- Home
- Skills
- Code Quality & Review
- Git History Analyzer
Works with the AI Agents you already use
Git History Analyzer
Extract engineering metrics, bus factor risks, and code hotspots from git history.
$1.99
Git History Analyzer
Example session with this skill installed
Run a git history analysis for the last 6 months on the src/ directory and identify hotspots and bus factor risks.
- Read your context and instructions
- Compiled the git history analyzer
- Generated the data export
I have analyzed the git history for src/ over the past 6 months. The analysis processed 452 commits from 8 authors, identifying 3 high-risk hotspots and 2 files with a bus factor of 1.
Repository Health Report (src/)
| Metric | Value | Risk Level |
|---|---|---|
| Top Hotspot | src/auth/provider.ts | High (42 changes) |
| Highest Churn | src/api/endpoints.ts | Medium (+1,200 / -850) |
| Bus Factor (Total) | 3 | Medium |
| Temporal Coupling | src/utils/db.ts & src/models/user.ts | 85% correlation |
Key Findings
Knowledge Silo: src/auth/provider.ts is 92% owned by dev-alpha. If this contributor is unavailable, the authentication logic has zero redundancy.
Architectural Debt: src/utils/db.ts and src/models/user.ts are coupled. 17 out of 20 commits to the utility file required a simultaneous change to the user model, suggesting a leaky abstraction.
Bug Hotspot: src/api/endpoints.ts shows high churn with a fix-to-feature commit ratio of 0.6, indicating frequent regressions.
Next steps
- Review the
insights/bus_factor.csvfor a full list of single-owner files. - Consider a pair-programming session for
src/auth/to distribute knowledge. - Refactor
src/utils/db.tsto decouple it from the user model.
bus_factor.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Engineering managers and leads often struggle to identify technical debt and bus factor risk until a developer leaves or a deployment fails. This skill mines git logs to transform raw commit history into actionable repository health metrics.
What it does
- Hotspot detection identifies files with high change frequency that are likely candidates for refactoring.
- Bus factor analysis calculates line ownership per file to surface single-point-of-failure risks.
- Temporal coupling finds hidden dependencies by tracking files that are frequently committed together.
- Churn tracking measures the ratio of lines added versus deleted to monitor codebase stability.
- Author distribution maps knowledge silos across directories based on commit volume and recency.
How it works
- Targeting specifies the time range or specific subdirectories to analyze within the local repository.
- Extraction runs the analysis engine to parse git logs, blame data, and commit metadata.
- Reporting generates a Markdown summary of hotspots, risks, and activity trends.
- Data Export produces CSV files for deeper analysis in external spreadsheet or visualization tools.
Frameworks & tools
This skill utilizes git CLI, python3, and standard shell utilities to process repository metadata.
Why this beats prompting it yourself
Standard LLM prompts cannot access the full history of a local repository or perform complex statistical aggregations on thousands of commits. This skill automates the heavy lifting of git log parsing and applies specific logic to calculate metrics like bus factor and temporal coupling accurately.
Use cases
- Auditing a legacy codebase to find the most bug-prone modules for refactoring.
- Assessing team knowledge distribution before a major organizational change.
- Identifying hidden architectural dependencies that cause regression errors.
- Onboarding new developers by showing them which files are high-activity hotspots.
Known limitations
Requires a local git repository and Python 3. Accuracy of author metrics depends on consistent git mailmap configurations.
Requires a local git repository and Python 3. Analysis accuracy depends on git mailmap consistency for author aliasing.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago