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/geeksfino/openskills/openskills-plugin-separationnpx skills add Geeksfino/openskills --skill openskills-plugin-separationgit clone --depth 1 https://github.com/Geeksfino/openskillsWrote 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/geeksfino/openskills/openskills-plugin-separation)<a href="https://agentmods.dev/skills/geeksfino/openskills/openskills-plugin-separation"><img src="https://agentmods.dev/badge/skills/geeksfino/openskills/openskills-plugin-separation.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 | $0.00034 | $0.00280 |
| Opus 5 | $0.00017 | $0.00140 |
| Sonnet 5 | $0.00007 | $0.00056 |
| Haiku 4.5 | $0.00003 | $0.00028 |
Grade A, and why
openskills-plugin-separation 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 5d 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.
What it actually says
OpenSkills Plugin Separation
Use this skill when changing plugin features, build-tool wiring, or runtime dependency topology.
Objective
Keep core runtime usable without plugin toolchains, especially for bindings and non-build execution paths.
Key Files
runtime/Cargo.tomlruntime/src/lib.rsruntime/src/bin/openskills-runtime.rsruntime/src/build/**bindings/ts/Cargo.tomlbindings/python/Cargo.toml
Separation Rules
- Build plugins must be gated behind explicit features.
- Core runtime defaults should not force plugin toolchains.
- Bindings should opt out of plugin-heavy default features when appropriate.
- Public exports for build functions must be feature-gated.
- CLI build commands must degrade gracefully when build features are disabled.
Validation Checklist
cargo check -p openskills-runtimepasses with default features.- Bindings compile without pulling plugin-specific dependencies unintentionally.
- Runtime tests that do not require plugin build paths continue to pass.
Output Format
- Feature graph summary
- Leakage findings (if any)
- Minimal patch plan
- Post-change verification commands
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.
- 5d ago First seen · 43 lines · 34 tokens per session scan A 00decd773d66
openskills-plugin-separation is a skill published in the GitHub repository Geeksfino/openskills (71 stars, last pushed 7d ago), licensed Apache-2.0. It adds 34 tokens to every session and 280 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.
Other skills, from other repositories
pie-testing
Start, stop, and query Play-In-Editor (PIE) sessions for runtime testing of Blueprints, gameplay logic, widgets, AI, and any in-game behavior. Use when the user asks you to "play", "test", "run", "PIE", "start/stop the game", or otherwise needs a live game world to validate changes.
Bun Test Runner
Fast test execution with Bun's built-in test runner including snapshot testing, mocking, code coverage, lifecycle hooks, DOM testing with happy-dom, and migration from Jest and Vitest to Bun test.
Code Execution
Run Python, Node.js, AND arbitrary shell commands in a secure E2B cloud sandbox that PERSISTS across calls within a conversation. Clone repos, install packages, run CLI tools (git, psql, ffmpeg, duckdb), and build up state turn over turn.
swarmclaw
AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.
runtime-self-improvement
Use when automatically improve OpenClaw and 1ai-skills at runtime. Analyze performance, detect gaps, enhance skills, and self-optimize during operation. Use when working with runtime self improvement.
Parallel Web Research
Deep web research powered by Parallel.ai — fast search with excerpts, URL→markdown extraction, long-running Task Runs, structured find-all datasets, and persistent web monitors.