Merge pull request 'feat(lint): wire Vale as deterministic prefilter for skill-audit/agent-audit' (#85) from feat/84-vale-audit-prefilter into main

Reviewed-on: https://git.dev.rkdr.net/Defame1297/holocron/pulls/85
Reviewed-by: Defame1297 <gitea@rkdr.net>

plugins/gitea/.claude-plugin/plugin.json

@@ -15,5 +15,5 @@
   ],
   "license": "MIT",
   "name": "gitea",
-  "version": "1.3.2"
+  "version": "1.3.3"
 }

plugins/gitea/plugin.json

@@ -20,5 +20,5 @@
   "skills": [
     "skills/"
   ],
-  "version": "1.3.2"
+  "version": "1.3.3"
 }

plugins/kyberforge/skills/agent-audit/scripts/vale-wrap.sh

@@ -77,6 +77,17 @@ is_builtin_output() {
     *) false ;;
   esac
 }
+# Absolutizes a `--config` value against the caller's cwd. Shared by both
+# argument forms below — separated (`--config X`) and joined (`--config=X`)
+# — so the "already absolute vs. needs $cwd prefixed" check lives in exactly
+# one place instead of being duplicated per form.
+abs_config_value() {
+  if [[ "$1" == /* ]]; then
+    printf '%s' "$1"
+  else
+    printf '%s' "$cwd/$1"
+  fi
+}
 for arg in "$@"; do
   if [[ -n "$pending_flag" ]]; then
     # Value of a separated two-argv flag. It is never a lint target, however
@@ -85,11 +96,7 @@ for arg in "$@"; do
     case "$pending_flag" in
       --config)
         # Always a path, and required to exist.
-        if [[ "$arg" == /* ]]; then
-          vale_args+=("$arg")
-        else
-          vale_args+=("$cwd/$arg")
-        fi
+        vale_args+=("$(abs_config_value "$arg")")
         ;;
       --output|--path)
         # See `is_builtin_output` above for why the built-in `--output` names
@@ -117,13 +124,8 @@ for arg in "$@"; do
       config_given=true
       continue
       ;;
-    --config=/*)
-      vale_args+=("$arg")
-      config_given=true
-      continue
-      ;;
     --config=*)
-      vale_args+=("--config=$cwd/${arg#--config=}")
+      vale_args+=("--config=$(abs_config_value "${arg#--config=}")")
       config_given=true
       continue
       ;;
@@ -204,11 +206,33 @@ abspath() {
 }
 
 flatten() {
-  python3 - "$1" "$2" <<'PYTHON'
+  # Two call shapes: `flatten src dest` (dest already resolved and inside the
+  # scratch tree — the per-markdown-file calls in the directory branch below)
+  # writes straight to `dest`. `flatten src raw_dest tmpdir` (the single-file
+  # branch further down) additionally resolves `raw_dest` the way a separate
+  # `abspath` call used to, applies the same sandbox-escape guard, and prints
+  # the resolved path — folding two python3 spawns per file into one.
+  python3 - "$@" <<'PYTHON'
+import os
 import re
 import sys
 
-src, dest = sys.argv[1], sys.argv[2]
+src, dest_input = sys.argv[1], sys.argv[2]
+tmpdir = sys.argv[3] if len(sys.argv) > 3 else None
+
+if tmpdir is None:
+    dest = dest_input
+else:
+    dest = os.path.abspath(dest_input)
+    if not dest.startswith(tmpdir + os.sep):
+        print(
+            f"vale-wrap.sh: refusing to lint '{src}': its scratch copy would "
+            f"land outside {tmpdir}",
+            file=sys.stderr,
+        )
+        sys.exit(2)
+    os.makedirs(os.path.dirname(dest), exist_ok=True)
+
 # surrogateescape keeps a non-UTF-8 file (reachable via a directory argument)
 # a byte-for-byte round trip instead of aborting the whole run on a decode error.
 with open(src, encoding='utf-8', errors='surrogateescape') as fh:
@@ -435,6 +459,9 @@ if header_m:
 
 with open(dest, 'w', encoding='utf-8', errors='surrogateescape') as fh:
     fh.write(content)
+
+if tmpdir is not None:
+    print(dest)
 PYTHON
 }
 
@@ -449,11 +476,12 @@ mkdir -p "$mirror"
 argv_paths=()
 for arg in ${path_args[@]+"${path_args[@]}"}; do
   if [[ "$arg" == /* ]]; then
-    dest="$tmpdir$arg"
+    raw_dest="$tmpdir$arg"
   else
-    dest="$mirror/$arg"
+    raw_dest="$mirror/$arg"
   fi
-  dest="$(abspath "$dest")"
+  if [[ -d "$arg" ]]; then
+    dest="$(abspath "$raw_dest")"
     # A path argument with enough leading `..` to climb past the mirror root would
     # write outside the scratch dir. The real filesystem clamps such a path at
     # `/`; the mirror can't, so refuse rather than scribble outside the sandbox.
@@ -465,7 +493,6 @@ for arg in ${path_args[@]+"${path_args[@]}"}; do
         ;;
     esac
     mkdir -p "$(dirname "$dest")"
-  if [[ -d "$arg" ]]; then
     # A directory is mirrored whole — vale applies its own format filtering to
     # the tree, so any file dropped here would be silently unlinted — and then
     # every markdown file in the copy is flattened in place. `.git` is pruned:
@@ -484,7 +511,9 @@ for arg in ${path_args[@]+"${path_args[@]}"}; do
       flatten "$md" "$md"
     done < <(find "$dest" -type f -name '*.md' -print0)
   else
-    flatten "$arg" "$dest"
+    # `abspath` + `flatten` folded into one python3 process — see the comment
+    # atop `flatten` above.
+    dest="$(flatten "$arg" "$raw_dest" "$tmpdir")"
   fi
   if [[ "$arg" == /* ]]; then
     argv_paths+=("$dest")

plugins/kyberforge/skills/skill-audit/scripts/vale-wrap.sh

@@ -77,6 +77,17 @@ is_builtin_output() {
     *) false ;;
   esac
 }
+# Absolutizes a `--config` value against the caller's cwd. Shared by both
+# argument forms below — separated (`--config X`) and joined (`--config=X`)
+# — so the "already absolute vs. needs $cwd prefixed" check lives in exactly
+# one place instead of being duplicated per form.
+abs_config_value() {
+  if [[ "$1" == /* ]]; then
+    printf '%s' "$1"
+  else
+    printf '%s' "$cwd/$1"
+  fi
+}
 for arg in "$@"; do
   if [[ -n "$pending_flag" ]]; then
     # Value of a separated two-argv flag. It is never a lint target, however
@@ -85,11 +96,7 @@ for arg in "$@"; do
     case "$pending_flag" in
       --config)
         # Always a path, and required to exist.
-        if [[ "$arg" == /* ]]; then
-          vale_args+=("$arg")
-        else
-          vale_args+=("$cwd/$arg")
-        fi
+        vale_args+=("$(abs_config_value "$arg")")
         ;;
       --output|--path)
         # See `is_builtin_output` above for why the built-in `--output` names
@@ -117,13 +124,8 @@ for arg in "$@"; do
       config_given=true
       continue
       ;;
-    --config=/*)
-      vale_args+=("$arg")
-      config_given=true
-      continue
-      ;;
     --config=*)
-      vale_args+=("--config=$cwd/${arg#--config=}")
+      vale_args+=("--config=$(abs_config_value "${arg#--config=}")")
       config_given=true
       continue
       ;;
@@ -204,11 +206,33 @@ abspath() {
 }
 
 flatten() {
-  python3 - "$1" "$2" <<'PYTHON'
+  # Two call shapes: `flatten src dest` (dest already resolved and inside the
+  # scratch tree — the per-markdown-file calls in the directory branch below)
+  # writes straight to `dest`. `flatten src raw_dest tmpdir` (the single-file
+  # branch further down) additionally resolves `raw_dest` the way a separate
+  # `abspath` call used to, applies the same sandbox-escape guard, and prints
+  # the resolved path — folding two python3 spawns per file into one.
+  python3 - "$@" <<'PYTHON'
+import os
 import re
 import sys
 
-src, dest = sys.argv[1], sys.argv[2]
+src, dest_input = sys.argv[1], sys.argv[2]
+tmpdir = sys.argv[3] if len(sys.argv) > 3 else None
+
+if tmpdir is None:
+    dest = dest_input
+else:
+    dest = os.path.abspath(dest_input)
+    if not dest.startswith(tmpdir + os.sep):
+        print(
+            f"vale-wrap.sh: refusing to lint '{src}': its scratch copy would "
+            f"land outside {tmpdir}",
+            file=sys.stderr,
+        )
+        sys.exit(2)
+    os.makedirs(os.path.dirname(dest), exist_ok=True)
+
 # surrogateescape keeps a non-UTF-8 file (reachable via a directory argument)
 # a byte-for-byte round trip instead of aborting the whole run on a decode error.
 with open(src, encoding='utf-8', errors='surrogateescape') as fh:
@@ -435,6 +459,9 @@ if header_m:
 
 with open(dest, 'w', encoding='utf-8', errors='surrogateescape') as fh:
     fh.write(content)
+
+if tmpdir is not None:
+    print(dest)
 PYTHON
 }
 
@@ -449,11 +476,12 @@ mkdir -p "$mirror"
 argv_paths=()
 for arg in ${path_args[@]+"${path_args[@]}"}; do
   if [[ "$arg" == /* ]]; then
-    dest="$tmpdir$arg"
+    raw_dest="$tmpdir$arg"
   else
-    dest="$mirror/$arg"
+    raw_dest="$mirror/$arg"
   fi
-  dest="$(abspath "$dest")"
+  if [[ -d "$arg" ]]; then
+    dest="$(abspath "$raw_dest")"
     # A path argument with enough leading `..` to climb past the mirror root would
     # write outside the scratch dir. The real filesystem clamps such a path at
     # `/`; the mirror can't, so refuse rather than scribble outside the sandbox.
@@ -465,7 +493,6 @@ for arg in ${path_args[@]+"${path_args[@]}"}; do
         ;;
     esac
     mkdir -p "$(dirname "$dest")"
-  if [[ -d "$arg" ]]; then
     # A directory is mirrored whole — vale applies its own format filtering to
     # the tree, so any file dropped here would be silently unlinted — and then
     # every markdown file in the copy is flattened in place. `.git` is pruned:
@@ -484,7 +511,9 @@ for arg in ${path_args[@]+"${path_args[@]}"}; do
       flatten "$md" "$md"
     done < <(find "$dest" -type f -name '*.md' -print0)
   else
-    flatten "$arg" "$dest"
+    # `abspath` + `flatten` folded into one python3 process — see the comment
+    # atop `flatten` above.
+    dest="$(flatten "$arg" "$raw_dest" "$tmpdir")"
   fi
   if [[ "$arg" == /* ]]; then
     argv_paths+=("$dest")

scripts/check-vale-style-sync.sh

@@ -10,11 +10,17 @@ set -euo pipefail
 # only one of the two. Run from repo root or pass REPO_ROOT as arg.
 
 REPO_ROOT="${1:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}"
+# A nonexistent REPO_ROOT must fail loudly, not fall through to the "neither
+# copy present" no-op below — that guard exists for a repo that legitimately
+# has no kyberforge plugin installed, not for a typo'd or stale path, and a
+# clean exit 0 here would read as "checked, in sync" when nothing ran at all.
+if [[ ! -d "$REPO_ROOT" ]]; then
+  echo "Vale style sync check failed: REPO_ROOT '$REPO_ROOT' is not a directory." >&2
+  exit 1
+fi
 # Absolutized because the glob probe below `cd`s into a scratch tree, where a
 # relative --config path would stop resolving.
-if [[ -d "$REPO_ROOT" ]]; then
 REPO_ROOT="$(cd "$REPO_ROOT" && pwd)"
-fi
 FAIL=0
 
 err() { echo "  FAIL: $1" >&2; FAIL=$((FAIL + 1)); }
@@ -80,8 +86,28 @@ done
 # Prints the `files:` regex of every hook, in either manifest, whose entry is
 # $1's vale-wrap.sh. Records are delimited by their `- id:` line, so the check
 # does not depend on `entry:` preceding `files:` within a record.
+#
+# Cached per skill (parallel HOOK_REGEX_CACHE_KEYS/_VALS arrays, populated
+# lazily) because the final validation loop below probes agent-audit twice —
+# once for its CC agent-file shape, once for its Copilot .agent.md shape — and
+# both probes need the same regex set. Without the cache, that pair of calls
+# would each re-parse both manifest files from scratch for no new information.
+# Plain indexed arrays, not `declare -A`: associative arrays are bash 4.0+ and
+# this script must run on macOS's stock bash 3.2. Only ${#arr[@]} (always safe
+# on an empty/unset array under `set -u`) and index access are used below —
+# never a bare `${arr[@]}` expansion, which aborts on bash < 4.4 under nounset.
+HOOK_REGEX_CACHE_KEYS=()
+HOOK_REGEX_CACHE_VALS=()
 hook_file_regexes() {
-  local skill="$1" manifest raw
+  local skill="$1" manifest raw result idx=0
+  while [[ $idx -lt ${#HOOK_REGEX_CACHE_KEYS[@]} ]]; do
+    if [[ "${HOOK_REGEX_CACHE_KEYS[$idx]}" == "$skill" ]]; then
+      printf '%s' "${HOOK_REGEX_CACHE_VALS[$idx]}"
+      return
+    fi
+    idx=$((idx + 1))
+  done
+  result="$(
     for manifest in "$REPO_ROOT/.pre-commit-hooks.yaml" "$REPO_ROOT/.pre-commit-config.yaml"; do
       [[ -f "$manifest" ]] || continue
       awk -v skill="$skill" '
@@ -100,6 +126,10 @@ hook_file_regexes() {
       raw="${raw%\"}"; raw="${raw#\"}"
       printf '%s\n' "$raw"
     done
+  )"
+  HOOK_REGEX_CACHE_KEYS[${#HOOK_REGEX_CACHE_KEYS[@]}]="$skill"
+  HOOK_REGEX_CACHE_VALS[${#HOOK_REGEX_CACHE_VALS[@]}]="$result"
+  printf '%s' "$result"
 }
 
 # Asks vale — the thing that actually applies these globs — whether a config

scripts/skill-size-check.sh

@@ -35,6 +35,13 @@ set -euo pipefail
 # tokenization and does not replace one. Re-measure the corpus before treating
 # any of these numbers as still current.
 
+# These constants are intentionally duplicated in
+# skill-audit/scripts/validate.sh (Python) rather than shared from one file:
+# this script is a standalone bash pre-commit hook, that one is an in-skill
+# Python validator invoked in a different context (same rationale as
+# vale-wrap.sh's per-plugin duplication — see its own header comment).
+# tests/test-skill-size-check.sh asserts both files agree on these values, so
+# drift between them fails CI rather than silently diverging.
 MAX_LINES=500
 MAX_WORDS=2770
 FAIL=0
@@ -42,16 +49,19 @@ FAIL=0
 for f in "$@"; do
   [[ -f "$f" ]] || continue
 
-  # awk's NR counts the final line even without a trailing newline, matching
-  # Python's splitlines() semantics (used by skill-audit/scripts/validate.sh
-  # for its own line count) — `wc -l` undercounts by 1 in that case.
-  lines=$(awk 'END{print NR}' "$f")
+  # Single awk pass computes both line count and word count, avoiding a
+  # second read of the file. NR counts the final line even without a
+  # trailing newline, matching Python's splitlines() semantics (used by
+  # skill-audit/scripts/validate.sh for its own line count) — `wc -l`
+  # undercounts by 1 in that case. Word count uses awk's default
+  # whitespace-splitting NF, matching `wc -w` semantics.
+  read -r lines words <<< "$(awk '{w += NF} END{print NR, w+0}' "$f")"
+
   if (( lines > MAX_LINES )); then
     echo "ERROR: $f has $lines lines, exceeding the $MAX_LINES-line ceiling (agentskills.io skill-authoring.md)" >&2
     FAIL=1
   fi
 
-  words=$(wc -w < "$f")
   if (( words > MAX_WORDS )); then
     echo "ERROR: $f has $words words (proxy for tokens), exceeding the $MAX_WORDS-word ceiling (~5,000 tokens, agentskills.io skill-authoring.md)" >&2
     FAIL=1

tests/test-check-vale-style-sync.sh

@@ -123,6 +123,19 @@ else
   fail "exited non-zero when skill-audit/agent-audit are simply absent"
 fi
 
+# --- 5b. Exits 1 when REPO_ROOT does not exist ---
+# A nonexistent path used to fall through to the "neither copy present" no-op
+# (test 5 above) and exit 0 — indistinguishable from a real, verified in-sync
+# result. That guard is for a repo legitimately missing kyberforge, not a
+# typo'd or stale path.
+echo ""
+echo "--- exits 1 when REPO_ROOT does not exist ---"
+if bash "$SCRIPT" "/nonexistent/path/$(date +%s)-$$" > /dev/null 2>&1; then
+  fail "exited 0 for a nonexistent REPO_ROOT — expected exit 1"
+else
+  pass "exits non-zero for a nonexistent REPO_ROOT"
+fi
+
 # --- 6. Exits 1 when only one of the two copies is present ---
 # The no-op guard used `||`, so a single missing copy also exited 0 — a deleted
 # or renamed copy passed the sync check silently.

tests/test-vale-wrap.sh

@@ -447,7 +447,10 @@ fi
 # scripts, and the test runner AGENTS.md tells contributors to run by hand.
 # `mapfile` is checked alongside, because it is bash 4.0+ and the expansion scan
 # cannot see it — run-tests.sh carried one until it was replaced with a
-# `while read` loop, and nothing would have caught its return.
+# `while read` loop, and nothing would have caught its return. `declare -A`
+# (bash 4.0+ associative arrays) is checked for the same reason — the
+# expansion scan cannot see it, and check-vale-style-sync.sh carried a pair of
+# them until they were replaced with index-scanned plain arrays.
 echo ""
 echo "--- no unguarded array expansion remains in the macOS-facing scripts ---"
 unguarded_expansions() {
@@ -474,6 +477,7 @@ for BASH32_SCRIPT in \
   "$SCRIPT" \
   "$REPO_ROOT/scripts/skill-size-check.sh" \
   "$REPO_ROOT/scripts/check-release-needed.sh" \
+  "$REPO_ROOT/scripts/check-vale-style-sync.sh" \
   "$REPO_ROOT/tests/run-tests.sh"; do
   FOUND16="$(unguarded_expansions "$BASH32_SCRIPT")"
   if [[ -n "$FOUND16" ]]; then
@@ -486,6 +490,15 @@ for BASH32_SCRIPT in \
   if [[ -n "$FOUND16B" ]]; then
     HAZARDS16+="${BASH32_SCRIPT##*/}:$FOUND16B "
   fi
+  # `declare -A` (associative arrays) is bash 4.0+ with no 3.2 fallback. The
+  # flag cluster can carry other letters in any order (-Ag, -rA, ...); what
+  # matters is a literal uppercase A appearing in it, so match on that rather
+  # than the exact string "-A".
+  FOUND16C="$(awk '{ if ($0 ~ /^[[:space:]]*#/) print ""; else print }' "$BASH32_SCRIPT" \
+    | grep -nE '(^|[^[:alnum:]_])declare[[:space:]]+-[a-zA-Z]*A[a-zA-Z]*([[:space:]]|$)' || true)"
+  if [[ -n "$FOUND16C" ]]; then
+    HAZARDS16+="${BASH32_SCRIPT##*/}:$FOUND16C "
+  fi
 done
 if [[ -n "$HAZARDS16" ]]; then
   fail "unguarded array expansion(s) abort on bash < 4.4 under set -u: $(echo "$HAZARDS16" | tr '\n' ' ')"