What is resolve-conflicts?

A command for fixing merge conflicts on an open GitHub pull request by merging the target branch into the proposed changes in a separate Git worktree. It can handle conflicts in JSON and Markdown files.

Use it when a GitHub pull request cannot be merged because its branch is out of date or conflicts with the target branch.

It avoids resolving conflicts directly in your main checkout and provides checks for the pull request and required GitHub tools.

resolve-conflicts — Command by sanmak

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/sanmak/specops/resolve-conflicts

Clone the repo

git clone --depth 1 https://github.com/sanmak/specops

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,326 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.03326
Opus 5	$0.00000	$0.01663
Sonnet 5	$0.00000	$0.00665
Haiku 4.5	$0.00000	$0.00333

Measured 2d ago against content hash 098615a85a35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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/commands/resolve-conflicts.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resolve merge conflicts on a GitHub PR by merging the base branch into the PR branch in an isolated git worktree, with JSON/markdown-aware conflict resolution.

Instructions

Follow these steps precisely. Do NOT add a Co-Authored-By line to commits.

Argument Parsing

Parse $ARGUMENTS for a PR number (e.g., 56).

If empty, try auto-detection: gh pr view --json number -q .number 2>/dev/null. If auto-detection fails, ask the user "Which PR number should I resolve conflicts for?" and wait for their response.

Step 1: Pre-flight checks

GitHub CLI available: Run gh --version. If unavailable, tell the user "GitHub CLI (gh) is required. Install with: brew install gh" and stop.
PR exists, is open, and is conflicting: Run gh pr view <PR_NUMBER> --json number,state,headRefName,baseRefName,title,mergeable. If the PR does not exist or is not open, report the error and stop. If mergeable is UNKNOWN, retry up to 5 times with 3-second waits — GitHub may still be computing the merge state. If mergeable remains UNKNOWN after retries, report "PR # mergeability is UNKNOWN after retries — try again shortly" and stop. If mergeable is not CONFLICTING (i.e., MERGEABLE), report "PR # has no merge conflicts (mergeable: )" and stop. Save headRefName as PR_BRANCH, baseRefName as BASE_BRANCH, title as PR_TITLE.
Extract owner/repo: Run gh repo view --json owner,name -q '.owner.login + "/" + .name'. Save as OWNER_REPO.
Working tree is clean: Run git status --porcelain. If there are uncommitted changes, tell the user "Working tree has uncommitted changes. Please commit or stash them first." and stop.
Clean stale worktree: Run git worktree list. If an entry exists with path .claude/worktrees/resolve-conflicts-<PR_NUMBER>, remove it with git worktree remove --force <path>. Only remove the worktree matching the current PR number — do NOT remove other worktrees, as they may belong to concurrent runs.

Read the full file on GitHub · 265 lines

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.

2d ago First seen · 265 lines · 0 tokens per session scan A 098615a85a35

Subscribe to this mod's changes

resolve-conflicts is a command published in the GitHub repository sanmak/specops (49 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,326 tokens. 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.

Git and workflow ai-coding claude claude-code codex copilot cursor

resolve-conflicts

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Instructions

Argument Parsing

Step 1: Pre-flight checks

What this file has done since we first saw it

Other commands, from other repositories

constitution

ijfw-execute

ijfw-metrics

analyze

review-pr

rea