Index of every page on this site: llms.txt
All skills
shubhamsaboo avatar

/commit-archaeologist

@14c5f8f
Run it yourself

Reconstructs why code exists from local git history, including the introducing commit, later changes, current authors, repeated companion files, and likely intent. Use when the user asks "why does this code exist", "who wrote this function and why", or to "explain the history of this function" before a rewrite, refactor, or risky edit. Runs entirely locally.

Use this Skill: https://skilld.dev/gh/shubhamsaboo/awesome-llm-apps/commit-archaeologist

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

README.md

≈586 tokens on demand. Your agent reads this file only when SKILL.md points to it.

🏺 Commit Archaeologist Agent Skill

git blame tells you who last changed a line. Commit Archaeologist reconstructs why the line exists.

Point it at a tracked file and an optional line range. Its local Python script finds the introducing commit, orders later modifications, classifies commit messages, summarizes current authorship, detects repeatedly co-changed files, and flags issue references, reverts, workarounds, temporary choices, and TODOs. The agent turns that evidence into a readable history and a change-risk note.

demo

Install

npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/agent_skills/commit-archaeologist

The skills CLI installs the folder for compatible coding agents. You can also copy this directory into an agent's skills directory.

Run

Ask your agent:

Why does src/cache.py lines 40-72 exist, and what should I know before I change it?

Or run the deterministic core from a clone of this repository:

python3 agent_skills/commit-archaeologist/scripts/archaeologist.py \
  /path/to/repo src/cache.py --lines 40-72 --json

Omit --lines to follow the entire file history. Omit --json for a compact terminal summary.

Output

The JSON dig report contains:

  • the normalized region, historical path aliases, and co-change threshold
  • the introducing commit
  • an oldest-to-newest timeline with changed files and intent categories
  • repeated co-changes and their supporting commits
  • current blamed-line counts alongside historical commit counts
  • intent signals grounded in commit subjects and bodies

Everything runs locally with Python's standard library and git. The script is read-only and makes no network calls.

Verify

python3 agent_skills/evals/commit-archaeologist/test_archaeologist.py

The eval builds its own temporary repository and checks ordering, co-changes, authorship, intent signals, deterministic JSON, and validation errors.

Files

commit-archaeologist/
|-- SKILL.md
|-- README.md
|-- scripts/archaeologist.py
`-- references/reading-git-history.md

Part of awesome-llm-apps. Apache-2.0. Last verified: July 2026.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts16d3 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    This skill provides a tool to analyze local git history to explain code changes. It executes git commands through a Python script with robust path validation and argument handling. The skill has a low risk of indirect prompt injection due to its processing of untrusted repository commit history, which is addressed by providing specific interpretation guidelines for the agent.

  • Socket1mo

    No alerts

  • Snyk16d

    Risk: LOW · No issues

Signed by skilld at 14c5f8f. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 4 months ago
Other metadata
metadata
{
  "author": "Matt Van Horn",
  "version": "1.0.0",
  "source": "https://github.com/Shubhamsaboo/awesome-llm-apps"
}

README badge

README badge for shubhamsaboo/awesome-llm-apps/commit-archaeologist