git-ai-archaeology

git-ai-archaeology

Produces a complete analysis of AI config evolution in a git repository. Finds when each AI configuration file was created, how AI-config commit velocity evolved month by month, which PRs structured the evolution, and identifies maturity phases.

**Output**: a single file `{output_dir}/{slug}-git-archaeology.md`

Expected Input

/git-ai-archaeology repo_path=/path/to/repo [output=./talks/slug] [slug=talk-name] [since=2025-01-01]

• `repo_path`: absolute path to the target git repo (required)
• `output`: output directory (default: `./talks`)
• `slug`: output filename (default: repo folder name)
• `since`: analysis start date (default: first repo commit)

Workflow

• **Verify the repo**: ensure the path exists and is a git repo
• **Global metrics**: total commits, releases, contributors, time period
• **Section 1 — First commits**: find creation date for key AI-config paths
• **Section 2 — Monthly distribution**: commits filtered by AI-config keywords
• **Section 3 — Major PRs**: extract and categorize significant AI-config commits
• **Section 4 — CHANGELOG**: if CHANGELOG.md exists, extract releases with AI mentions
• **Section 5 — Phases**: synthesize evolution phases
• **Save** the output file

---

Step 1: Verification and Global Metrics

# Verify it's a git repo
git -C {repo_path} rev-parse --git-dir

# Global metrics
git -C {repo_path} log --oneline | wc -l                                    # total commits
git -C {repo_path} tag --sort=version:refname | wc -l                       # total releases
git -C {repo_path} shortlog -sn --no-merges | wc -l                         # contributors
git -C {repo_path} log --pretty=format:"%ad" --date=short | tail -1         # first commit
git -C {repo_path} log --pretty=format:"%ad" --date=short | head -1         # last commit
git -C {repo_path} log --merges --oneline | wc -l                           # merged PRs

---

Step 2: Section 1 — First Commits per AI-Config Path

For each path, find the origin commit with `--diff-filter=A`:

# Paths to analyze — adapt based on what exists in the repo
PATHS=(
  "CLAUDE.md"
  ".claude"
  ".claude/commands"
  ".claude/agents"
  ".claude/hooks"
  ".claude/skills"
  ".claude/rules"
  ".agents"
  ".cursor"
  "doc/knowledge-base.md"
  "doc/guides/ai-instructions"
  "doc/guides/ai-review"
)

for path in "${PATHS[@]}"; do
  git -C {repo_path} log --diff-filter=A --follow \
    --format="%ad | %H | %s" --date=short \
    -- "$path" | tail -1
done

Build the Section 1 table from results. Skip paths with no output (don't exist in this repo).

Also build the ASCII timeline:

{date} ─── {path} ─── {message}

Sorted chronologically.

---

Step 3: Section 2 — Monthly Distribution of AI-Config Commits

Filter commits by AI-config-related keywords:

# All commits with AI-config keywords
git -C {repo_path} log --format="%H %s" | \
  grep -iE "(claude|feat.ai|docs.ai|tech.ai|mcp|skill|hook|agent|llm|prompt)" \
  > /tmp/ai_commits_filtered.txt

# Count AI-config commits per month
git -C {repo_path} log --format="%ad %H" --date=format:"%Y-%m" | \
  while read month hash; do
    if grep -q "$hash" /tmp/ai_commits_filtered.txt; then
      echo "$month"
    fi
  done | sort | uniq -c

More direct alternative:

git -C {repo_path} log --format="%ad %s" --date=format:"%Y-%m" | \
  grep -iE " (feat|fix|docs|tech|chore|refactor)\(ai\)|claude|mcp.*server|\.claude/|skill|hook.*security|guardrail" | \
  awk '{print $1}' | sort | uniq -c

Compute per month:

• AI-config commit count
• % of monthly total (cross-reference with all-category monthly total)
• Context (if notable period)

Build ASCII distribution chart (horizontal or vertical bars).

---

Step 4: Section

<!-- truncated -->