diff --git a/canon/standards/repo-classification.exclusions.yaml b/canon/standards/repo-classification.exclusions.yaml
new file mode 100644
index 0000000..20d3673
--- /dev/null
+++ b/canon/standards/repo-classification.exclusions.yaml
@@ -0,0 +1,73 @@
+# Repo Classification exclusion list (CUST-WP-0050 T11 / D3).
+# Repos listed here are intentionally out of scope for classification and
+# State Hub registration under the portfolio taxonomy.
+#
+# Validate additions against canon/standards/repo-classification-standard_v1.0.md.
+
+version: "1.0"
+updated: "2026-06-22"
+
+exclusions:
+  # Forks and personal repos — not ecosystem inventory.
+  - slug: tegwick/the-custodian
+    gitea_path: tegwick/the-custodian
+    reason: fork of the-custodian; not a managed ecosystem repo
+
+  - slug: python-snake
+    gitea_path: lando_worsch/python-snake
+    reason: personal / non-ecosystem repo
+
+  # Archived or collapsed hub registrations — superseded by another slug.
+  - slug: markitect-project
+    reason: archived; workstreams relinked to markitect-main (ADR-005 disposition)
+
+  - slug: railiance-bootstrap
+    reason: archived phantom registration; no Gitea repo
+
+  - slug: railiance-hosts
+    reason: archived phantom registration; no Gitea repo
+
+  - slug: vergabe_teilnahme
+    reason: archived duplicate; collapsed into vergabe-teilnahme
+
+  - slug: test_domain_v2
+    reason: archived test domain; not active portfolio
+
+  # Local-only templates / sandboxes — not product inventory.
+  - slug: hub-core-seed
+    reason: hub-core bootstrap seed copy; not a standalone service
+
+  - slug: sand-boxer
+    reason: agentic coding sandbox; throwaway experimentation surface
+
+  - slug: .nvm
+    reason: Node version manager checkout; not a coulomb project repo
+
+  # Gitea repos referenced in portfolio review but not present / not cloned locally
+  # at T11 execution time — classify when a checkout exists or Gitea inventory confirms.
+  - slug: binect-chrome
+    reason: not cloned locally; pending inventory confirmation
+
+  - slug: binect-js
+    reason: not cloned locally; pending inventory confirmation
+
+  - slug: direkt-vermittlung-de
+    reason: not cloned locally; pending inventory confirmation
+
+  - slug: polycode-sim
+    reason: not cloned locally; pending inventory confirmation
+
+  - slug: ralph-workplan
+    reason: not cloned locally; pending inventory confirmation
+
+  - slug: tele-mcp
+    reason: not cloned locally; pending inventory confirmation
+
+  - slug: testdrive-jsui
+    reason: not cloned locally; pending inventory confirmation
+
+  - slug: timeline-svg
+    reason: not cloned locally; pending inventory confirmation
+
+  - slug: marki-docx
+    reason: registered in hub; no local checkout at T11 — classify on next clone
\ No newline at end of file
diff --git a/tools/batch_author_repo_classifications.py b/tools/batch_author_repo_classifications.py
new file mode 100644
index 0000000..2f94ec9
--- /dev/null
+++ b/tools/batch_author_repo_classifications.py
@@ -0,0 +1,383 @@
+#!/usr/bin/env python3
+"""First-pass .repo-classification.yaml author for CUST-WP-0050 T11.
+
+Writes agent-classified files for local git checkouts, validates against
+canon/standards/repo-classification.allowed.yaml, and optionally commits.
+
+Skips repos that already carry human-reviewed classifications and slugs on the
+exclusion list.
+"""
+from __future__ import annotations
+
+import argparse
+import json
+import subprocess
+import sys
+import urllib.request
+from datetime import date
+from pathlib import Path
+
+import yaml
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+ALLOWED_PATH = REPO_ROOT / "canon" / "standards" / "repo-classification.allowed.yaml"
+EXCLUSIONS_PATH = REPO_ROOT / "canon" / "standards" / "repo-classification.exclusions.yaml"
+VALIDATOR = REPO_ROOT / "tools" / "validate_repo_classification.py"
+HOME = Path.home()
+API_BASE = "http://127.0.0.1:8000"
+CLASSIFIED_AT = date.today().isoformat()
+
+# Curated overrides — standard §13 examples and T11 first-pass judgments.
+OVERRIDES: dict[str, dict] = {
+    "helix-forge": {
+        "category": "product",
+        "domain": "infotech",
+        "secondary_domains": ["agents"],
+        "capability_tags": [
+            "platform",
+            "capability-registry",
+            "coordination",
+            "knowledge",
+            "product-development",
+        ],
+        "business_stake": ["product", "technology", "execution", "automation", "intelligence"],
+        "business_mechanics": ["intention", "coordination", "operation", "adaptation"],
+        "notes": "Capability development platform; standard §13.1 example.",
+    },
+    "identity-canon": {
+        "category": "research",
+        "domain": "infotech",
+        "secondary_domains": ["government"],
+        "capability_tags": ["identity", "access-control", "terminology", "canon", "governance"],
+        "business_stake": ["technology", "legal", "operations", "intelligence"],
+        "business_mechanics": ["intention", "control", "adaptation"],
+        "notes": "Identity terminology and canon; standard §13.3 example.",
+    },
+    "net-kingdom": {
+        "category": "product",
+        "domain": "infotech",
+        "secondary_domains": [],
+        "capability_tags": ["security", "identity", "platform", "operations", "access-control"],
+        "business_stake": ["technology", "operations", "legal", "automation"],
+        "business_mechanics": ["control", "operation", "adaptation"],
+        "notes": "NetKingdom security/identity platform; standard §13.4 example.",
+    },
+    "citation-evidence": {
+        "category": "product",
+        "domain": "infotech",
+        "secondary_domains": ["communication", "government"],
+        "capability_tags": ["citations", "evidence", "knowledge", "traceability", "source-management"],
+        "business_stake": ["intelligence", "legal", "product", "technology"],
+        "business_mechanics": ["control", "coordination", "adaptation"],
+        "notes": "Citation and evidence product; standard §13.5 example.",
+    },
+    "adaptive-pricing": {
+        "category": "product",
+        "domain": "financials",
+        "secondary_domains": ["infotech", "agents"],
+        "capability_tags": ["pricing", "monetization", "lifecycle", "decision-support", "product-development"],
+        "business_stake": ["finance", "product", "sales", "intelligence", "automation"],
+        "business_mechanics": ["intention", "control", "adaptation"],
+        "notes": "Adaptive pricing product; standard §13.6 example.",
+    },
+    "reuse-surface": {
+        "category": "product",
+        "domain": "infotech",
+        "secondary_domains": ["agents"],
+        "capability_tags": ["capability-registry", "discovery", "reuse", "maturity", "evidence"],
+        "business_stake": ["technology", "product", "intelligence", "automation"],
+        "business_mechanics": ["intention", "control", "adaptation"],
+        "notes": "Reuse discovery surface; standard §13.7 example.",
+    },
+    "audit-core": {
+        "category": "tooling",
+        "domain": "infotech",
+        "secondary_domains": [],
+        "capability_tags": ["audit", "traceability", "security", "governance", "operations"],
+        "business_stake": ["technology", "operations", "legal", "automation"],
+        "business_mechanics": ["control", "operation"],
+        "notes": "Multi-tenant audit emit capability for platform bootstrap wiring.",
+    },
+    "whynot-design": {
+        "category": "product",
+        "domain": "consumer",
+        "secondary_domains": ["communication"],
+        "capability_tags": ["design-system", "documentation", "product-development", "experience"],
+        "business_stake": ["product", "experience", "technology"],
+        "business_mechanics": ["intention", "coordination", "adaptation"],
+        "notes": "whynot visual language — tokens, CSS, and web components for prototype artefacts.",
+    },
+    "coordination-engine": {
+        "category": "product",
+        "domain": "communication",
+        "secondary_domains": ["infotech", "agents"],
+        "capability_tags": ["coordination", "workflow", "orchestration", "evidence", "platform"],
+        "business_stake": ["product", "technology", "operations", "automation"],
+        "business_mechanics": ["coordination", "operation", "adaptation"],
+        "notes": "Goal-driven digital coordination framework and adapter runtime.",
+    },
+    "human-resources": {
+        "category": "research",
+        "domain": "consumer",
+        "secondary_domains": ["health"],
+        "capability_tags": ["knowledge", "documentation", "product-development"],
+        "business_stake": ["people", "product", "experience"],
+        "business_mechanics": ["intention", "adaptation"],
+        "notes": "Research toward optimal human performance.",
+    },
+    "repo-seed": {
+        "category": "tooling",
+        "domain": "infotech",
+        "secondary_domains": [],
+        "capability_tags": ["platform", "configuration", "documentation"],
+        "business_stake": ["technology", "execution"],
+        "business_mechanics": ["operation"],
+        "notes": "Git template for bootstrapping coulomb projects.",
+    },
+    "tegwick-control": {
+        "category": "research",
+        "domain": "consumer",
+        "secondary_domains": ["infotech"],
+        "capability_tags": ["coordination", "governance", "documentation", "knowledge"],
+        "business_stake": ["people", "operations", "intelligence"],
+        "business_mechanics": ["intention", "coordination", "adaptation"],
+        "notes": "Personal control repository for life/projects landscape.",
+    },
+    "whynot-control": {
+        "category": "research",
+        "domain": "consumer",
+        "secondary_domains": ["communication"],
+        "capability_tags": ["product-development", "knowledge", "coordination", "documentation"],
+        "business_stake": ["product", "experience", "intelligence"],
+        "business_mechanics": ["intention", "coordination", "adaptation"],
+        "notes": "whynot prototype and market-signal control repository.",
+    },
+    "markitect-main": {
+        "category": "product",
+        "domain": "communication",
+        "secondary_domains": ["infotech", "agents"],
+        "capability_tags": ["knowledge", "documentation", "product-development", "platform"],
+        "business_stake": ["product", "technology", "execution"],
+        "business_mechanics": ["intention", "coordination", "operation", "adaptation"],
+        "notes": "Markitect main product repo; successor to archived markitect-project.",
+    },
+    "vantage-point": {
+        "category": "research",
+        "domain": "infotech",
+        "secondary_domains": [],
+        "capability_tags": ["knowledge", "analytics", "platform", "documentation"],
+        "business_stake": ["technology", "intelligence", "product"],
+        "business_mechanics": ["intention", "adaptation"],
+        "notes": "Network-based graph model exploration and dependency reasoning framework.",
+    },
+}
+
+DOMAIN_DEFAULT_STAKE: dict[str, list[str]] = {
+    "infotech": ["technology", "product", "operations"],
+    "financials": ["finance", "technology", "operations"],
+    "communication": ["product", "experience", "technology"],
+    "consumer": ["product", "experience"],
+    "agents": ["technology", "automation", "product"],
+    "government": ["legal", "operations", "technology"],
+    "health": ["product", "experience", "operations"],
+    "realestate": ["finance", "operations"],
+}
+
+SLUG_TAG_HINTS: dict[str, list[str]] = {
+    "citation": ["citations", "evidence", "knowledge"],
+    "evidence": ["evidence", "traceability", "source-management"],
+    "railiance": ["platform", "operations"],
+    "markitect": ["knowledge", "documentation"],
+    "marki": ["knowledge", "documentation"],
+    "ops-": ["operations", "platform"],
+    "canon": ["canon", "knowledge", "governance"],
+    "flex-auth": ["identity", "access-control", "policy"],
+    "key-cape": ["identity", "access-control", "security"],
+    "shard-wiki": ["knowledge", "documentation"],
+    "vergabe": ["procurement", "governance"],
+    "agentic": ["automation", "orchestration"],
+    "repo-scoping": ["governance", "policy", "coordination"],
+}
+
+
+def load_excluded_slugs() -> set[str]:
+    with EXCLUSIONS_PATH.open() as fh:
+        doc = yaml.safe_load(fh)
+    return {entry["slug"].split("/")[-1] for entry in doc.get("exclusions", [])}
+
+
+def fetch_hub_repos() -> dict[str, dict]:
+    with urllib.request.urlopen(f"{API_BASE}/repos/", timeout=30) as resp:
+        repos = json.load(resp)
+    return {r["slug"]: r for r in repos}
+
+
+def local_git_repos() -> dict[str, Path]:
+    found: dict[str, Path] = {}
+    for child in HOME.iterdir():
+        if child.name.startswith(".") or not child.is_dir():
+            continue
+        if (child / ".git").is_dir():
+            found[child.name] = child
+    return found
+
+
+def _tag_hints(slug: str) -> list[str]:
+    tags: list[str] = []
+    for needle, hint_tags in SLUG_TAG_HINTS.items():
+        if needle in slug:
+            for tag in hint_tags:
+                if tag not in tags:
+                    tags.append(tag)
+    return tags
+
+
+def _enrich_from_hub(slug: str, hub: dict | None) -> dict:
+    if hub:
+        category = hub.get("category") or "project"
+        domain = hub.get("domain_slug") or "infotech"
+        secondary = hub.get("secondary_domains") or []
+        tags = list(hub.get("capability_tags") or [])
+        stake = list(hub.get("business_stake") or [])
+        mechanics = list(hub.get("business_mechanics") or [])
+    else:
+        category = "project"
+        domain = "infotech"
+        secondary = []
+        tags = []
+        stake = []
+        mechanics = []
+
+    for tag in _tag_hints(slug):
+        if tag not in tags:
+            tags.append(tag)
+    if not stake:
+        stake = list(DOMAIN_DEFAULT_STAKE.get(domain, ["technology", "product"]))
+    if not mechanics:
+        mechanics = ["coordination", "operation"]
+
+    return {
+        "category": category,
+        "domain": domain,
+        "secondary_domains": secondary,
+        "capability_tags": tags,
+        "business_stake": stake,
+        "business_mechanics": mechanics,
+        "notes": f"First-pass agent classification (CUST-WP-0050 T11); derived from hub migration row.",
+    }
+
+
+def build_classification(slug: str, hub: dict | None) -> dict:
+    if slug in OVERRIDES:
+        data = dict(OVERRIDES[slug])
+    else:
+        data = _enrich_from_hub(slug, hub)
+    data.pop("notes", None)
+    block = {
+        "repo_classification": {
+            "standard": "Repo Classification Standard",
+            "version": "1.0",
+            "classified_at": CLASSIFIED_AT,
+            "classified_by": "agent",
+            **{k: v for k, v in data.items() if k != "notes"},
+        }
+    }
+    if "notes" in OVERRIDES.get(slug, {}) or "notes" in data:
+        note = OVERRIDES.get(slug, {}).get("notes") or data.get("notes")
+        if note:
+            block["repo_classification"]["notes"] = note
+    return block
+
+
+def render_yaml(block: dict) -> str:
+    return yaml.dump(block, sort_keys=False, allow_unicode=True, default_flow_style=False)
+
+
+def validate_file(path: Path) -> bool:
+    proc = subprocess.run(
+        [sys.executable, str(VALIDATOR), str(path)],
+        capture_output=True,
+        text=True,
+    )
+    if proc.returncode != 0:
+        print(proc.stdout)
+        print(proc.stderr, file=sys.stderr)
+    return proc.returncode == 0
+
+
+def maybe_commit(repo_path: Path, dry_run: bool) -> None:
+    if dry_run:
+        return
+    subprocess.run(["git", "add", ".repo-classification.yaml"], cwd=repo_path, check=True)
+    status = subprocess.run(
+        ["git", "diff", "--cached", "--quiet"],
+        cwd=repo_path,
+    )
+    if status.returncode != 0:
+        subprocess.run(
+            [
+                "git",
+                "commit",
+                "-m",
+                "Add .repo-classification.yaml (CUST-WP-0050 T11 agent first-pass)",
+            ],
+            cwd=repo_path,
+            check=True,
+        )
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--dry-run", action="store_true", help="Print actions only")
+    parser.add_argument("--no-commit", action="store_true", help="Write files but skip git commit")
+    args = parser.parse_args()
+
+    excluded = load_excluded_slugs()
+    hub_repos = fetch_hub_repos()
+    local_repos = local_git_repos()
+
+    targets = sorted(set(local_repos) - excluded)
+    written: list[str] = []
+    skipped_human: list[str] = []
+    failed: list[str] = []
+
+    for slug in targets:
+        repo_path = local_repos[slug]
+        target = repo_path / ".repo-classification.yaml"
+        if target.exists():
+            with target.open() as fh:
+                existing = yaml.safe_load(fh) or {}
+            if existing.get("repo_classification", {}).get("classified_by") == "human":
+                skipped_human.append(slug)
+                continue
+
+        block = build_classification(slug, hub_repos.get(slug))
+        content = render_yaml(block)
+        if args.dry_run:
+            print(f"[dry-run] would write {target}")
+            continue
+
+        target.write_text(content)
+        if not validate_file(target):
+            failed.append(slug)
+            continue
+        if not args.no_commit:
+            maybe_commit(repo_path, dry_run=False)
+        written.append(slug)
+
+    print(f"Written: {len(written)}")
+    for slug in written:
+        print(f"  + {slug}")
+    print(f"Skipped (human-reviewed): {len(skipped_human)}")
+    for slug in skipped_human:
+        print(f"  = {slug}")
+    if failed:
+        print(f"Failed validation: {len(failed)}", file=sys.stderr)
+        for slug in failed:
+            print(f"  ! {slug}", file=sys.stderr)
+        return 1
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())
\ No newline at end of file
diff --git a/workplans/CUST-WP-0050-repo-classification-registration-redesign.md b/workplans/CUST-WP-0050-repo-classification-registration-redesign.md
index 36c7fa7..43cf372 100644
--- a/workplans/CUST-WP-0050-repo-classification-registration-redesign.md
+++ b/workplans/CUST-WP-0050-repo-classification-registration-redesign.md
@@ -4,7 +4,7 @@ type: workplan
 title: "Repo Classification & State Hub Registration Redesign"
 domain: custodian
 repo: the-custodian
-status: active
+status: finished
 owner: custodian
 topic_slug: custodian
 planning_priority: high
@@ -12,6 +12,7 @@ planning_order: 50
 created: "2026-06-22"
 updated: "2026-06-22"
 started: "2026-06-22"
+finished: "2026-06-22"
 state_hub_workstream_id: "9f031f48-8de8-48b6-8e69-d2d83ad70a7a"
 ---
 
@@ -305,7 +306,7 @@ Re-homed → STATE-WP-0065 P1 (re-anchor `repo_id` required + `workstream → wo
 
 ```task
 id: CUST-WP-0050-T11
-status: todo
+status: done
 priority: medium
 state_hub_task_id: "d8895c58-a930-42aa-8207-9babf9ba572a"
 ```
@@ -321,6 +322,21 @@ Done when every non-excluded active Gitea repo has a committed, validated
 classification file and a `managed_repo` row under the new taxonomy (or is on the
 recorded exclusion list).
 
+**Done (2026-06-22):**
+
+- Exclusion list: `canon/standards/repo-classification.exclusions.yaml` (forks,
+  archived phantoms, templates/sandboxes, Gitea repos pending local checkout).
+- Batch author: `tools/batch_author_repo_classifications.py` — agent first-pass
+  for 51 local repos (skips 10 human-reviewed custodian fixtures); all validated
+  against T01; committed in each target repo.
+- Registration: 7 newly registered (`coordination-engine`, `human-resources`,
+  `markitect-main`, `repo-seed`, `tegwick-control`, `vantage-point`,
+  `whynot-control`); `make register-from-classification-all` updated 43 existing
+  rows from `classified_by: migration` → `agent` (0 invalid).
+- **Coverage:** 63 active `managed_repos` — 11 `human`, 51 `agent`, 1 deferred
+  (`marki-docx`, hub-only, on exclusion list pending clone). Excluded locally:
+  `hub-core-seed`, `sand-boxer`. Archived hub rows (4) unchanged.
+
 ## Open Questions / Decisions
 
 - **D1 (RESOLVED 2026-06-22): the repo is the primary anchor.** Workplans bind to
@@ -335,8 +351,10 @@ recorded exclusion list).
   (e.g. `proj-<slug>` vs a dedicated grouping) and the archival trigger details.
 - **D2: classification ownership/approval.** Who approves each repo's
   `.repo-classification.yaml` — per-repo owner, or central custodian review?
-- **D3: exclusion list.** Confirm exclusions (fork `tegwick/the-custodian`,
-  `lando_worsch/python-snake`, archived `test_domain_v2`, any inactive repos).
+- **D3 (RESOLVED 2026-06-22): exclusion list.** Recorded at
+  `canon/standards/repo-classification.exclusions.yaml` — forks/personal repos,
+  archived phantoms, template/sandbox checkouts, and Gitea slugs pending local
+  checkout (incl. `marki-docx`).
 - **D4: behavioural vs descriptive.** Do `secondary_domains` / `capability_tags`
   / `business_stake` drive any Hub behaviour initially, or are they descriptive
   until a later phase?