Hack23 · pethers · Apr 23, 2026 · Apr 23, 2026 · Apr 23, 2026 · Apr 23, 2026
@@ -4,9 +4,37 @@ Analysis is the **primary product**. Articles are derived from analysis. Never w
 
 Authoritative methodology & templates:
 
+- **Read-me-first** → [`analysis/methodologies/artifact-catalog.md`](../../analysis/methodologies/artifact-catalog.md) (single source of truth for every artifact — family, template, depth floor, Mermaid type, MCP data source, gate check) and [`analysis/methodologies/per-artifact-methodologies.md`](../../analysis/methodologies/per-artifact-methodologies.md) (Inputs / Analytic-moves / Evidence-rules / Anti-patterns per artifact). Open these before any framework-specific methodology.
 - Methodology → [`analysis/methodologies/ai-driven-analysis-guide.md`](../../analysis/methodologies/ai-driven-analysis-guide.md) (DIW weighting, tier depths, Pass 1/Pass 2 rules, F3EAD mapping)
+- Indicator maps → [`worldbank-indicator-mapping.md`](../../analysis/methodologies/worldbank-indicator-mapping.md) (non-economic: social, health, education, environment, defence, agriculture, innovation, governance) + [`imf-indicator-mapping.md`](../../analysis/methodologies/imf-indicator-mapping.md) (**authoritative** for all economic / fiscal / trade / monetary context with vintage-tagged WEO forecasts)
+- Depth floors → [`reference-quality-thresholds.json`](../../analysis/methodologies/reference-quality-thresholds.json) (per-article-type × per-artifact line floors + tradecraft signals consumed by Pass-2 self-audit)
 - Supporting frameworks → [`political-classification-guide.md`](../../analysis/methodologies/political-classification-guide.md), [`political-swot-framework.md`](../../analysis/methodologies/political-swot-framework.md), [`political-risk-methodology.md`](../../analysis/methodologies/political-risk-methodology.md), [`political-threat-framework.md`](../../analysis/methodologies/political-threat-framework.md), [`synthesis-methodology.md`](../../analysis/methodologies/synthesis-methodology.md), [`strategic-extensions-methodology.md`](../../analysis/methodologies/strategic-extensions-methodology.md), [`electoral-domain-methodology.md`](../../analysis/methodologies/electoral-domain-methodology.md), [`structural-metadata-methodology.md`](../../analysis/methodologies/structural-metadata-methodology.md), [`per-document-methodology.md`](../../analysis/methodologies/per-document-methodology.md), [`political-style-guide.md`](../../analysis/methodologies/political-style-guide.md), [`osint-tradecraft-standards.md`](../../analysis/methodologies/osint-tradecraft-standards.md) — **tradecraft canon: ICD 203 + Admiralty + WEP + SAT catalog + OSINT ethics + DIW alignment + PIR handoff**
-- Templates → [`analysis/templates/*.md`](../../analysis/templates/) (one file per artifact — 23 always-on + per-document)
+- Templates → [`analysis/templates/*.md`](../../analysis/templates/) (one file per artifact — 23 always-on + per-document + 7 operational supplementary)
+
+**Operational supplementary artifacts** — 7 enrichment templates that strengthen the AI-FIRST quality loop, cross-run memory, and MCP health auditability. **Recommended** for every `deep` run; **mandatory** for every `comprehensive` / Tier-C aggregation run; enforced by [`05-analysis-gate.md §Supplementary checks`](05-analysis-gate.md):
+
+| Template | When to produce | Feeds |
+|----------|-----------------|-------|
+| [`analysis-index.md`](../../analysis/templates/analysis-index.md) | always for `deep`/`comprehensive` | downstream reviewers |
+| [`reference-analysis-quality.md`](../../analysis/templates/reference-analysis-quality.md) | `comprehensive`; operationalises AI-FIRST | Pass-2 self-audit |
+| [`mcp-reliability-audit.md`](../../analysis/templates/mcp-reliability-audit.md) | `comprehensive` or any MCP degradation | incident follow-up |
+| [`workflow-audit.md`](../../analysis/templates/workflow-audit.md) | `comprehensive` | 11-principle compliance |
+| [`cross-run-diff.md`](../../analysis/templates/cross-run-diff.md) | any article type with ≥ 2 runs | Bayesian update |
+| [`cross-session-intelligence.md`](../../analysis/templates/cross-session-intelligence.md) | `weekly-review`, `monthly-review`, quarterly | session narrative |
+| [`session-baseline.md`](../../analysis/templates/session-baseline.md) | any aggregation workflow | calendar + roster fact layer |
+
+These are **not counted in the 23 mandatory artifacts** — the 23-artifact contract is unchanged.
+
+**Analytical supplementary artifacts** — 4 optional deep-dive templates mapped to frameworks explicitly listed in the intelligence-operative agent's "Core Expertise" that previously had no template. **Never blocking** in `05-analysis-gate.md` and **never replace** a core artifact. Produce when the trigger condition applies; otherwise skip. See [`analytical-supplementary-methodology.md`](../../analysis/methodologies/analytical-supplementary-methodology.md) for composition rules and per-template analytic moves.
+
+| Template | Produce when | Pairs with |
+|----------|--------------|-----------|
+| [`pestle-analysis.md`](../../analysis/templates/pestle-analysis.md) | event crosses ≥ 2 PESTLE dimensions | `swot-analysis.md`, `risk-assessment.md`, `scenario-analysis.md` |
+| [`political-stride-assessment.md`](../../analysis/templates/political-stride-assessment.md) | election-adjacent / integrity incident / disinfo / critical-infra vote | `threat-analysis.md`, `risk-assessment.md` Institutional/Corruption |
+| [`wildcards-blackswans.md`](../../analysis/templates/wildcards-blackswans.md) | long-horizon forecasting (`monthly-review`, election year) | `scenario-analysis.md`, `forward-indicators.md` |
+| [`quantitative-swot.md`](../../analysis/templates/quantitative-swot.md) | decision memo needing scored ranking | `swot-analysis.md`, `significance-scoring.md`, `executive-brief.md` |
+
+These are **not counted in the 23 mandatory artifacts** and **not counted in the 7 operational supplementary** — the contract is unchanged. Agents ignoring them still produce valid output.
 
 ## Role boundary
 

@@ -6,6 +6,7 @@ This is the **only** gate separating analysis from article generation. If it fai
 
 - `$ANALYSIS_DIR = analysis/daily/$ARTICLE_DATE/$SUBFOLDER`
 - 23 required artifacts (Families A + B + C + D from `04-analysis-pipeline.md`) + per-document Family E.
+- Authoritative reference — [`analysis/methodologies/artifact-catalog.md`](../../analysis/methodologies/artifact-catalog.md) (single source of truth for every artifact), [`analysis/methodologies/per-artifact-methodologies.md`](../../analysis/methodologies/per-artifact-methodologies.md) (per-artifact Inputs / Analytic-moves / Evidence-rules / Anti-patterns), [`analysis/methodologies/reference-quality-thresholds.json`](../../analysis/methodologies/reference-quality-thresholds.json) (per-article-type line floors + tradecraft signals).
 
 ## Checks (all must pass)
 
@@ -232,3 +233,46 @@ Exit code 0 = pass, non-zero = fail with per-check report. Precondition for chec
 ## Deduplication note
 
 If today's article HTML already exists under `news/` **and** `force_generation=false`, skip article generation but still run analysis and still commit. The PR label is `analysis-only`. There is still exactly one PR call.
+
+## Supplementary checks
+
+Non-blocking for `standard` / `deep` runs; **blocking for `comprehensive` / Tier-C aggregation runs**. These checks consume the 7 operational supplementary artifacts defined in [`analysis/templates/README.md §Operational Supplementary`](../../analysis/templates/README.md) and catalogued in [`analysis/methodologies/artifact-catalog.md §Operational Supplementary`](../../analysis/methodologies/artifact-catalog.md#-operational-supplementary-artifacts-7).
+
+| S# | File | Blocking when | Methodology §link |
+|:--:|------|---------------|-------------------|
+| S1 | `analysis-index.md` | `comprehensive` | [`per-artifact-methodologies.md#analysis-index`](../../analysis/methodologies/per-artifact-methodologies.md#analysis-index) |
+| S2 | `reference-analysis-quality.md` | `comprehensive` | [`per-artifact-methodologies.md#reference-analysis-quality`](../../analysis/methodologies/per-artifact-methodologies.md#reference-analysis-quality) |
+| S3 | `mcp-reliability-audit.md` | `comprehensive`, or any run with ≥ 1 MCP endpoint failure | [`per-artifact-methodologies.md#mcp-reliability-audit`](../../analysis/methodologies/per-artifact-methodologies.md#mcp-reliability-audit) |
+| S4 | `workflow-audit.md` | `comprehensive` | [`per-artifact-methodologies.md#workflow-audit`](../../analysis/methodologies/per-artifact-methodologies.md#workflow-audit) |
+| S5 | `cross-run-diff.md` | any article type with ≥ 2 production runs | [`per-artifact-methodologies.md#cross-run-diff`](../../analysis/methodologies/per-artifact-methodologies.md#cross-run-diff) |
+| S6 | `cross-session-intelligence.md` | `weekly-review`, `monthly-review`, quarterly aggregation | [`per-artifact-methodologies.md#cross-session-intelligence`](../../analysis/methodologies/per-artifact-methodologies.md#cross-session-intelligence) |
+| S7 | `session-baseline.md` | `weekly-review`, `monthly-review`, any aggregation workflow | [`per-artifact-methodologies.md#session-baseline`](../../analysis/methodologies/per-artifact-methodologies.md#session-baseline) |
+
+Inline bash probe — append to the main block after `FAIL=0` bookkeeping completes. The gate blocks on **aggregation article types** (`weekly-review`, `monthly-review`), on any run whose **tier** is `comprehensive` (the Tier-C run mode), and on `cross-run-diff.md` when the workflow has **≥ 2 production runs** of the same article type. `ARTICLE_TYPE` encodes the workflow family; `ANALYSIS_TIER` (when set) encodes the depth tier (`standard` | `deep` | `comprehensive`); `ANALYSIS_RUN_COUNT` (when set) is the numeric count of runs for the same article-generation cycle (if unset or non-numeric, treated as `1`).
-Inline bash probe — append to the main block after `FAIL=0` bookkeeping completes. The gate blocks on **aggregation article types** (`weekly-review`, `monthly-review`), on any run whose **tier** is `comprehensive` (the Tier-C run mode), and on `cross-run-diff.md` when the workflow has **≥ 2 production runs** of the same article type. `ARTICLE_TYPE` encodes the workflow family; `ANALYSIS_TIER` (when set) encodes the depth tier (`standard` | `deep` | `comprehensive`); `ANALYSIS_RUN_COUNT` (when set) is the numeric count of runs for the same article-generation cycle (if unset or non-numeric, treated as `1`).
+Inline bash probe — append to the main block after `FAIL=0` bookkeeping completes. Supplementary artifacts have **three independent blocking triggers**, not a single tier-only rule: **aggregation article types** (`weekly-review`, `monthly-review`) require the aggregation artifacts; any run whose **tier** is `comprehensive` (the Tier-C run mode) requires the Tier-C supplementary set; and `cross-run-diff.md` is blocking whenever the workflow has **≥ 2 production runs** of the same article type, including `standard` and `deep` runs. `ARTICLE_TYPE` encodes the workflow family; `ANALYSIS_TIER` (when set) encodes the depth tier (`standard` | `deep` | `comprehensive`); `ANALYSIS_RUN_COUNT` (when set) is the numeric count of runs for the same article-generation cycle (if unset or non-numeric, treated as `1`).
-Inline bash probe — append to the main block after `FAIL=0` bookkeeping completes. The gate blocks on **aggregation article types** (`weekly-review`, `monthly-review`), on any run whose **tier** is `comprehensive` (the Tier-C run mode), and on `cross-run-diff.md` when the workflow has **≥ 2 production runs** of the same article type. `ARTICLE_TYPE` encodes the workflow family; `ANALYSIS_TIER` (when set) encodes the depth tier (`standard` | `deep` | `comprehensive`); `ANALYSIS_RUN_COUNT` (when set) is the numeric count of runs for the same article-generation cycle (if unset or non-numeric, treated as `1`).
+Inline bash probe — append to the main block after `FAIL=0` bookkeeping completes. Supplementary artifacts have **three independent blocking triggers**, not a single tier-only rule: **aggregation article types** (`weekly-review`, `monthly-review`) require the aggregation artifacts; any run whose **tier** is `comprehensive` (the Tier-C run mode) requires the Tier-C supplementary set; and `cross-run-diff.md` is blocking whenever the workflow has **≥ 2 production runs** of the same article type, including `standard` and `deep` runs. `ARTICLE_TYPE` encodes the workflow family; `ANALYSIS_TIER` (when set) encodes the depth tier (`standard` | `deep` | `comprehensive`); `ANALYSIS_RUN_COUNT` (when set) is the numeric count of runs for the same article-generation cycle (if unset or non-numeric, treated as `1`).
+
+```bash
+# Check 9 — supplementary artifacts (blocking for aggregation types, any Tier-C run, and S5 when run-count >= 2)
+IS_AGGREGATION=0
+IS_TIER_C=0
+IS_MULTI_RUN=0
+RUN_COUNT=1
+[[ "${ARTICLE_TYPE:-}" =~ ^(weekly-review|monthly-review)$ ]] && IS_AGGREGATION=1
+[[ "${ANALYSIS_TIER:-standard}" == "comprehensive" ]] && IS_TIER_C=1
+[[ "${ANALYSIS_RUN_COUNT:-}" =~ ^[0-9]+$ ]] && RUN_COUNT="${ANALYSIS_RUN_COUNT}"
+(( RUN_COUNT >= 2 )) && IS_MULTI_RUN=1
+if (( IS_AGGREGATION == 1 || IS_TIER_C == 1 || IS_MULTI_RUN == 1 )); then
+  SUPP=()
+  if (( IS_AGGREGATION == 1 || IS_TIER_C == 1 )); then
+    SUPP+=(analysis-index.md reference-analysis-quality.md mcp-reliability-audit.md workflow-audit.md)
+  fi
+  (( IS_AGGREGATION == 1 )) && SUPP+=(cross-session-intelligence.md session-baseline.md)
+  (( IS_MULTI_RUN == 1 )) && SUPP+=(cross-run-diff.md)
+  for f in "${SUPP[@]}"; do
+    [ -s "$ANALYSIS_DIR/$f" ] || { echo "❌ supplementary missing (agg=$IS_AGGREGATION tier-c=$IS_TIER_C multi-run=$IS_MULTI_RUN): $f"; FAIL=1; }
+  done
+fi
+```
+
+Depth floors for S1–S7 are configured under `thresholds.breaking.*` / per-type sections in [`reference-quality-thresholds.json`](../../analysis/methodologies/reference-quality-thresholds.json); when a floor is absent the `defaults.supplementaryFloor` (120 lines) applies.
+
+**Pass-2 quality audit — recommendation, not enforced in the bash probe** — the bash check above does **not** parse `reference-analysis-quality.md §5`. When the artifact is produced, agents SHOULD re-read its `§5 Overall Benchmark Judgement` total and trigger another Pass-2 iteration if the score is below **7.0/10** before invoking this gate. This is a non-enforced self-discipline rule (no blocking logic); an enforced numeric-floor check would require adding a YAML/JSON score block to the template and a dedicated parser, which is deferred to a follow-up change.
@@ -21,9 +21,14 @@ This directory is the **single source of truth** for how GitHub Agentic Workflow
   - Source repo: <https://github.com/github/gh-aw>
   - GitHub CLI: <https://cli.github.com/manual/>
 - **Analysis artifact contract** (the "deep political analysis" product that every news workflow must produce *before* writing a single article sentence):
+  - **Read-me-first** — [`analysis/methodologies/artifact-catalog.md`](../../analysis/methodologies/artifact-catalog.md) (single source of truth for every artifact — family, template, depth floor, Mermaid, MCP, gate check) and [`analysis/methodologies/per-artifact-methodologies.md`](../../analysis/methodologies/per-artifact-methodologies.md) (Inputs / Analytic-moves / Evidence-rules / Anti-patterns per artifact)
   - Methodology → [`analysis/methodologies/ai-driven-analysis-guide.md`](../../analysis/methodologies/ai-driven-analysis-guide.md)
-  - Templates → [`analysis/templates/`](../../analysis/templates/) (one file per artifact)
+  - Indicator maps → [`worldbank-indicator-mapping.md`](../../analysis/methodologies/worldbank-indicator-mapping.md) (non-economic WB) + [`imf-indicator-mapping.md`](../../analysis/methodologies/imf-indicator-mapping.md) (authoritative IMF for all economic context)
+  - Depth floors → [`reference-quality-thresholds.json`](../../analysis/methodologies/reference-quality-thresholds.json) (per-article-type × per-artifact line floors, tradecraft signals)
+  - Templates → [`analysis/templates/`](../../analysis/templates/) (one file per artifact — 23 always-on + per-document + 7 operational supplementary)
   - **23 required artifacts** (every workflow, produced in `analysis/daily/$ARTICLE_DATE/$SUBFOLDER/`): Family A Core Synthesis — `README.md`, `executive-brief.md`, `synthesis-summary.md`, `significance-scoring.md`, `classification-results.md`, `swot-analysis.md`, `risk-assessment.md`, `threat-analysis.md`, `stakeholder-perspectives.md`; Family B Structural Metadata — `data-download-manifest.md`, `cross-reference-map.md`; Family C Strategic Extensions (F3EAD Exploit→Analyze) — `scenario-analysis.md`, `comparative-international.md`, `devils-advocate.md`, `intelligence-assessment.md`, `methodology-reflection.md` ⭐; Family D Electoral & Domain Lenses — `election-2026-analysis.md`, `voter-segmentation.md`, `coalition-mathematics.md`, `historical-parallels.md`, `media-framing-analysis.md`, `implementation-feasibility.md`, `forward-indicators.md`. Plus Family E per-document `documents/{dok_id}-analysis.md`. Full definitions in [`04-analysis-pipeline.md`](04-analysis-pipeline.md).
+  - **7 operational supplementary artifacts** (not counted in the 23; recommended for `deep`, mandatory for `comprehensive` / Tier-C): `analysis-index.md`, `reference-analysis-quality.md`, `mcp-reliability-audit.md`, `workflow-audit.md`, `cross-run-diff.md`, `cross-session-intelligence.md`, `session-baseline.md`.
+  - **4 analytical supplementary artifacts** (never blocking, optional deep-dives): `pestle-analysis.md`, `political-stride-assessment.md`, `wildcards-blackswans.md`, `quantitative-swot.md`. Full rules in [`analytical-supplementary-methodology.md`](../../analysis/methodologies/analytical-supplementary-methodology.md).
   - **Tier-C aggregation** produces the same 23 artifacts plus depth multipliers, cross-type sibling-folder citations, prior-cycle PIR ingestion, and a 1 500-word article floor — see [`ext/tier-c-aggregation.md`](ext/tier-c-aggregation.md).
 - **Single blocking gate**: [`05-analysis-gate.md`](05-analysis-gate.md) is the only enforcer. No article may be touched until the gate passes.
 - **AI-FIRST rule** (from [`00-base-contract.md`](00-base-contract.md) §Non-negotiable rules #5): minimum 2 complete iterations — Pass 1 creates every artifact, Pass 2 reads Pass 1 back in full and improves every section.

@@ -11,13 +11,13 @@
 
 <p align="center">
   <a href="#"><img src="https://img.shields.io/badge/Owner-CEO-0A66C2?style=for-the-badge" alt="Owner"/></a>
-  <a href="#"><img src="https://img.shields.io/badge/Version-4.2-555?style=for-the-badge" alt="Version"/></a>
+  <a href="#"><img src="https://img.shields.io/badge/Version-4.3-555?style=for-the-badge" alt="Version"/></a>
   <a href="#"><img src="https://img.shields.io/badge/Effective-2026--06--01-success?style=for-the-badge" alt="Effective Date"/></a>
   <a href="#"><img src="https://img.shields.io/badge/Classification-Public-green?style=for-the-badge" alt="Classification"/></a>
 </p>
 
-**📋 Document Owner:** CEO | **📄 Version:** 4.2 | **📅 Last Updated:** 2026-06-01 (UTC)  
-**🔄 Review Cycle:** Quarterly | **⏰ Next Review:** 2026-06-30  
+**📋 Document Owner:** CEO | **📄 Version:** 4.3 | **📅 Last Updated:** 2026-04-23 (UTC)  
+**🔄 Review Cycle:** Quarterly | **⏰ Next Review:** 2026-07-23  
 **🏢 Owner:** Hack23 AB (Org.nr 5595347807) | **🏷️ Classification:** Public
 
 ---
@@ -321,6 +321,35 @@ graph TB
 
 ## 📖 Methodology Catalog
 
+### 🗂️ Reference & Meta Methodologies (v4.3 — Added 2026-04-23)
+
+| Document | Purpose | Consumers |
+|----------|---------|-----------|
+| [`artifact-catalog.md`](artifact-catalog.md) | **Single source of truth** for every markdown artifact produced by a news workflow (23 core + 7 supplementary + N per-document). One row per artifact naming methodology, template, line floor, Mermaid type, MCP data source and gate check. | All agents, `.github/prompts/04-analysis-pipeline.md`, `05-analysis-gate.md` |
+| [`per-artifact-methodologies.md`](per-artifact-methodologies.md) | Per-artifact **Inputs / Analytic-moves / Evidence-rules / Anti-patterns** reference. One §section per artifact — read only the sections needed for the current run. | All agents writing artifacts |
+| [`worldbank-indicator-mapping.md`](worldbank-indicator-mapping.md) | Article-type → non-economic World Bank indicator codes (social, health, education, environment, defence, agriculture, innovation, governance). Wave-2 WB↔IMF split. | `comparative-international.md`, `voter-segmentation.md`, `implementation-feasibility.md`, `session-baseline.md` |
+| [`imf-indicator-mapping.md`](imf-indicator-mapping.md) | Article-type → IMF WEO/IFS/BOP/FM/GFS codes — **authoritative source** for all economic context (macro / fiscal / trade / monetary / exchange rates). Vintage-tagged forecasts, T+5. | Every artifact with economic-context obligations |
+| [`reference-quality-thresholds.json`](reference-quality-thresholds.json) | Per-article-type × per-artifact **minimum line-count floors** enforced by [`05-analysis-gate.md`](../../.github/prompts/05-analysis-gate.md) Check 3. Additive tradecraft signals (WEP / Admiralty / ICD 203 / SATs / DIW / neutrality) consumed by Pass-2 self-audit. | Gate, `reference-analysis-quality.md`, Pass-2 validators |
+
+These five files are the **meta-layer** — read them before opening any framework-specific methodology. They define *what* is produced, *how* it is measured, and *where* the data comes from.
+
+### 🔭 Analytical Supplementary Methodology (v1.1 — Added 2026-04-23)
+
+| Document | Purpose | Templates governed |
+|----------|---------|--------------------|
+| [`analytical-supplementary-methodology.md`](analytical-supplementary-methodology.md) | Rules for **optional deep-dive analytical templates** that augment the 23 core artifacts with specialised lenses. Non-blocking in `05-analysis-gate.md`. Defines composition rules (DIW weight vector, evidence citations, Forward-Indicator feed, TTP mapping) and per-template analytic moves. | `pestle-analysis.md` · `political-stride-assessment.md` · `wildcards-blackswans.md` · `quantitative-swot.md` |
+
+**When to produce:**
+
+- **PESTLE** — event crosses ≥ 2 macro dimensions (policy with economic spill-over, tech regulation with EU exposure, etc.)
+- **STRIDE-political** — election-adjacent events, integrity incidents, disinformation spikes, critical-infrastructure votes
+- **Wildcards & Black-Swans** — long-horizon forecasting (`monthly-review`, election-year aggregation)
+- **Quantitative SWOT** — decision-oriented memos requiring scored ranking (coalition negotiations, party strategy)
+
+These templates **never replace** a core artifact — they always pair with and cite the canonical artifact they extend.
+
+---
+
 ### 🤖 AI-Driven Analysis Guide — `ai-driven-analysis-guide.md`
 
 | Attribute | Value |