agentmods.dev

git:conflicts

git:conflicts is a skill for Claude Code from bendrucker/claude. It costs 41 tokens per session (847 once invoked), scanned A, original, MIT.

A skill for resolving conflicts when Git cannot combine changes during a rebase, merge, or cherry-pick. It shows the common ancestor, your version, and the incoming version so the correct result can be chosen.

In plain words
What is it for?
Use it to inspect conflict state, compare the three versions of a file, edit and stage the merged result, regenerate conflicted generated files, and finish or push the operation when requested.
Why use it?
It makes conflicting changes easier to compare and helps prevent silently losing work from either side. It also provides status and upstream context during the operation.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the git plugin — 1 skill shipped together

not rated 18repo changed 6d ago A scan 41 tokens original MIT

Good fit Use it to inspect conflict state, compare the three versions of a file, edit and stage the merged result, regenerate conflicted generated files, and finish or push the operation when requested.

Compare 6 skills from other repositories ↓
View source ↗ bendrucker/claude
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add bendrucker/claude
Claude Code
/plugin install git

Made for: Claude Code.

Or install git, the plugin that ships this one along with the rest of its 1 skill.

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:conflicts

README.md
[![agentmods](https://agentmods.dev/badge/skills/bendrucker/claude/conflicts/github.svg)](https://agentmods.dev/skills/bendrucker/claude/conflicts)
Your own site
<a href="https://agentmods.dev/skills/bendrucker/claude/conflicts"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/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 git:conflicts

Your own site · 80×15
<a href="https://agentmods.dev/skills/bendrucker/claude/conflicts"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/conflicts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 847 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 $0.00041 $0.00847
Opus 5.5 $0.00016 $0.00339
Sonnet 5.5 $0.00008 $0.00169
Haiku 4.5 $0.00004 $0.00085

Measured 6d ago against content hash cbd236d7a3a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git: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 6d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/check-markers.ts, scripts/context.ts, scripts/status.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/git/skills/conflicts/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Conflicts

Status

!bun ${CLAUDE_PLUGIN_ROOT}/skills/conflicts/scripts/status.ts

Context

!bun ${CLAUDE_PLUGIN_ROOT}/skills/conflicts/scripts/context.ts

Upstream

!bun ${CLAUDE_PLUGIN_ROOT}/skills/conflicts/scripts/upstream.ts

Resolving

Resolve each conflicted file, then git add it.

  • Regenerate a generated file, such as a lockfile or a build artifact, from its source. Follow the project's CLAUDE.md for lockfile guidance.
  • When repeated rebases hit the same conflict, references/rerere.md records a resolution and replays it.

Resolving is done when every conflicted file is staged and git diff --cached --check reports no conflict markers. Leave the commit, the continue, and the push to the user.

Completing the Operation

Take the operation past the staged resolution only when the user asks for it: the --push argument, its alias push, or a request such as "fix conflicts and push". Then:

  1. When no rebase, merge, or cherry-pick is in progress and upstream has diverged, run git merge origin/<default-branch> to produce the conflicts. A clean merge goes straight to the push.
  2. Before continuing, set aside the dirty files unrelated to the resolution, which git status --porcelain lists. The continue then commits only the resolution. Run git stash push -m "conflicts: <branch>" -- <files> for all of them at once, then record that entry's SHA from git stash list --format='%H %gs'. When that stash fails, which the sandbox causes by blocking the unlink of a protected file such as .mcp.json, stash the files one at a time and skip the failures. Hide each file that cannot be stashed with git update-index --assume-unchanged <file>.
  3. Continue the operation and run git push, with --force-with-lease after a rebase, then restore the files you set aside: git update-index --no-assume-unchanged <file> for each hidden file, and git stash apply <sha> then git stash drop <sha> for a stash you created. Restore by the SHA you recorded, because the stash stack is shared with every other worktree on the repo and the top entry may belong to another session.

Read the full file on GitHub · 66 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago Changed · -3 lines cbd236d7a3a1
  2. 10d ago Changed · -12 lines 9a48cdda162b
  3. 1mo ago Changed · +1 lines 8ebb20182354
  4. 1mo ago Changed · -5 lines · -6 tokens per session 2234dcb62e8d
  5. 2mo ago First seen · 85 lines · 47 tokens per session scan A 4b5c342cdd8c

Subscribe to this mod's changes

git:conflicts is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 847 once invoked, about $0.0002 per session on Opus 5.5. 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.

Claude CodeGit and workflowclaude-code-plugin
Related

git:conflicts compared with skills from other repositories

git:conflicts next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
git:conflictsbendrucker/claudeSkill18todayMITA41Claude Code
update-prReflexioAI/claude-smartSkill7932d agoApache-2.0A71Claude Code, Codex
glabNikiforovAll/claude-code-rulesSkill1427d agoApache-2.0A59Claude Code
deploy-landedavelikiy/great_ctoSkill113todayMITA103Claude Code
commitsuxrobGM/jobpilotSkill111todayMITA38Claude Code
check-prdoodledood/manifest-devSkill78todayMITA77Claude Code
babysit-prdoodledood/manifest-devSkill78todayMITA59Claude Code