consensus-loop:merge

A merge step that combines a worktree branch into a target branch as one commit with a structured message. A worktree is a separate working copy of the same repository.

In plain words
What is it for?
Use it to merge completed work after audit consensus and retrospective completion.
Why use it?
It provides a defined way to finish a branch after the required audit and retrospective are complete.

Skill for Claude CodeCodex

Part of the consensus-loop plugin — 9 skills, 9 commands, 3 agents, 12 hooks shipped together

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.

agentmods
npx agentmods add skills/berrzebb/consensus-loop/merge-worktree
Any agent
npx skills add berrzebb/consensus-loop --skill merge-worktree
Clone the repo
git clone --depth 1 https://github.com/berrzebb/consensus-loop

Made for: Claude Code, Codex.

Or install consensus-loop, the plugin that ships this one along with the rest of its 9 skills, 9 commands, 3 agents, 12 hooks.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,819 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin unknown 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 $0.00032 $0.01819
Opus 5 $0.00016 $0.00910
Sonnet 5 $0.00006 $0.00364
Haiku 4.5 $0.00003 $0.00182

Measured 3d ago against content hash fc5ee856628c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

consensus-loop:merge scanned grade A 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 3d 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

git -C "$(git rev-parse --git-common-dir)/.." cat-file -e HEAD:.claude/retro-marker.json 2>/dev/null || cat "$(git rev-parse --git-common-dir)/../.claude/retro-marker.json" 2>/dev/null

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/merge-worktree/SKILL.md · 231 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 3d ago First seen · 231 lines · 32 tokens per session scan A fc5ee856628c

Subscribe to this mod's changes

consensus-loop:merge is a skill published in the GitHub repository berrzebb/consensus-loop (15 stars, last pushed 5mo ago), with no licence file. It adds 32 tokens to every session and 1,819 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.