#!/usr/bin/env bash
set -euo pipefail

# Enforces agentskills.io's skill-authoring.md guidance: keep SKILL.md within
# 500 lines and roughly 5,000 tokens, so the full body doesn't crowd out
# conversation history and other active skills once loaded into context. Vale
# can't express a whole-file length ceiling (its checks operate on text
# patterns, not raw file size), so this is a plain script instead of a Vale
# rule.
#
# Both ceilings are inclusive: a file at exactly MAX_LINES or MAX_WORDS passes,
# and only one past it fails. That matches skill-audit/scripts/validate.sh,
# which has always used `line_count <= 500` as its pass condition — the two
# previously disagreed at exactly 500 lines, so a SKILL.md could pass its own
# audit and still be blocked by the commit hook.
#
# Token counts aren't computed exactly here — word count (`wc -w`) is used as
# a proxy. Measured over this repo's 39 in-scope SKILL.md files, characters per
# word runs min 5.97 / median 6.79 / mean 6.77 / max 7.22. At the standard
# ~4-characters-per-token English approximation that is 1.49 / 1.70 / 1.69 /
# 1.81 tokens per word.
#
# MAX_WORDS=2770 is therefore calibrated to the corpus WORST case rather than
# its median: 2770 words at the densest observed 7.22 chars/word is ~20,000
# characters, or ~5,000 tokens at the 4-characters-per-token approximation. So
# what this gate guarantees is "under 5,000 tokens even for the densest prose
# the corpus has produced" — the earlier median-calibrated MAX_WORDS=2900 let
# such a file sit at exactly the ceiling and still spend ~5,240 tokens. A
# median-density file at 2770 words spends ~4,700 tokens, so typical prose
# gives up ~130 words of headroom to close that gap. The largest SKILL.md in
# the repo is 2,489 words, so no current file is affected.
#
# It is a one-sided proxy in the useful direction — nothing under the word
# ceiling is wildly over the token ceiling — but it is not exact BPE
# 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

for f in "$@"; do
  [[ -f "$f" ]] || continue

  # 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

  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
  fi
done

exit $FAIL