merge

merge is a skill for Claude Code from fivol/claude-make-better. It costs 112 tokens per session (3,090 once invoked), scanned C, original, MIT.

A workflow for integrating a finished task branch into its base branch, the branch it started from. It updates the task, resolves conflicts, reviews the combined code, waits for successful checks, merges, and removes the temporary workspace.

In plain words
What is it for?
Use it after explicit approval to finish a task, resolve Git conflicts, run the final review, wait for CI—the automated build and test checks—and merge the branch.
Why use it?
It provides a defined final path for merging work and cleaning up related servers, worktrees, branches, ports, and proxy settings.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

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 feature plugin — 5 skills, 2 commands, 2 agents shipped together

Good fit Use it after explicit approval to finish a task, resolve Git conflicts, run the final review, wait for CI—the automated build and test checks—and merge the branch.

Compare 6 skills from other repositories ↓
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 fivol/claude-make-better
Claude Code
/plugin install feature

Made for: Claude Code.

Or install feature, the plugin that ships this one along with the rest of its 5 skills, 2 commands, 2 agents.

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/fivol/claude-make-better/merge/github.svg)](https://agentmods.dev/skills/fivol/claude-make-better/merge)
Your own site
<a href="https://agentmods.dev/skills/fivol/claude-make-better/merge"><img src="https://agentmods.dev/badge/skills/fivol/claude-make-better/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/fivol/claude-make-better/merge"><img src="https://agentmods.dev/badge/skills/fivol/claude-make-better/merge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,090 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00112 $0.03090
Opus 5 $0.00056 $0.01545
Sonnet 5 $0.00022 $0.00618
Haiku 4.5 $0.00011 $0.00309

Measured 10d ago against content hash a7c61edb586d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

merge scanned grade C with 1 finding 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$ROOT/<worktrees>/<task>" # leftover .feature.json / empty repo dirs
plugins/feature/skills/merge/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Merge — integrate the task branch, then clean up

Runs only on an explicit user go-ahead ("done", "finish", "merge it", or the equivalent in the user's language). Confirm once before merging. In workspace context read <worktrees>/<task>/.feature.json for the repos, base branches, ports, PIDs and PR links, and do every step for all involved repos; standalone, the current repo and its branch's PR are the whole job (steps 7–9 are then no-ops).

Strategy — read it from the config, don't assume:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/config.py" --root "$ROOT"   # → .merge
merge.strategy merge.via What happens
merge (default) local-push Merge the task branch into BASE locally and push. The task SHAs land in BASE, so the host marks the PR Merged by itself and your local base is already up to date.
merge gh Same commit shape, but the host performs it (gh pr merge --merge); pull BASE afterwards.
squash / rebase gh (forced) The host rewrites the SHAs (gh pr merge --squash|--rebase). Required by repos with a squash-only policy. Steps 5–6 below are replaced by that single call, and the local base is refreshed with git pull --ff-only.

Whatever the strategy, step 2 is not optional: the integration happens on the task branch, in its worktree, so the PR shows exactly what will land and CI runs on it. merge.wait_ci: false skips step 3; merge.cleanup: false stops after step 6.

Per repo: WT="$ROOT/<worktrees>/<task>/<repo>", BRANCH = the task branch, BASE = .feature.json .repos.<repo>.base (the repo's base_branch). ROOT = the workspace root — anchor it via the .claude/feature/config.json marker, never $(pwd). SCRIPTS="${CLAUDE_PLUGIN_ROOT}/scripts".

1. Make sure the task branch is fully committed

git -C "$WT" status --porcelain   # must be empty

2. Sync the latest base into the task branch — resolve conflicts HERE (in the worktree)

Read the full file on GitHub · 224 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. 10d ago First seen · 224 lines · 112 tokens per session scan C a7c61edb586d

Subscribe to this mod's changes

merge is a skill published in the GitHub repository fivol/claude-make-better (5 stars, last pushed 29d ago), licensed MIT. It adds 112 tokens to every session and 3,090 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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