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.
npx agentmods add skills/isac322/kwin-mcp/release-notesnpx skills add isac322/kwin-mcp --skill release-notesgit clone --depth 1 https://github.com/isac322/kwin-mcpWrote 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.
[](https://agentmods.dev/skills/isac322/kwin-mcp/release-notes)<a href="https://agentmods.dev/skills/isac322/kwin-mcp/release-notes"><img src="https://agentmods.dev/badge/skills/isac322/kwin-mcp/release-notes.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01013 |
| Opus 5 | $0.00000 | $0.00507 |
| Sonnet 5 | $0.00000 | $0.00203 |
| Haiku 4.5 | $0.00000 | $0.00101 |
Grade A, and why
release-notes 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Notes Generator
Generate SEO-optimized GitHub release notes for kwin-mcp.
Usage
/release-notes <version>
Example: /release-notes v0.5.1
Instructions
Step 1: Gather Context
- Read
CHANGELOG.mdand find the entry for the specified version - Read
pyproject.tomlto confirm the current version and project metadata - Check existing GitHub releases for style consistency:
gh release list --limit 5 gh release view <previous-version>
Step 1.5: Verify plugin manifests + bundled SKILL.md are in sync
Before generating release notes, ensure all integrations (.claude-plugin/marketplace.json, integrations/claude-code/.claude-plugin/plugin.json, integrations/opencode/plugin/package.json, and the OpenCode plugin's bundled SKILL.md) reflect the version being released:
python3 scripts/sync_plugin_version.py # write synced state
python3 scripts/sync_plugin_version.py --check # verify (CI also runs this)
If new MCP tools were added or renamed in this release, also confirm that integrations/claude-code/skills/kwin-desktop-automation/SKILL.md reflects them — the OpenCode plugin auto-mirrors that file on its next npm run build. The release notes' New Tools table should match what the SKILL.md exposes.
Step 2: Determine Release Type
- Patch release (x.y.Z): bug fixes, minor improvements
- Minor release (x.Y.0): new features, new tools, non-breaking changes
- Major release (X.0.0): breaking changes
Step 3: Generate Release Notes
Minor+ Release Template
kwin-mcp vX.Y.Z <one-line value proposition with primary keywords>.
## Highlights
- **Feature name**: Description mentioning exact technology (AT-SPI2, libei, EIS, D-Bus, etc.)
- **Feature name**: Description with concrete numbers (e.g. "17 new MCP tools")
- ...
## New Tools
| Tool | Description |
|------|-------------|
| `tool_name` | What it does |
| ... | ... |
## Installation
\```bash
# Using uv (recommended)
uv tool install kwin-mcp
# Using pip
pip install kwin-mcp
\```
**Full Changelog**: https://github.com/isac322/kwin-mcp/compare/vPREVIOUS...vCURRENT
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.
- 4d ago First seen · 105 lines · 0 tokens per session scan A 134e0f5a6897
release-notes is a skill published in the GitHub repository isac322/kwin-mcp (42 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,013 tokens. 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.
Other skills, from other repositories
agent-desktop
Desktop automation via native OS accessibility trees using the agent-desktop CLI. Use when an AI agent needs to observe, interact with, or automate desktop applications (click buttons, fill forms, navigate menus, read UI state, toggle checkboxes, scroll, drag, type text, take screenshots, manage windows, use…
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]…
axstream
Fast deterministic macOS UI automation via replayable macros. Use BEFORE driving any macOS app's UI by hand (clicking/typing via computer-use or screenshots) — if a macro exists, replay finishes the task in seconds with no per-step reasoning; after doing a UI task manually, save it as a macro so the next run is fast.…
goshipit
Pre-launch codebase audit skill. Use this whenever someone is about to ship, deploy, launch, push to main/prod, or merge a release - even without "goshipit" explicitly. Trigger on: "is my app ready?", "can I deploy now?", "pre-deploy check", "review before launch", "is this production-ready?", "check my codebase"…
nova-grounding
AX-first reading and grounded activation workflow for Nova desktop automation on macOS and Windows. Use for reading UI, clicking controls, OCR fallback, screenshots, and coordinate input without guessing.
computer-use
Windows 桌面自动化执行规则。使用 screeninteractor 观察与操作原生桌面应用。.