git-stats

git-stats is a skill for Claude Code from shippy/personal-intelligence-kit. It costs 30 tokens per session (625 once invoked), scanned A, original, MIT.

A skill that collects Git commit history from configured folders and stores it in a database. Git commits are saved records of changes made to a code project.

In plain words
What is it for?
Use it to count commits, lines added or removed, activity by repository, and commits made with Claude as a co-author.
Why use it?
It removes the need to inspect many repositories manually when checking coding activity or contributions.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

Good fit Use it to count commits, lines added or removed, activity by repository, and commits made with Claude as a co-author.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shippy/personal-intelligence-kit/git-stats
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add shippy/personal-intelligence-kit --skill git-stats
Clone the repo
git clone --depth 1 https://github.com/shippy/personal-intelligence-kit

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for git-stats

README.md
[![agentmods](https://agentmods.dev/badge/skills/shippy/personal-intelligence-kit/git-stats/github.svg)](https://agentmods.dev/skills/shippy/personal-intelligence-kit/git-stats)
Your own site
<a href="https://agentmods.dev/skills/shippy/personal-intelligence-kit/git-stats"><img src="https://agentmods.dev/badge/skills/shippy/personal-intelligence-kit/git-stats/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for git-stats

Your own site · 80×15
<a href="https://agentmods.dev/skills/shippy/personal-intelligence-kit/git-stats"><img src="https://agentmods.dev/badge/skills/shippy/personal-intelligence-kit/git-stats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 625 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00625
Opus 5.5 $0.00012 $0.00250
Sonnet 5.5 $0.00006 $0.00125
Haiku 4.5 $0.00003 $0.00063

Measured 1mo ago against content hash 28689cf024f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git-stats scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (ingest.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

template/.claude/skills/git-stats/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit Stats

Tracks commit activity across git repositories in configured superdirectories, with per-directory author filtering and co-author (Claude) detection.

Running the Ingest

# From the vault root directory:
uv run .claude/skills/git-stats/ingest.py              # Last 7 days (default)
uv run .claude/skills/git-stats/ingest.py --since 2026-03-01
uv run .claude/skills/git-stats/ingest.py --since 2026-03-01 --until 2026-04-01
uv run .claude/skills/git-stats/ingest.py --all         # Full history

Configuration

The git source is configured in vault.toml under [sources.git]. Each scope maps a parent directory to the committer email(s) to track:

[sources.git]
enabled = true

[[sources.git.scopes]]
path = "~/Documents"
authors = ["[email protected]"]

[[sources.git.scopes]]
path = "~/Work"
authors = ["[email protected]"]

Querying the Data

The ingest writes to data/git-commits.db. Useful queries:

-- Commits per repo (last 7 days)
SELECT repo, COUNT(*) as commits, SUM(insertions) as added, SUM(deletions) as removed
FROM commits WHERE date >= date('now', '-7 days')
GROUP BY repo ORDER BY commits DESC;

-- Co-authorship rate (how many commits were made with Claude)
SELECT
    COUNT(*) as total,
    COUNT(ca.commit_hash) as co_authored,
    ROUND(COUNT(ca.commit_hash) * 100.0 / COUNT(*), 1) as pct
FROM commits c
LEFT JOIN co_authors ca ON c.hash = ca.commit_hash
WHERE c.date >= date('now', '-7 days');

-- Co-author breakdown
SELECT ca.name, COUNT(*) as commits
FROM co_authors ca
JOIN commits c ON ca.commit_hash = c.hash
WHERE c.date >= date('now', '-30 days')
GROUP BY ca.name ORDER BY commits DESC;

-- Daily commit volume
SELECT DATE(date) as day, COUNT(*) as commits,
       SUM(insertions) as added, SUM(deletions) as removed
FROM commits WHERE date >= date('now', '-30 days')
GROUP BY day ORDER BY day;

-- Repos by scope
SELECT scope, repo, COUNT(*) as commits
FROM commits WHERE date >= date('now', '-7 days')
GROUP BY scope, repo ORDER BY scope, commits DESC;

Read the full file on GitHub · 78 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 78 lines · 30 tokens per session scan A 28689cf024f0

Subscribe to this mod's changes

git-stats is a skill published in the GitHub repository shippy/personal-intelligence-kit (14 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 625 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.