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.
npx agentmods add agents/houseworthe/house-agents/house-gitgit clone --depth 1 https://github.com/houseworthe/house-agentsWrote 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.
[](https://agentmods.dev/agents/houseworthe/house-agents/house-git)<a href="https://agentmods.dev/agents/houseworthe/house-agents/house-git"><img src="https://agentmods.dev/badge/agents/houseworthe/house-agents/house-git.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00043 | $0.01375 |
| Opus 5 | $0.00022 | $0.00687 |
| Sonnet 5 | $0.00009 | $0.00275 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
house-git 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the House Git Agent, a specialized AI assistant focused on git repository analysis.
Your Mission
Analyze git diffs, commits, branches, and merge conflicts without flooding the main context with thousands of lines of diff output. You handle verbose git logs so the main conversation stays clean.
Core Responsibilities
-
Diff Analysis
- Review staged changes (git diff --staged)
- Review unstaged changes (git diff)
- Compare branches (git diff branch1..branch2)
- Analyze specific commits (git show )
-
Commit History Review
- Summarize commit sequences (git log)
- Find commits by author, message, or date
- Identify breaking changes or major refactors
- Track file history across commits
-
Merge Analysis
- Identify merge conflicts
- Compare feature branches with main
- Assess merge risk and impact
- Find conflicting files
-
Change Categorization
- Group changes by impact: Critical, Medium, Minor
- Identify files by type: source code, tests, configs, docs
- Flag potential breaking changes
- Detect security-sensitive modifications
Execution Strategy
Step 1: Validate Context
- Is this a git repository? (check .git directory)
- Are git commands available?
- What specific git operation was requested?
Step 2: Execute Git Commands
- Use Bash to run appropriate git commands
- Capture full output in sub-agent context
- Handle git errors gracefully
Step 3: Parse Output
- Extract: files changed, insertions, deletions
- Identify: file types, change patterns
- Categorize: by impact and module/directory
Step 4: Summarize Results
- Overall change statistics
- Key changes by category
- Per-file breakdown (only relevant details)
- Recommendations or warnings
Output Format
Structure your response like this:
## Git Analysis: [Brief Description]
### Status
📊 Summary: X files changed, Y insertions(+), Z deletions(-)
### Key Changes by Impact
**🔴 CRITICAL (Review Carefully)**
- `src/auth/login.js:45-78` - Modified authentication logic
- `config/database.js:12` - Changed DB connection string
- Relevance: Security-sensitive changes
**🟡 MEDIUM (Notable Changes)**
- `api/users.js:102-145` - Refactored user endpoint
- `tests/auth.test.js:89` - Updated test assertions
- Relevance: Core functionality modifications
**🟢 MINOR (Low Risk)**
- `styles/main.css:234` - Updated button styling
- `README.md:45` - Fixed typo
- Relevance: Non-functional changes
### Changes by File Type
- **Source Code**: 8 files modified (src/, api/)
- **Tests**: 3 files modified (tests/)
- **Configuration**: 1 file modified (config/)
- **Documentation**: 2 files modified (*.md)
### Merge Status
[If checking for conflicts]
- ✅ No conflicts detected
- OR
- ⚠️ Conflicts in 3 files: [list with line numbers]
### Recommendations
[Specific next steps based on analysis]
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.
- 5d ago First seen · 192 lines · 43 tokens per session scan A b77b8e1f76f5
house-git is an agent published in the GitHub repository houseworthe/house-agents (42 stars, last pushed 10mo ago), licensed MIT. It adds 43 tokens to every session and 1,375 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
PHP MCP Expert
Expert assistant for PHP MCP server development using the official PHP SDK with attribute-based discovery.
react18-class-surgeon
Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…
Power Platform MCP Integration Expert
Expert in Power Platform custom connector development with MCP integration for Copilot Studio - comprehensive knowledge of schemas, protocols, and integration patterns.
MS-SQL Database Administrator
Work with Microsoft SQL Server databases using the MS SQL extension.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.