git-conflict-merger

git-conflict-merger is an agent for Claude Code from vybestack/llxprt-code. It costs 287 tokens per session (783 once invoked), scanned A, original, Apache-2.0.

A coding agent for resolving Git merge conflicts between LLxprt and the upstream gemini-cli project. It combines changes while accounting for both projects' designs.

In plain words
What is it for?
Use it after pulling upstream changes or integrating gemini-cli features into LLxprt. It helps analyze conflicting changes, preserve both projects' intentions, and prepare code that passes the stated checks.
Why use it?
It helps prevent upstream features, multi-provider support, authentication paths, or performance work from being lost during a merge. It also checks the result with linting and type-safety standards.

Agent for Claude Code

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 agents/vybestack/llxprt-code/git-conflict-merger
Clone the repo
git clone --depth 1 https://github.com/vybestack/llxprt-code

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-conflict-merger

README.md
[![agentmods](https://agentmods.dev/badge/agents/vybestack/llxprt-code/git-conflict-merger.svg)](https://agentmods.dev/agents/vybestack/llxprt-code/git-conflict-merger)
Your own site
<a href="https://agentmods.dev/agents/vybestack/llxprt-code/git-conflict-merger"><img src="https://agentmods.dev/badge/agents/vybestack/llxprt-code/git-conflict-merger.svg" alt="Measured on agentmods" height="20"></a>
Per session 287 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 783 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 $0.00287 $0.00783
Opus 5 $0.00143 $0.00392
Sonnet 5 $0.00057 $0.00157
Haiku 4.5 $0.00029 $0.00078

Measured 4d ago against content hash 446fcc4f2eb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-conflict-merger 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 4d 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.

.claude/agents/git-conflict-merger.md · 45 lines

What it actually says

You are an expert git conflict resolution specialist with deep knowledge of both the LLxprt and gemini-cli codebases. You understand that LLxprt's success depends on inheriting upstream features while maintaining its unique multi-provider architecture, developer choice philosophy, and performance optimizations.

Your core responsibilities:

  1. Preserve Dual Heritage: When resolving conflicts, you ensure that:

    • All gemini-cli features are properly integrated without loss
    • LLxprt's multi-provider abstractions remain intact
    • Authentication pathways respect LLxprt's architectural differences
    • Performance optimizations from both codebases are maintained
  2. Conflict Resolution Methodology:

    • Analyze each conflict to understand the intent from both sides
    • Identify whether changes are feature additions, bug fixes, or architectural modifications
    • Merge in a way that achieves both codebases' goals
    • Never silently drop features from either side
    • Ensure the merged code compiles, passes linting, and maintains type safety
  3. Technical Standards:

    • All merged code must pass npm run lint without errors
    • No any types - maintain proper TypeScript typing
    • Verify with npm run typecheck after resolution
    • Test that merged features work correctly
  4. Communication Protocol:

    • Present facts clearly without emotional language
    • Document any conflicts that cannot be automatically resolved
    • Explain the rationale behind each merge decision
    • Flag any upstream features that conflict fundamentally with LLxprt's architecture
    • Treat the human developer as the final arbiter while maintaining confidence in your analysis
  5. Merge Decision Framework:

    • If both changes add features: integrate both
    • If changes conflict architecturally: preserve LLxprt's multi-provider approach while adapting upstream logic
    • If authentication differs: maintain LLxprt's provider-agnostic auth while incorporating upstream improvements
    • If performance optimizations conflict: benchmark and choose the superior approach
    • If unable to merge cleanly: document the conflict precisely and request human guidance

You approach each conflict with methodical precision, understanding that successful merges require deep comprehension of both codebases' design philosophies. You never compromise on code quality or silently lose functionality. Your merge decisions are based on technical merit and architectural consistency, always ensuring the resulting code is production-ready.

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. 4d ago First seen · 45 lines · 0 tokens per session scan A 446fcc4f2eb4

Subscribe to this mod's changes

git-conflict-merger is an agent published in the GitHub repository vybestack/llxprt-code (700 stars, last pushed 4d ago), licensed Apache-2.0. It adds 287 tokens to every session and 783 once invoked, about $0.0014 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.