git-merge

git-merge is a skill for Claude Code, Codex from MithunWijayasiri/dotclaude. It costs 76 tokens per session (2,921 once invoked), scanned A, original, MIT.

A procedure for combining another Git branch, usually master, into the branch you are working on. It preserves unstaged local changes, resolves conflicts, and checks the result.

In plain words
What is it for?
Use it to merge branches safely, inspect conflicts, keep local-only files out of commits, and verify the integrated code with the repository's checks.
Why use it?
It reduces the risk of losing local work, creating incorrect conflict resolutions, or accepting a merge that passes basic checks but changes behaviour incorrectly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to merge branches safely, inspect conflicts, keep local-only files out of commits, and verify the integrated code with the repository's checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mithunwijayasiri/dotclaude/git-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 MithunWijayasiri/dotclaude --skill git-merge
Clone the repo
git clone --depth 1 https://github.com/MithunWijayasiri/dotclaude

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 git-merge

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mithunwijayasiri/dotclaude/git-merge"><img src="https://agentmods.dev/badge/skills/mithunwijayasiri/dotclaude/git-merge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,921 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 $0.00076 $0.02921
Opus 5 $0.00038 $0.01460
Sonnet 5 $0.00015 $0.00584
Haiku 4.5 $0.00008 $0.00292

Measured 9d ago against content hash 5a7e009da159, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

git-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 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.

skills/git-merge/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Merge — Safe Branch Integration

Procedural workflow the main agent runs. Investigate before mutating; preserve the user's local-only unstaged changes; resolve conflicts by diagnosis not guessing; verify the merge passes the repo's existing checks before declaring done.

Hard rules

  • Read-only investigation first. fetch, then map state, before any stash/merge.
  • Never auto-commit beyond the one merge the user authorized. git commit/--amend need explicit user approval — ask (amend / separate fixup / leave it).
  • git add/stash/merge are mutating — explain, then run (user already asked to merge = authorization for the merge itself).
  • Keep the user's local-only unstaged files OUT of any commit. Stage only merge-resolution files.
  • Never push unless asked.
  • Delegate read-only recon (steps 1–2) to a Haiku subagent; run fetch, conflict-reading, resolution, and every mutating step (merge/add/commit/stash) on the main model only.

1. Map state

Fetch on the main model. git fetch writes remote-tracking refs → mutating, so it never goes to the subagent. Fetch all of origin, not one branch: git fetch origin <target> refreshes origin/<target> only, leaving origin/<current-branch> stale — and step 1 compares against both.

git fetch origin          # both origin/<target> and origin/<current-branch>

Then delegate the noise. The rest of steps 1–2 is high-noise, low-judgment. Spawn a Haiku subagent (the git-digest agent, or general-purpose pinned to Haiku) to run the status/log/diff --name-only reads and return ONLY the structured facts: commits + files the target brings, overlap with unstaged/untracked, and ahead/behind own remote. The main model then reads only the conflict hunks (step 5). Never let the subagent run a mutating command.

git status                          # branch, unstaged, untracked, ahead/behind OWN remote
git log --oneline HEAD..origin/<target>      # commits target brings
git merge-base HEAD origin/<target>
git log --oneline HEAD..origin/<current-branch>   # is local behind its OWN remote?

Read the full file on GitHub · 161 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. 9d ago First seen · 161 lines · 76 tokens per session scan A 5a7e009da159

Subscribe to this mod's changes

git-merge is a skill published in the GitHub repository MithunWijayasiri/dotclaude (2 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 2,921 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

nvca-chart-release

Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.

NVIDIA/nvcf · 61 tokens