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/fboldo/oiap/create-pluginnpx skills add fboldo/oiap --skill create-plugingit clone --depth 1 https://github.com/fboldo/oiapWhat 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 | $0.00060 | $0.01149 |
| Opus 5 | $0.00030 | $0.00575 |
| Sonnet 5 | $0.00012 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
create-plugin 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 yesterday.
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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create OIAP Plugin
Use this skill when the user needs to write an agent plugin in TypeScript using OIAP.
OIAP lets plugin authors define a plugin once and export host-native bundles for multiple agent platforms. Treat OIAP as an external SDK and CLI unless the user is explicitly working inside the OIAP source repository.
First Response
Start by identifying the plugin shape the user wants:
- What should the plugin help an agent do?
- Which targets matter first, such as
claude-code,codex,cursor,openclaw,vscode-copilot-chat, orantigravity? - Does the plugin need commands, always-on instructions, skills, hooks, agents, MCP tools, executable recipes, or policies?
- Should generated bundles be committed, published, or only built locally for review?
If the request is already clear, do not over-interview. Scaffold the smallest useful plugin and explain where to extend it.
Install OIAP
For normal plugin projects, use the published OIAP CLI and SDK.
Use the existing project package manager in commands and examples. If the
project already uses bun, pnpm, yarn, or npm, follow that choice
instead of switching tools. Only fall back to npm when the project has no
clear package manager yet.
Install the OIAP packages with that package manager. For example:
# npm
npm install --save-dev @oiap/cli @oiap/core
# pnpm
pnpm add -D @oiap/cli @oiap/core
# yarn
yarn add --dev @oiap/cli @oiap/core
# bun
bun add --dev @oiap/cli @oiap/core
Use npx oiap in examples and instructions:
npx oiap targets
npx oiap build oiap.plugin.ts --target claude-code --out dist/claude-code
npx oiap build oiap.plugin.ts --out dist/oiap
Do not tell users to clone the OIAP repository unless they are contributing to OIAP itself.
Authoring Rules
- Create an
oiap.plugin.tsfile that exportsdefinePlugin(...)as the default export. - Import from
@oiap/core; avoid repository-relative imports. - Put larger prompts and agent instructions in Markdown files and load them with
markdownFile("path.md", { baseUrl: import.meta.url }). - Keep target-specific overrides small. Prefer portable primitives first.
- Declare
supportedTargetshonestly. Use only targets the user wants to build or verify. - Include policies when hooks, tools, scripts, network access, file writes, secrets, or destructive actions are involved.
- Build target bundles into
dist/and tell the user that OIAP generates artifacts; installing those artifacts into a host is handled by the host or the user's own workflow.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 146 lines · 60 tokens per session scan A 1b4ca7d03812
create-plugin is a skill published in the GitHub repository fboldo/oiap (5 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 1,149 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
publish-registry
Publish @agentos-software/ registry packages from AgentOS. Use whenever the user asks to publish or release registry software/agent packages.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.
lazarus-group
Adversary-emulation profile for Lazarus Group (G0032, aka Hidden Cobra / Diamond Sleet / Labyrinth Chollima), a North Korean RGB-linked actor conducting espionage, destructive, and financially motivated operations.