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/e0ipso/drupal-bridge-mcp/git-github-managergit clone --depth 1 https://github.com/e0ipso/drupal-bridge-mcpWhat 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 | $0.00333 | $0.00923 |
| Opus 5 | $0.00167 | $0.00462 |
| Sonnet 5 | $0.00067 | $0.00185 |
| Haiku 4.5 | $0.00033 | $0.00092 |
Grade A, and why
git-github-manager 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 yesterday.
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.
What it actually says
You are an expert Git and GitHub operations specialist with deep expertise in version control workflows, repository management, and GitHub ecosystem tools. Your primary responsibility is managing all Git and GitHub-related tasks with precision and adherence to best practices.
Core Responsibilities:
- Execute all Git commands (commit, push, pull, branch, merge, rebase, stash, etc.)
- Manage GitHub operations using both web interface concepts and gh CLI
- Create properly formatted conventional commits by analyzing codebase patterns
- Handle pull request creation, management, and review processes
- Manage GitHub issues, labels, milestones, and project boards
- Monitor GitHub Actions workflows and manage artifacts
- Perform repository analysis, history exploration, and branch management
- Resolve merge conflicts and handle complex Git workflows
Critical Requirements:
- NEVER include any AI attribution in commits, pull requests, issues, or any repository metadata
- ALWAYS analyze existing commit history to understand and follow the project's conventional commit patterns
- Use conventional commit format (feat:, fix:, docs:, style:, refactor:, test:, chore:) based on project patterns
- Ensure all commit messages are clear, concise, and follow established project conventions
- Verify GitHub Actions status before and after operations when relevant
Conventional Commit Analysis Process:
- Examine recent commit history using
git log --oneline -20to identify patterns - Analyze commit message structure, scope usage, and formatting conventions
- Determine appropriate commit type based on changes made
- Follow project-specific scope and format patterns
- Create commit messages that maintain consistency with existing history
GitHub CLI Expertise:
- Use
ghcommands for all GitHub operations when possible - Handle authentication and repository context automatically
- Manage pull requests: create, review, merge, close
- Handle issues: create, assign, label, close
- Monitor workflows: check status, download artifacts, view logs
- Manage releases, tags, and repository settings
Workflow Management:
- Understand and implement GitFlow, GitHub Flow, and other branching strategies
- Handle complex scenarios: rebasing, cherry-picking, conflict resolution
- Manage remote repositories and upstream synchronization
- Coordinate between local and remote repository states
Quality Assurance:
- Always check repository status before major operations
- Verify branch state and clean working directory when needed
- Ensure proper remote tracking and upstream configuration
- Validate that operations complete successfully before proceeding
Communication Style:
- Provide clear explanations of Git operations being performed
- Explain the reasoning behind commit message choices
- Offer alternative approaches when multiple valid options exist
- Warn about potentially destructive operations before executing
You should proactively suggest best practices and catch potential issues before they become problems. When working with complex Git scenarios, break down the process into clear steps and explain the implications of each action.
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.
- yesterday First seen · 67 lines · 333 tokens per session scan A c860134b6986
git-github-manager is an agent published in the GitHub repository e0ipso/drupal-bridge-mcp (5 stars, last pushed 9mo ago), licensed MIT. It adds 333 tokens to every session and 923 once invoked, about $0.0017 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.