bump-version-dev

A development release workflow that builds a release-like sim-use application and installs it locally for testing. It produces an Android app package and command-line tool without publishing them.

In plain words
What is it for?
Use it to prepare a local release candidate, test the Android app and CLI, or restore the previous local installation.
Why use it?
It lets developers check a release build on their machines before publishing. It also checks required build tools and handles version selection, staging, and local installation.

Skill for Claude CodeCodex

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/lycorp-jp/sim-use/bump-version-dev
Any agent
npx skills add lycorp-jp/sim-use --skill bump-version-dev
Clone the repo
git clone --depth 1 https://github.com/lycorp-jp/sim-use

Made for: Claude Code, Codex.

Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,010 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00111 $0.01010
Opus 5 $0.00056 $0.00505
Sonnet 5 $0.00022 $0.00202
Haiku 4.5 $0.00011 $0.00101

Measured 2d ago against content hash 8d0a4840be87, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bump-version-dev 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 2d 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.

.agents/skills/bump-version-dev/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This skill builds and locally installs a release-shaped sim-use binary so the user can validate it before publishing. It delegates the heavy lifting to scripts/dev-install.sh and handles version determination + user confirmation.

Run from the sim-use repo root (git rev-parse --show-toplevel).

Restore flow

If the user passes restore as an argument (e.g. /bump-version-dev restore), skip everything and run:

scripts/dev-install.sh --restore

Report success or failure and stop.

Step 1: Pre-flight

Run these checks. Abort with a clear error if any fails.

  1. Current directory is the sim-use repo root.
  2. build_products/Frameworks/ exists. If missing, tell the user to run scripts/build.sh dev (~30 min). Do NOT run it automatically.
  3. Android bridge toolchain: scripts/build-bridge.sh --check succeeds. If not, surface the missing tool.

Unlike /release, this skill does NOT require:

  • Clean working tree (local modifications are fine — this is a dev build)
  • GitHub auth
  • Homebrew tap clone
  • Codesign identity or notary profile

Step 2: Determine the next version

  1. Find the latest sim-use tag: git tag --list 'v*' --sort=-v:refname | head -1.
  2. If a prior tag exists, read commits since it: git log <last-tag>..HEAD --pretty=format:'%h %s'.
  3. Pick bump type from conventional commit prefixes:
    • feat!: / BREAKING CHANGEmajor
    • feat:minor
    • Only fix: / chore: / docs: / refactor: / test:patch
  4. Compute the next version.

If the user specified a version (e.g. /bump-version-dev 0.9.1), use that verbatim instead of auto-bumping.

Step 3: Confirm with the user

Show:

  • The current tag and the target version.
  • The commit list since the last tag (one line each).
  • What will happen: "Build APK + CLI as vX.Y.Z, stage, ad-hoc sign, and replace the PATH binary."

Ask: "Build and install vX.Y.Z locally?" Wait for explicit yes/no/version override.

Step 4: Run the dev-install script

scripts/dev-install.sh --version X.Y.Z

Read the full file on GitHub · 93 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. 2d ago First seen · 93 lines · 111 tokens per session scan A 8d0a4840be87

Subscribe to this mod's changes

bump-version-dev is a skill published in the GitHub repository lycorp-jp/sim-use (1,297 stars, last pushed 5d ago), licensed Apache-2.0. It adds 111 tokens to every session and 1,010 once invoked, about $0.0006 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

open-gui-remote-control

Control an Android phone through OpenGUI from an AI coding agent such as Claude Code, Codex, or OpenCode. Use when an agent should list online devices, run a natural-language mobile task, check execution status, pause, resume, or cancel through the local OpenGUI backend and CLI.

Core-Mate/OpenGUI · 66 tokens

open-gui-bootstrap

Launch and bootstrap OpenGUI from a plain-language user request. Use when an AI coding agent such as Claude Code, Codex, or OpenCode should install, configure, debug, and run the backend and Android client shipped in this repository while keeping manual setup to a minimum.

Core-Mate/OpenGUI · 60 tokens

control

Automatically control locally connected Android phones with OpenGUI screenshots and allowlisted actions whenever a request targets a phone, Android app, mobile game, or multiple devices. The user does not need to name OpenGUI. Use the native Codex Browser instead for browser-only work.

Core-Mate/OpenGUI · 55 tokens

agent-desktop-ffi

C-ABI bindings over agent-desktop's PlatformAdapter. Consumers (Python ctypes, Swift, Node ffi-napi, Go cgo, C++, Ruby fiddle) link libagentdesktopffi.{dylib,so,dll} and call ad functions directly instead of spawning the CLI binary per call. The canonical observe-act workflow is: adinit → adadaptercreate[withsession]…

lahfir/agent-desktop · 111 tokens

iOS SwiftUI Accessibility

Enforces WCAG 2.2 accessible coding patterns when writing SwiftUI — labels, traits, Dynamic Type, contrast, touch targets, focus management, orientation, and more. Based on the ios-swiftui-accessibility-techniques project with 41 static analysis rules across 23 WCAG criteria.

cvs-health/ios-swiftui-accessibility-techniques · 67 tokens

hig-project-context

Create or update a shared Apple design context document that other HIG skills use to tailor guidance. Use when the user says "set up my project context," "what platforms am I targeting," "configure HIG settings," or when starting a new Apple platform project. Also activates when other HIG skills need project context…

raintree-technology/hig-doctor · 113 tokens