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.
npx agentmods add skills/bendrucker/claude/conflictsnpx skills add bendrucker/claude --skill conflictsgit clone --depth 1 https://github.com/bendrucker/claudeWhat 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 | $0.00047 | $0.00988 |
| Opus 5 | $0.00023 | $0.00494 |
| Sonnet 5 | $0.00009 | $0.00198 |
| Haiku 4.5 | $0.00005 | $0.00099 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 85 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
Three-Way Access
Git stores three versions in staging slots during a conflict:
| Slot | Version | Command |
|---|---|---|
:1:path |
Base (common ancestor) | git show :1:path |
:2:path |
Ours (HEAD) | git show :2:path |
:3:path |
Theirs (incoming) | git show :3:path |
Resolving
For each conflicted file:
- Read the three slots above to understand base, ours, and theirs.
- Edit the file to produce the correct merged result, then
git addit. - For generated files (lockfiles, build artifacts), delete and regenerate rather than merge by hand. Follow the project's
CLAUDE.mdfor lockfile-specific guidance. - Never silently drop either side. When in doubt, keep both and ask.
- If a conflict is in a file you don't understand, ask rather than guess.
Committing and Pushing
This step runs only when you are asked to take the operation to completion: the --push argument (its alias push), or a request like "fix conflicts and push". By default, on auto-activation or when asked only to resolve, stop after git add and do not commit, continue, or push.
When driving to completion:
- Initiate the merge if needed. If no rebase, merge, or cherry-pick is in progress but upstream has diverged, run
git merge origin/<default-branch>to surface conflicts. If it merges cleanly, push and finish. - Assess complexity before resolving.
- Simple (generated files only, or fewer than 3 conflicts across 1-2 files with obvious resolutions): proceed.
- Complex (3+ files, non-trivial code, or ambiguous intent): summarize the conflicts and confirm with the user via
AskUserQuestionbefore resolving.
- Resolve per the section above.
- Stash unrelated dirty files. Check
git status --porcelainfor unstaged changes beyond the resolved conflicts. Trygit stash push -m "conflicts: temp" -- <files>for all of them at once. If the stash fails (the sandbox may block unlinking protected files like.mcp.json), stash individually and skip failures. For files that cannot be stashed, hide them withgit update-index --assume-unchanged <file>. - Continue the operation with
git rebase --continue,git merge --continue, orgit cherry-pick --continue. - Push and restore. Run
git push, then restore hidden files withgit update-index --no-assume-unchanged <file>andgit stash popif anything was stashed.
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.
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 · 85 lines · 47 tokens per session scan A 4b5c342cdd8c
git:conflicts is a skill published in the GitHub repository bendrucker/claude (16 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 988 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…