mainbranch: Skill for Claude Code

.claude/skills/mb-update/SKILL.md

mb-update is a skill for Claude Code from noontide-co/mainbranch. It costs 38 tokens per session (770 once invoked), scanned A, original, MIT.

A workflow for updating the installed Main Branch command-line tool and refreshing its links in a business workspace. It checks whether an update is needed and reports problems when the update cannot finish.

In plain words
What is it for?
Updating Main Branch, checking the result, refreshing workspace links, and showing warnings or repair instructions when something goes wrong.
Why use it?
It avoids guessing how the tool was installed or asking the user to remember package-manager commands. It also gives a direct status when the installed version is already current.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is noontide-co/mainbranch's own configuration. It tells Claude Code how to work on mainbranch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mainbranch configures →

Part of the mainbranch plugin — 21 skills shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to noontide-co/mainbranch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/noontide-co/mainbranch/main/.claude/skills/mb-update/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/noontide-co/mainbranch

Made for: Claude Code.

Or install mainbranch, the plugin that ships this one along with the rest of its 21 skills.

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 mb-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/noontide-co/mainbranch/mb-update.svg)](https://agentmods.dev/skills/noontide-co/mainbranch/mb-update)
Your own site
<a href="https://agentmods.dev/skills/noontide-co/mainbranch/mb-update"><img src="https://agentmods.dev/badge/skills/noontide-co/mainbranch/mb-update.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 770 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00038 $0.00770
Opus 5 $0.00019 $0.00385
Sonnet 5 $0.00008 $0.00154
Haiku 4.5 $0.00004 $0.00077

Measured 8d ago against content hash 242141fd3d2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mb-update 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 8d 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.

.claude/skills/mb-update/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update

Update the installed Main Branch CLI and skills, then refresh this business folder's Claude Code links.

Use this instead of asking the user to remember whether they installed with pipx or an old clone. The CLI owns the mechanics. Do not suggest raw package commands such as pipx upgrade mainbranch as the first update path; only use that as the bootstrap fallback when mb update is unavailable or the installed version is 0.1.x.

CLI facts first: Run mb update --repo . --json from the business folder and use its result before giving install-mode advice.


Step 1: Update Main Branch

Run from the business folder:

mb update --repo . --json 2>&1

Handle the JSON result:

Result What to say
"ok": true, old_version != new_version "Updated Main Branch and refreshed skill links."
"ok": true, old_version == new_version "Main Branch is already up to date."
"ok": false Show the first error and the repair copy below.
Invalid JSON Run mb update --check --repo . yourself if possible; if not, ask the user for that output.

If the result includes warnings, show them after the main status.


Step 2: If Update Fails

Tell the user:

"I wasn't able to update Main Branch. This can leave you on old skills or old migration behavior.

Try these from your business repo:

mb update --check --repo .
mb doctor

If mb --version says 0.1.x, run this once first:

pipx upgrade mainbranch
```"

Do not continue as if the update worked.


If skills_relinked_count is greater than zero after an actual update, tell the user:

"Skill links were refreshed. If a slash command does not appear in Claude Code, restart Claude from this repo and run /mb-start."

Claude Code loads slash commands at session start, so a restart can be required after repairing links. In --check --json output, treat planned_skills_relink_count as a dry-run preview, not proof that links already changed.

Read the full file on GitHub · 102 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. 8d ago First seen · 102 lines · 38 tokens per session scan A 242141fd3d2c

Subscribe to this mod's changes

mb-update is a skill published in the GitHub repository noontide-co/mainbranch (39 stars, last pushed 24d ago), licensed MIT. It adds 38 tokens to every session and 770 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

cn-check

Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.

continuedev/continue · 49 tokens

web-scraping

Fetches web pages and extracts structured data using mq's toolchain (mq-crawl for fetching/crawling/JS rendering, mq for HTML-to-Markdown selector-based extraction, http() for in-query requests). Use when the user wants to scrape a URL, pull structured data out of a webpage, crawl a site, or turn HTML into…

harehare/mq · 89 tokens

crit-story

Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.

tomasz-tomczyk/crit · 47 tokens

larksnap-fetch

A bridge for downloading Feishu/Lark documents or ordinary webpages into local files, with options such as Markdown, HTML, or PDF. Feishu, also called Lark, is a workplace collaboration platform.

AmbroseX/larksnap · 111 tokens

alive:demo

Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.

alivecontext/alive · 52 tokens

alive:system-upgrade

Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.

alivecontext/alive · 57 tokens