output arrays, validation rules, result CSV schemas, units, coordinate systems, component naming, or ID matching contracts.
-- Use $fem-theory-query when interface contracts need wiki-grounded Abaqus manual evidence or FEM output semantics.
+- Must use $fem-theory-query when interface contracts need FEM output semantics, tensor conventions, or numerical context.
+- For Abaqus ABI and argument facts, read docs/AbaqusUserSubroutineManual/INDEX_MAP.md first, locate the complete INDEX.md record, and read every listed source_ranges span in order.
 
 Hard boundaries:
 - Do not implement wrappers.
@@ -24,6 +25,7 @@ Hard boundaries:
 - Do not approve readiness.
 
 Interface rules:
+- Treat INDEX.md summaries and keywords as retrieval metadata; cite the authoritative manual source spans used for interface decisions.
 - For UMAT, explicitly define STRESS, STRAN, DSTRAN, TIME, DTIME, TEMP, PREDEF, PROPS, NPROPS, COORDS, DROT, DDSDDE, STATEV, PNEWDT, NOEL, NPT, KSTEP, and KINC usage when applicable.
 - For VUMAT or UEL, define the equivalent argument direction, block layout, and update responsibility.
 - Define units, coordinate system, tensor component order, output location, and CSV extraction rules.

.codex/agents/numerical-review-agent.toml

@@ -13,7 +13,7 @@ Mission:
 
 Skill references:
 - Use $abaqus-subroutine-numerical-review when reviewing formulation correctness, algorithmic consistency, tangent consistency, patch tests, locking, Jacobian handling, state variable updates, or implementation readiness.
-- Use $fem-theory-query when review findings need wiki-grounded FEM theory or benchmark evidence.
+- Must use $fem-theory-query when review findings need FEM theory or benchmark evidence.
 
 Hard boundaries:
 - Do not implement code.

.codex/agents/physics-evaluation-agent.toml

@@ -13,7 +13,7 @@ Mission:
 
 Skill references:
 - Use $abaqus-subroutine-physics-sanity when evaluating physical plausibility, global equilibrium, reaction consistency, displacement direction, symmetry, stress/strain, state variable behavior, energy/residual evidence, or model coverage.
-- Use $fem-theory-query when physical findings need wiki-grounded FEM theory or benchmark context.
+- Must use $fem-theory-query when physical findings need FEM theory or benchmark context.
 
 Hard boundaries:
 - Do not edit source code.

.codex/agents/reference-model-agent.toml

@@ -13,7 +13,7 @@ Mission:
 
 Skill references:
 - Use $abaqus-subroutine-test-models when designing no-Abaqus driver cases, Abaqus `.inp` reference bundles, metadata provenance, source hash contracts, msg/dat/log tail requirements, extracted CSV artifacts, or coverage matrices.
-- Use $fem-theory-query when model design needs FEM theory, benchmark, patch test, or verification context.
+- Must use $fem-theory-query when model design needs FEM theory, benchmark, patch test, or verification context.
 
 Hard boundaries:
 - Do not implement code.

.codex/agents/research-agent.toml

@@ -13,7 +13,7 @@ Mission:
 
 Skill references:
 - Use $abaqus-subroutine-research when collecting research evidence, FEM theory sources, official Abaqus documentation, benchmark candidates, source reliability tiers, applicability limits, or downstream handoff evidence.
-- Use $fem-theory-query when a question needs wiki-grounded FEM theory, constitutive integration, element formulation, tangent, benchmark, or verification context.
+- Must use $fem-theory-query when a question needs FEM theory, constitutive integration, element formulation, tangent, benchmark, or numerical verification context.
 
 Hard boundaries:
 - Do not implement code.
@@ -24,7 +24,9 @@ Hard boundaries:
 - Do not approve readiness.
 
 Source policy:
-- Prefer official Abaqus documentation, Abaqus User Subroutines Reference Guide, Abaqus Analysis User's Guide, textbooks, peer-reviewed papers, NAFEMS/NASA benchmarks, and project-provided sources.
+- For Abaqus User Subroutine manual facts, read docs/AbaqusUserSubroutineManual/INDEX_MAP.md first, locate the complete record in INDEX.md, and read every listed source_ranges span in order.
+- Treat INDEX.md summaries and keywords as retrieval metadata, not authoritative facts.
+- Prefer local authoritative Abaqus manual spans, textbooks, peer-reviewed papers, NAFEMS/NASA benchmarks, and project-provided sources according to the question type.
 - Record source reliability, assumptions, version relevance, and applicability limits.
 - Label inference explicitly.