resolve-conflicts

resolve-conflicts is a command for Claude Code from smrafiz/claude-supercharger. It costs 0 tokens per session (522 once invoked), scanned A, original, MIT.

A guided process for handling conflicts when Git cannot combine changes from different branches, a merge, rebase, or cherry-pick.

In plain words
What is it for?
Use it during an in-progress conflict to inspect the repository state, understand each side's intent, resolve each file, and finish the operation correctly.
Why use it?
It helps preserve the purpose of both sets of changes instead of resolving conflicting lines by guesswork.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the supercharger plugin — 37 commands, 10 agents, 28 hooks shipped together

Good fit Use it during an in-progress conflict to inspect the repository state, understand each side's intent, resolve each file, and finish the operation correctly.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/smrafiz/claude-supercharger/resolve-conflicts
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.

Clone the repo
git clone --depth 1 https://github.com/smrafiz/claude-supercharger

Made for: Claude Code.

Or install supercharger, the plugin that ships this one along with the rest of its 37 commands, 10 agents, 28 hooks.

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 resolve-conflicts

README.md
[![agentmods](https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/resolve-conflicts/github.svg)](https://agentmods.dev/commands/smrafiz/claude-supercharger/resolve-conflicts)
Your own site
<a href="https://agentmods.dev/commands/smrafiz/claude-supercharger/resolve-conflicts"><img src="https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/resolve-conflicts/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for resolve-conflicts

Your own site · 80×15
<a href="https://agentmods.dev/commands/smrafiz/claude-supercharger/resolve-conflicts"><img src="https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/resolve-conflicts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 522 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00522
Opus 5 $0.00000 $0.00261
Sonnet 5 $0.00000 $0.00104
Haiku 4.5 $0.00000 $0.00052

Measured 9d ago against content hash 0b8aac27bed2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 9d 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.

commands/resolve-conflicts.md · 43 lines

What it actually says

Resolve an in-progress merge or rebase conflict. Context: $ARGUMENTS

Step 1 — See the actual state Run git status and git diff --name-only --diff-filter=U for the conflicted files. Identify whether this is a merge, a rebase, or a cherry-pick — the finish step differs.

Step 2 — Recover the intent behind each side For every conflicted file, find out why each side changed. git log --merge -p <file> shows the commits that touched it on both branches; read their messages, and the PR or issue if the message points at one.

Resolving without this is guessing. A conflict is two intentions colliding, and you cannot preserve an intention you never read.

Step 3 — Resolve each hunk

  • Preserve both intents wherever they compose.
  • Where they genuinely conflict, keep the one matching the stated goal of this merge and say which trade-off you made and why.
  • Do not invent behaviour that was on neither side. A conflict is not a licence to redesign — that change belongs in its own commit where it can be reviewed.
  • Never git merge --abort to escape a hard conflict unless the user asks. Aborting discards the resolution work and the next attempt starts from the same place.
  • Delete every marker. Grep for <<<<<<<, =======, >>>>>>> before continuing — a committed marker is a broken build that git will not warn you about.

Step 4 — Verify against the project's own checks Discover them rather than assuming: look at package.json scripts, Makefile, .github/workflows/, justfile. Run typecheck, then tests, then formatter — in that order, since a type error makes test failures unreadable.

A conflict resolution that compiles is not correct. It is the minimum bar for finding out whether it is correct.

Step 5 — Finish Stage the resolved files and complete the operation: git commit for a merge, git rebase --continue for a rebase (repeating until every commit is replayed), git cherry-pick --continue for a cherry-pick.

Step 6 — Report State which files conflicted, what you kept from each side, and every trade-off made. If any resolution was a judgement call rather than a clear merge, say so explicitly — that is the part the user needs to check.

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. 9d ago First seen · 43 lines · 0 tokens per session scan A 0b8aac27bed2

Subscribe to this mod's changes

resolve-conflicts is a command published in the GitHub repository smrafiz/claude-supercharger (11 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 522 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.