…mposes_with: lists)

The `fix-markdown-md032-md026.py` tool's MD032 (blanks-around-lists)
fix was too aggressive — it inserted blank lines around lists inside
YAML frontmatter, which breaks YAML parsing.

Concrete failure mode (caught while running on PR #699 substrate):

  composes_with:
    - B-0060
  tags: [...]

becomes:

  composes_with:

    - B-0060

  tags: [...]

YAML now parses `composes_with: null` plus a separate top-level
`- B-0060` list item, breaking the frontmatter structure.

## The fix

Extended `_classify_lines()` to detect YAML frontmatter regions
(file starts with `---`, has another `---` later) and mark those
lines as "inside" so MD032/MD026 transforms skip them — same
treatment as fenced code blocks.

Detection is light-weight:
- Only triggers when line 0 is exactly `---`
- Looks for closing `---` later in the file
- If found, marks all lines through the closing `---` as inside
- If no closing `---` found (file probably isn't real
  frontmatter), treats normally — no false-positive blocking

Files without frontmatter (line 0 not `---`) skip the
frontmatter-detection logic entirely — no behavior change.

## Smoke test results

```
$ cat /tmp/test-fm.md
---
id: TEST
composes_with:
  - X
tags: [a, b]
---

# Title

Aaron's role:
- input
- ask
```

After fix:

```
---
id: TEST
composes_with:
  - X         ← preserved (would have been broken by old version)
tags: [a, b]
---

# Title

Aaron's role:
                ← inserted (correct: body MD032 fix still applied)
- input
- ask
```

Both behaviors:
- YAML frontmatter preserved verbatim ✓
- Body MD032 fix applied ✓

## Idempotence

Running on already-clean files is still no-op. Verified on
freshly-fixed PR #699 substrate files — "OK: no changes needed"
for files that had previously been fixed (now via the new
YAML-aware path).

Discovered as a side effect during PR #699 review work
(commit fe72fa5 noted the tool-improvement candidate; this PR
delivers the fix).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

…hematic break (Copilot threads on PR #703)

Three Copilot threads on PR #703 addressed:

## P2 thread #1 (load-bearing): thematic-break false positive

Previous heuristic: line 0 is `---` + closing `---` later → frontmatter.
Bug: a markdown file starting with a thematic break (`---` followed
by markdown body) would have all subsequent content marked as "inside
frontmatter," skipping every list and heading from being processed.

Fix: tightened detection to require all THREE conditions:
1. line 0 is exactly `---`
2. line 1 is YAML-shaped (matches `^\s*[A-Za-z_][\w-]*\s*:`)
3. a closing `---` line exists later

The (b) check is the discriminator. YAML frontmatter starts with a
key:value line; a thematic break is `---` followed by markdown body
(heading, prose, blank line, etc.).

Smoke tests verify both cases:
- thematic break → body MD032 applied (no false-positive frontmatter)
- real frontmatter → frontmatter preserved + body MD032 applied

## P2 thread #2 (nit): docstring overstated YAML/MD026 risk

Previous docstring claimed MD026 would "strip trailing punctuation
from YAML keys" — but MD026 only matches ATX headings (`^#+ `),
which YAML keys can't accidentally match (they don't start with `#`).
Updated docstring to accurately scope the YAML risk to MD032 blank-
insertion only.

## P2 thread #3 (nit): docstring/implementation mismatch

Previous docstring said "line 0 is exactly `---`" but implementation
used `lines[0].strip() == "---"`. Now uses `.rstrip()` (more
permissive: tolerates trailing whitespace/newline; rejects leading
whitespace which would indicate non-frontmatter shape) AND docstring
matches.

Added `_YAML_KEY_LINE` regex with explanatory comment for the
discriminator.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

…s (Copilot P2 thread on PR #703)

Copilot P2 push: prior 3-check heuristic still mis-classifies prose
as frontmatter when:
  - line 0 is `---` (thematic break)
  - line 1 happens to look like `key: value` (e.g. `note: Some text`)
  - another `---` appears later (closing thematic break)

In that case everything between would be treated as inside frontmatter
and MD032/MD026 fixes would silently skip real lint violations.

## Tightened to 5 conditions

(a) line 0 is exactly `---`
(b) line 1 is YAML-shaped
(c) closing `---` exists within next 200 lines (defense-in-depth cap;
    real frontmatter rarely > 50 lines)
(d) line BEFORE closing `---` is YAML-shaped, blank, or YAML
    continuation (catches the case where closing `---` is just
    another thematic break, preceded by markdown prose)
(e) at least 75% of non-blank lines between bookends are YAML-shaped
    (catches single-YAML-key prose pattern: "note:" or "warning:" or
    "tip:" between two thematic breaks)

The (d)/(e) checks together resolve the false-positive class.

## Smoke tests

Prose case (thematic break + "note:" prose + closing thematic break):
  → NOT treated as frontmatter
  → body MD032 fires correctly on lists in body

Real frontmatter (`composes_with:` + list + `tags:` + closing `---`):
  → preserved verbatim (no blank lines injected inside list)
  → body MD032 fires correctly on body lists

Both behaviors verified.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

…e redundant comparison + fix docstring (PR #703 4 threads)

Four Copilot threads addressed:

## P2 #1 + #2: column-0 markdown lists wrongly counted as YAML

The (e) ratio check counted any line starting with `- ` as
YAML-shaped, including column-0 markdown list items. A normal
markdown document with prose + bullet lists between thematic
breaks could pass the ratio check and be wrongly flagged as
frontmatter.

## Fix: distinguish indented YAML lists from column-0 markdown

Added `_is_yaml_continuation()` helper that requires LEADING
INDENT (`  ` or `\t`) — a column-0 `- item` is almost always
markdown, not YAML.

Real YAML list items appear under a parent key with indent:

```yaml
composes_with:
  - X       ← indented = YAML continuation
  - Y
```

Markdown list items at column 0 are NOT YAML:

```markdown
A list:
- item one  ← column 0 = markdown list
- item two
```

The leading-indent check disambiguates these two cases.

## P1 (CodeQL): Redundant comparison

Removed `if fm_end > 0 else ""` ternary — already inside the
`if fm_end > 0:` block so the test was always true.

## P2 #4: Docstring inconsistency on _YAML_KEY_LINE

Comment claimed the regex matches `  - item`, but the regex
`^\s*[A-Za-z_][\w-]*\s*:` only matches key:value lines.
Updated comment to accurately describe what the regex matches +
what it doesn't (list items go through `_is_yaml_continuation`).

## Smoke test results

Markdown with thematic-break + `note:` + bullet list + closing
thematic break:
  → NOT treated as frontmatter
  → body MD032 fires correctly on the bullet list

Real frontmatter with `composes_with:` + indented list items:
  → preserved verbatim
  → body MD032 fires correctly on body lists

Both behaviors verified.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>