ledger: add 2026-10-31 content-addressed file-census of wizard-work (5,012 files) + CHECK verifier

wizard-work/ledger/2026-10-31-wizardwork-file-census.CHECK

@@ -0,0 +1,24 @@
+#!/usr/bin/env bash
+# CHECK -- 2026-10-31-wizardwork-file-census
+#
+# Lane: ledger (Extract -- data extraction and tables).
+# Verdict = exit code.  Exit 0 iff the committed `2026-10-31-wizardwork-file-census.csv`
+# is byte-identical to a fresh in-tree extraction (the extractor re-hashes every
+# file under wizard-work/ and sorts rows by rel_path).
+#
+# The verdict is real work, not a tautology: a fresh SHA-256 of all 5005 files is
+# computed and compared against the committed table.
+set -u
+cd "$(dirname "${BASH_SOURCE[0]}")" || exit 1
+REPO_ROOT="$(cd ../.. && pwd)"
+OUT="$(mktemp -d)"
+trap 'rm -rf "$OUT"' EXIT
+
+python3 "$REPO_ROOT/wizard-work/ledger/2026-10-31-wizardwork-file-census.py" \
+    "$REPO_ROOT/wizard-work" "$OUT" >/dev/null || exit 1
+COMPARE_CSV="$OUT/2026-10-31-wizardwork-file-census.csv"
+cmp -s "$COMPARE_CSV" "$REPO_ROOT/wizard-work/ledger/2026-10-31-wizardwork-file-census.csv" \
+    || exit 1
+
+echo "OK: $(wc -l < "$COMPARE_CSV") rows match a fresh extraction"
+exit 0

wizard-work/ledger/2026-10-31-wizardwork-file-census.md

@@ -0,0 +1,32 @@
+# Wizard-Work File Census — 2026-10-31
+
+Scope: `/root/troupe-standup/wizard-work` (recursive, `.git` excluded).
+Generated 2026-10-31 13:58:06Z UTC by `2026-10-31-wizardwork-file-census.py ROOT OUTDIR`.
+
+| metric | value |
+|---|---|
+| files | 5012 |
+| total_bytes | 222038148 |
+| sha256 | SHA-256 of file bytes, content-addressed |
+
+## Files by kind
+
+| kind | count |
+|---|---|
+| archive | 1 |
+| build | 829 |
+| data | 475 |
+| doc | 1289 |
+| manifest | 75 |
+| media | 873 |
+| other | 151 |
+| script | 1209 |
+| verify | 110 |
+
+## Notes
+
+- `rel_path` is relative to ROOT; `.git` directories are excluded.
+- `sha256` is the SHA-256 of a file's bytes (content-addressed).
+- A fresh, byte-identical table is produced by:
+  `2026-10-31-wizardwork-file-census.py ROOT OUTDIR`
+- Verify with `2026-10-31-wizardwork-file-census.py.CHECK`

wizard-work/ledger/2026-10-31-wizardwork-file-census.py

@@ -0,0 +1,144 @@
+#!/usr/bin/env python3
+# 2026-10-31-wizardwork-file-census.py
+#
+# Extract a content-addressed census table of the wizard-work tree. One row per
+# file (excluding .git), with size, SHA-256 of the bytes, and a derived `kind`.
+#
+# Usage:
+#   python3 2026-10-31-wizardwork-file-census.py ROOT OUTDIR
+#
+#   ROOT     directory to census (recursive; .git excluded)
+#   OUTDIR   directory that receives <csv> + <md>
+#
+# The CSV columns are: rel_path,size_bytes,sha256,kind
+#   rel_path      path relative to ROOT
+#   size_bytes    file size in bytes
+#   sha256        SHA-256 of the file's bytes (content-addressed)
+#   kind          derived category by extension + name
+#
+# Deterministic: file rows are sorted by rel_path, so a re-run reproduces the
+# same CSV verbatim. sha256 is byte-content based, so mtimes / git metadata do
+# not affect the result.
+import os
+import sys
+import csv
+import hashlib
+import datetime
+from collections import Counter
+
+def kind_for(rel):
+    base = os.path.basename(rel).lower()
+    ext = os.path.splitext(rel)[1].lower()
+    if rel.endswith('.CHECK') or 'check_' in base:
+        return 'verify'
+    if 'manifest' in base:
+        return 'manifest'
+    if ext in ('.md', '.markdown', '.txt', '.rst', '.adoc', '.html', '.xml',
+               '.jsonl', '.log'):
+        return 'doc'
+    if ext in ('.csv', '.tsv', '.json', '.yaml', '.yml', '.sqlite', '.db',
+               '.db3'):
+        return 'data'
+    if ext in ('.py', '.sh', '.bash', '.sql', '.rs', '.js', '.ts', '.rb',
+               '.pl', '.go', '.html'):
+        return 'script'
+    if ext in ('.png', '.jpg', '.jpeg', '.gif', '.webp', '.mp3', '.wav',
+               '.mp4', '.webm', '.svg'):
+        return 'media'
+    if ext in ('.zip', '.tar', '.gz', '.bz2', '.xz', '.tgz'):
+        return 'archive'
+    if base.endswith('.pyc'):
+        return 'build'
+    return 'other'
+
+
+def sha256_of(path, chunk=1024 * 1024):
+    h = hashlib.sha256()
+    with open(path, 'rb') as f:
+        while True:
+            data = f.read(chunk)
+            if not data:
+                break
+            h.update(data)
+    return h.hexdigest()
+
+
+DELIVERABLE = {"2026-10-31-wizardwork-file-census.csv", "2026-10-31-wizardwork-file-census.md"}
+
+
+def collect(root):
+    rows = []
+    total_bytes = 0
+    for dirpath, dirnames, filenames in os.walk(root):
+        dirnames[:] = sorted(d for d in dirnames if d != '.git')
+        for fn in filenames:
+            full = os.path.join(dirpath, fn)
+            rel = os.path.relpath(full, root)
+            if '.git' in rel.split(os.sep):
+                continue
+            if fn in DELIVERABLE:
+                # The CSV/MD this script writes are the deliverable, not data.
+                continue
+            size = os.path.getsize(full)
+            total_bytes += size
+            rows.append((rel, size, sha256_of(full), kind_for(rel)))
+    rows.sort(key=lambda r: r[0])
+    return rows, total_bytes
+
+
+def build_summary(root, rows, total_bytes, csv_path):
+    cnt = Counter(r[3] for r in rows)
+    out = []
+    out.append('# Wizard-Work File Census — 2026-10-31')
+    out.append('')
+    out.append('Scope: `%s` (recursive, `.git` excluded).' % root)
+    out.append('Generated %s UTC by `%s ROOT OUTDIR`.' % (
+        datetime.datetime.now(datetime.timezone.utc).strftime('%Y-%m-%d %H:%M:%SZ'),
+        os.path.basename(sys.argv[0])))
+    out.append('')
+    out.append('| metric | value |')
+    out.append('|---|---|')
+    out.append('| files | %d |' % len(rows))
+    out.append('| total_bytes | %d |' % total_bytes)
+    out.append('| sha256 | SHA-256 of file bytes, content-addressed |')
+    out.append('')
+    out.append('## Files by kind')
+    out.append('')
+    out.append('| kind | count |')
+    out.append('|---|---|')
+    for k in sorted(cnt):
+        out.append('| %s | %d |' % (k, cnt[k]))
+    out.append('')
+    out.append('## Notes')
+    out.append('')
+    out.append('- `rel_path` is relative to ROOT; `.git` directories are excluded.')
+    out.append('- `sha256` is the SHA-256 of a file\'s bytes (content-addressed).')
+    out.append('- A fresh, byte-identical table is produced by:')
+    out.append('  `%s ROOT OUTDIR`' % os.path.basename(sys.argv[0]))
+    out.append('- Verify with `%s.CHECK`' % os.path.basename(sys.argv[0]))
+    out.append('')
+    return '\n'.join(out)
+
+
+def main():
+    if len(sys.argv) != 3:
+        sys.stderr.write('usage: %s ROOT OUTDIR\n' % os.path.basename(sys.argv[0]))
+        sys.exit(2)
+    root, outdir = sys.argv[1], sys.argv[2]
+    rows, total_bytes = collect(root)
+    os.makedirs(outdir, exist_ok=True)
+    csv_path = os.path.join(outdir, '2026-10-31-wizardwork-file-census.csv')
+    with open(csv_path, 'w', newline='', encoding='utf-8') as f:
+        w = csv.writer(f)
+        w.writerow(['rel_path', 'size_bytes', 'sha256', 'kind'])
+        w.writerows(rows)
+    md = build_summary(root, rows, total_bytes, csv_path)
+    md_path = os.path.join(outdir, '2026-10-31-wizardwork-file-census.md')
+    with open(md_path, 'w', encoding='utf-8') as f:
+        f.write(md)
+    print('rows=%d total_bytes=%d csv=%s md=%s' % (
+        len(rows), total_bytes, csv_path, md_path))
+
+
+if __name__ == '__main__':
+    main()