merge

merge is a skill for Claude Code, Codex from julianobarbosa/claude-code-skills. It costs 135 tokens per session (900 once invoked), scanned A, original, MIT.

A Git workflow for merging the current feature branch into the main branch, then optionally removing the old branch and worktree.

In plain words
What is it for?
Use it to update main, prefer a linear history when possible, create a merge commit when needed, push the result, and clean up related branches or worktrees.
Why use it?
It provides a consistent merge process and avoids accidentally merging with uncommitted changes or deleting work without confirmation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to update main, prefer a linear history when possible, create a merge commit when needed, push the result, and clean up related branches or worktrees.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/julianobarbosa/claude-code-skills/merge
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.

Any agent
npx skills add julianobarbosa/claude-code-skills --skill merge
Clone the repo
git clone --depth 1 https://github.com/julianobarbosa/claude-code-skills

Made for: Claude Code, Codex.

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 merge

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/julianobarbosa/claude-code-skills/merge"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/merge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 900 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 $0.00135 $0.00900
Opus 5.5 $0.00054 $0.00360
Sonnet 5.5 $0.00027 $0.00180
Haiku 4.5 $0.00014 $0.00090

Measured 1mo ago against content hash f9426f58e691, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

merge 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 1mo 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.

skills/merge/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Merge

Combine merge-and-cleanup and merge-to-main into one flow. Default to fast-forward; preserve a merge commit when fast-forward isn't possible or the user asks for one. Always interactive about deleting branches and worktrees.

Flow

  1. Refuse if already on main. If git rev-parse --abbrev-ref HEAD returns main (or master), stop and report — there's nothing to merge.
  2. Working tree must be clean. If there are uncommitted changes, ask the user whether to commit, stash, or abort. Do not silently stash.
  3. Capture the feature branch name — FEATURE=$(git rev-parse --abbrev-ref HEAD).
  4. Sync main.
    • git checkout main
    • git pull --ff-only origin main
  5. Try fast-forward merge first.
    • git merge --ff-only "$FEATURE"
    • If it succeeds, history is linear — done with the merge step.
    • If it fails (branch diverged), proceed to step 6.
  6. Fall back to merge commit — git merge --no-ff "$FEATURE".
    • If there are conflicts, stop and report. Do not auto-resolve.
    • Write a meaningful merge-commit message; do not accept the default if it's just "Merge branch …".
  7. Push — git push origin main.
  8. Interactive cleanup. Ask the user: "Delete $FEATURE (local + remote) and any associated worktree?"
    • On yes:
      • If a worktree exists for $FEATURE (git worktree list | grep -F "$FEATURE"), cd to the main repo dir first, then git worktree remove <path>.
      • git branch -d "$FEATURE" (use -D only if user explicitly confirms — -d refuses if branch isn't merged, which is the safety we want).
      • git push origin --delete "$FEATURE" (ignore failure if branch was never pushed).
    • On no: leave everything in place.
  9. Report final status — commit hash on main, whether branch was deleted, whether a worktree was removed.

Notes

  • Prefer ff-only. Linear history is easier to reason about. Only fall back to a merge commit when the branch genuinely diverged.
  • Never --no-verify. If a pre-push hook fails, fix the underlying issue; don't bypass.
  • Worktree-first cleanup. If the feature branch was developed in a worktree, you cannot delete the branch from inside the worktree. Always cd to the main repo working directory first.
  • Conflict policy. This skill does not auto-resolve conflicts. If git merge reports a conflict, stop and surface it to the user — they decide.

Read the full file on GitHub · 47 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.

  1. 1mo ago First seen · 47 lines · 135 tokens per session scan A f9426f58e691

Subscribe to this mod's changes

merge is a skill published in the GitHub repository julianobarbosa/claude-code-skills (14 stars, last pushed 11d ago), licensed MIT. It adds 135 tokens to every session and 900 once invoked, about $0.0005 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 2026-08-31.