team_analytics

team_analytics is a command for coding agents from yonggao/claude-plugins. It costs 18 tokens per session (980 once invoked), scanned A, original, MIT.

A command for examining Git history across multiple repositories, which are folders containing tracked project code.

In plain words
What is it for?
Finding repositories, checking their current status and branches, counting recent commits, comparing developer contributions, and reviewing collaboration or repository health.
Why use it?
It gathers activity and contribution information in one review instead of requiring developers to inspect each repository separately.

Command

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.

agentmods
npx agentmods add commands/yonggao/claude-plugins/team_analytics
Clone the repo
git clone --depth 1 https://github.com/yonggao/claude-plugins

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 team_analytics

README.md
[![agentmods](https://agentmods.dev/badge/commands/yonggao/claude-plugins/team_analytics.svg)](https://agentmods.dev/commands/yonggao/claude-plugins/team_analytics)
Your own site
<a href="https://agentmods.dev/commands/yonggao/claude-plugins/team_analytics"><img src="https://agentmods.dev/badge/commands/yonggao/claude-plugins/team_analytics.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 980 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.00980
Opus 5 $0.00009 $0.00490
Sonnet 5 $0.00004 $0.00196
Haiku 4.5 $0.00002 $0.00098

Measured 3d ago against content hash d8afdd2a99e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

team_analytics 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 3d ago.

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.

commands/team_analytics.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team Git Analytics

Analyze the git commit history across all repositories in the current directory to understand team activity patterns, individual developer contributions, performance metrics, and working areas.

Analysis Parameters

  • Time Period: $ARGUMENTS (default: "90 days ago" if not specified)
  • Scope: All subdirectories containing git repositories
  • Focus: Developer-specific metrics, collaboration patterns, repository health

Execution Instructions

Please perform a comprehensive git analysis following these steps:

1. Repository Discovery

First, discover all git repositories in the current directory and subdirectories:

find . -maxdepth 2 -name ".git" -type d

Then list the subdirectories to identify repositories:

ls -la

2. Data Collection Phase

For each repository directory found, navigate to it and collect detailed git data using the time period: $ARGUMENTS (or "90 days ago" if no arguments provided).

For each repository, execute these git commands:

Basic repository info:

git status
git branch --show-current

Commit statistics:

git rev-list --count --since="90 days ago" HEAD
git shortlog --since="90 days ago" -sne

Detailed commit history:

git log --since="90 days ago" --pretty=format:"%H|%an|%ae|%ad|%s" --date=iso

File change statistics:

git log --since="90 days ago" --numstat --pretty=format:"%an|%ad" --date=short

Most active files:

git log --since="90 days ago" --name-only --pretty=format:

Author activity:

git log --since="90 days ago" --pretty=format:"%an"

3. Analysis Instructions

Based on the collected git data from all repositories, provide a comprehensive analysis including:

Developer Profiles (per individual):
  • Commit Activity: Total commits, commit frequency, timeline patterns
  • Code Changes: Lines added/deleted, net contribution, change velocity
  • Working Areas: Primary files/directories worked on, specialization areas
  • Collaboration: Cross-repository contributions, patterns across repos
  • Commit Patterns: Timing patterns, commit message analysis, work categorization

Read the full file on GitHub · 162 lines

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. 3d ago First seen · 162 lines · 18 tokens per session scan A d8afdd2a99e6

Subscribe to this mod's changes

team_analytics is a command published in the GitHub repository yonggao/claude-plugins (2 stars, last pushed 8mo ago), licensed MIT. It adds 18 tokens to every session and 980 once invoked, about $0.0001 per session on Opus 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.