roo-resolve-conflicts

A procedure for resolving merge conflicts in a pull request by examining the conflicting code and its Git history. Merge conflicts happen when two changes modify the same parts of a file in incompatible ways.

In plain words
What is it for?
Use it to fetch a pull request, rebase it, identify conflicts, inspect blame and commit messages, and combine or select changes according to their intent.
Why use it?
It uses who changed each section and why they changed it to guide a resolution instead of choosing one side blindly.

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/zgsm-ai/costrict/roo-resolve-conflicts
Clone the repo
git clone --depth 1 https://github.com/zgsm-ai/costrict
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 445 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00008 $0.00445
Opus 5 $0.00004 $0.00222
Sonnet 5 $0.00002 $0.00089
Haiku 4.5 $0.00001 $0.00044

Measured yesterday against content hash 24dd17ed9159, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

roo-resolve-conflicts 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.

Origin

This is a copy

100% identical to roo-resolve-conflicts — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.roo/commands/roo-resolve-conflicts.md · 75 lines

What it actually says

Resolve merge conflicts for a specific pull request by analyzing git history, commit messages, and code changes to make intelligent resolution decisions.

Quick Start

  1. Provide a PR number (e.g., #123 or just 123)

  2. The workflow will automatically:

    • Fetch PR information (title, description, branches)
    • Checkout the PR branch
    • Rebase onto the target branch to reveal conflicts
    • Analyze and resolve conflicts using git history

Workflow Steps

1. Initialize PR Resolution

# Fetch PR info
gh pr view [PR_NUMBER] --json title,body,headRefName,baseRefName

# Checkout and rebase
gh pr checkout [PR_NUMBER] --force
git fetch origin main
GIT_EDITOR=true git rebase origin/main

2. Identify Conflicts

git status --porcelain | grep "^UU"

3. Analyze Each Conflict

For each conflicted file:

  • Read the conflict markers
  • Run git blame on conflicting sections
  • Fetch commit messages for context
  • Determine the intent behind each change

4. Apply Resolution Strategy

Based on the analysis:

  • Bugfixes generally take precedence over features
  • Recent changes are often more relevant (unless older is a security fix)
  • Combine non-conflicting changes when possible
  • Preserve test updates alongside code changes

5. Complete Resolution

git add [resolved-files]
GIT_EDITOR=true git rebase --continue

Key Guidelines

  • Always escape conflict markers with \ when using apply_diff
  • Document resolution decisions in the summary
  • Verify no syntax errors after resolution
  • Preserve valuable changes from both sides when possible

Examples

  • /roo-resolve-conflicts #123 - Resolve conflicts for PR #123
  • /roo-resolve-conflicts 456 - Resolve conflicts for PR #456
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. yesterday First seen · 75 lines · 8 tokens per session scan A 24dd17ed9159

Subscribe to this mod's changes

roo-resolve-conflicts is a command published in the GitHub repository zgsm-ai/costrict (4,397 stars, last pushed 13d ago), licensed Apache-2.0. It adds 8 tokens to every session and 445 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to roo-resolve-conflicts, differing in 10 lines, and is treated as a copy.