OpenMausBot: Skill for Claude Code

.claude/skills/windows-release/SKILL.md

windows-release is a skill for Claude Code from milind-soni/OpenMausBot. It costs 75 tokens per session (1,549 once invoked), scanned A, original, Apache-2.0.

A Windows release workflow for building and publishing an OpenMausBot desktop installer and its update feed.

In plain words
What is it for?
Use it to bump the app version, run type checks, create the NSIS installer, and publish the Windows release files.
Why use it?
It gathers the versioning, build, and packaging checks needed to ship a consistent Windows update.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is milind-soni/OpenMausBot's own configuration. It tells Claude Code how to work on OpenMausBot 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 OpenMausBot configures →

About the project

OpenMausBot is an open-source chat application where users interact with multiple AI bots, each backed by an agent, model, computer, and connected apps. It is for people who want to run Claude, Codex, or Grok-based agents locally through a messaging-style interface. Its catalogue add-ons provide skills and instructions for working with the application.

milind-soni/OpenMausBot · 5,687 stars · on GitHub · openmausbot.com

Reuse

Borrowing it

Nothing to install: this file belongs to milind-soni/OpenMausBot. 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/milind-soni/OpenMausBot/main/.claude/skills/windows-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/milind-soni/OpenMausBot

Made for: Claude Code.

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 windows-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/milind-soni/openmausbot/windows-release/github.svg)](https://agentmods.dev/skills/milind-soni/openmausbot/windows-release)
Your own site
<a href="https://agentmods.dev/skills/milind-soni/openmausbot/windows-release"><img src="https://agentmods.dev/badge/skills/milind-soni/openmausbot/windows-release/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 windows-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/milind-soni/openmausbot/windows-release"><img src="https://agentmods.dev/badge/skills/milind-soni/openmausbot/windows-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,549 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 $0.00075 $0.01549
Opus 5.5 $0.00030 $0.00620
Sonnet 5.5 $0.00015 $0.00310
Haiku 4.5 $0.00007 $0.00155

Measured 1mo ago against content hash d161c5ba12f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

windows-release 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.

.claude/skills/windows-release/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Windows release

Ships OpenMausBot-<version>-setup.exe and its update feed to milind-soni/OpenMausBot. The unified release workflow mirrors the same bytes to the legacy releases repository for apps installed before the updater migration.

Scope: Windows only. The macOS build is a separate flow (dmg + notarytool + staple) that must run on a Mac. This skill never touches mac artifacts — but see Every release ships both before you finish.

Preconditions

  • Run on Windows. NSIS packaging from macOS needs Wine; don't.
  • Node 24+ (package.json engines). Node 23 builds fine but pnpm warns on every step and CI runs 24 — don't debug a runtime oddity on the wrong major.
  • pnpm via corepack pnpm. If corepack enable fails with EPERM (no admin), drop a pnpm.cmd shim containing @echo off / corepack pnpm %* somewhere on PATH — package:win chains pnpm build && … and needs bare pnpm to resolve.

1. Version

Bump version in package.json. It must match the tag on the GitHub release you upload to, and it becomes the version electron-updater compares against.

2. Build

pnpm install
pnpm typecheck
pnpm package:win

package:win deliberately omits build:speech — the dictation helper is a signed macOS Swift binary and has no Windows counterpart.

Output in release/:

File Purpose
OpenMausBot-<version>-setup.exe the installer
latest.yml the update feed — see step 4
OpenMausBot-<version>-setup.exe.blockmap differential updates
OpenMausBot-<version>-x64.zip portable, not used by the updater

3. Verify before uploading

Three things silently produce a broken app if wrong. Check all three:

Test-Path release\win-unpacked\resources\server\index.js   # harness server
Test-Path release\win-unpacked\resources\ui\index.html     # built UI
Get-Content release\win-unpacked\resources\app-update.yml  # feed config

Read the full file on GitHub · 139 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 Changed · +8 lines · +1 tokens per session d161c5ba12f4
  2. 1mo ago First seen · 131 lines · 74 tokens per session scan A ea4183531fb8

Subscribe to this mod's changes

windows-release is a skill published in the GitHub repository milind-soni/OpenMausBot (5,687 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 1,549 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

create-draft-pr

Create a draft pull request for the current session. Use when the user wants to open a draft PR with the session's changes.

microsoft/vscode · 31 tokens

create-pr

Create a pull request for the current session. Use when the user wants to open a PR with the session's changes.

microsoft/vscode · 27 tokens

git-ops

Close out a local coding task on the bound daemon — stage, commit, branch, merge, push via cloud git — and when a merge conflicts, STOP and escalate with the file list instead of auto-resolving. Push reaches only the bare replica; prod-triggering tags are refused.

Prismer-AI/PrismerCloud · 62 tokens

release-rollback

Roll a release back for real when post-deploy regression goes red — apc release rollback flips the current version to pulled and the last good version back to current in the release ledger, and (with --mirror) repoints the bare mirror ref. Behind an approval gate; with no previous good version it BLOCKS instead of…

Prismer-AI/PrismerCloud · 96 tokens

release-tag

Cut a release tag behind a real tier gate and cloud approval readback. The approval, task, approved commit, and resulting tag are bound; self-approval and HEAD drift fail closed. Prod prefixes remain refused.

Prismer-AI/PrismerCloud · 46 tokens

releasing-prod

A controlled process for deploying already tested changes to the production environment. Production is the live environment used by users, and this process includes owner approval, database migration checks, deployment, and smoke tests.

Prismer-AI/PrismerCloud · 74 tokens