Borrowing it
Nothing to install: this file belongs to G-Research/bobbit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/G-Research/bobbit/main/.claude/skills/resolve-pr-conflicts/SKILL.mdgit clone --depth 1 https://github.com/G-Research/bobbitWrote 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.
[](https://agentmods.dev/skills/g-research/bobbit/resolve-pr-conflicts)<a href="https://agentmods.dev/skills/g-research/bobbit/resolve-pr-conflicts"><img src="https://agentmods.dev/badge/skills/g-research/bobbit/resolve-pr-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.
<a href="https://agentmods.dev/skills/g-research/bobbit/resolve-pr-conflicts"><img src="https://agentmods.dev/badge/skills/g-research/bobbit/resolve-pr-conflicts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00031 | $0.00413 |
| Opus 5.5 | $0.00012 | $0.00165 |
| Sonnet 5.5 | $0.00006 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
resolve-pr-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 2mo 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.
What it actually says
Get a PR branch ready for merge by rebasing it onto the primary branch and resolving any conflicts.
Steps
- Determine the primary branch: run
git symbolic-ref refs/remotes/origin/HEADand extract the branch name. - Determine the PR branch:
- If $ARGUMENTS is provided, use that as the branch name.
- Otherwise, run
gh pr view --json headRefName -q .headRefNameto get the current PR's branch.
- Run
git fetch originto get the latest state. - Check out the PR branch:
git checkout <pr-branch> - Rebase onto the primary branch:
git rebase origin/<primary-branch> - If there are merge conflicts:
- For each conflicted file, read the file, understand both sides of the conflict, and resolve it intelligently — preserve the intent of both the PR changes and the upstream changes.
- After resolving each file,
git add <file>. - Run
git rebase --continue. Repeat if more conflicts arise.
- Run
npm run checkto verify the resolved code compiles. - If type-check fails, fix the issues and amend the last commit.
- Force-push:
git push --force-with-lease - Report what was done: how many conflicts were resolved, which files, and whether the build passes.
Rules
- Never delete or drop commits — always rebase, never squash unless asked.
- Resolve conflicts by understanding the intent of both sides, not by picking one side blindly.
- If a conflict is genuinely ambiguous (e.g. both sides rewrote the same function differently), explain what you chose and why.
- Always verify the build passes before pushing.
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.
- 2mo ago First seen · 33 lines · 31 tokens per session scan A 157d9e1e9a9b
resolve-pr-conflicts is a skill published in the GitHub repository G-Research/bobbit (18 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 413 once invoked, about $0.0001 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.
resolve-pr-conflicts compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| resolve-pr-conflictsG-Research/bobbit | Skill | 18 | 1mo ago | MIT | A | 31 | Claude Code |
| merge-batchdiegosouzapw/OmniRoute | Skill | 83k | 5d ago | MIT | A | 46 | Claude Code |
| prowler-commitprowler-cloud/prowler | Skill | 15k | yesterday | Apache-2.0 | A | 44 | Claude Code, Codex |
| gh-auth-isolationgithub/gh-aw | Skill | 5.6k | yesterday | MIT | A | 20 | Claude Code, Codex |
| github-skillzeenie-ai/OpenCompany | Skill | 1.1k | yesterday | MIT | A | 51 | Claude Code |
| comet-githubrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 72 | Claude Code, Codex |
| release-helperSahir619/fable-method | Skill | 2.3k | 1mo ago | MIT | A | 43 | Claude Code |