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 skills add ntaffzii/Skill-Agents --skill model-portability-adaptergit clone --depth 1 https://github.com/ntaffzii/Skill-AgentsWrote 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/ntaffzii/skill-agents/model-portability-adapter)<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/model-portability-adapter"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/model-portability-adapter/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.
<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/model-portability-adapter"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/model-portability-adapter.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00055 | $0.00545 |
| Opus 5 | $0.00028 | $0.00272 |
| Sonnet 5 | $0.00011 | $0.00109 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
model-portability-adapter 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 9d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Portability Adapter
Use this skill to make agent instructions portable across model providers and clients.
Portability Principle
Write for agent capability, not provider branding.
Good:
- Use available file-reading tools.
- Use available command execution tools.
- Use available web/search tools.
- Use the client's artifact/document feature if present.
Avoid:
- Hardcoding one client's tool name.
- Assuming one model's memory, browsing, artifact, or MCP behavior.
- Depending on hidden system prompts.
Compatibility Targets
This skill is intended for:
- Claude or Claude Code
- ChatGPT or custom GPT-style agents
- Gemini or Gems-style agents
- Codex or coding agents
- Local agents with MCP servers
- Multi-agent systems with their own tool registry
Workflow
-
Identify the instruction type
- Skill: behavior or domain process.
- Workflow: ordered multi-step job.
- Tool instruction: executable action mapping.
- Prompt: one-off request or reusable template.
-
Remove vendor coupling
- Replace exact tool names with capability names.
- Replace client-specific UI assumptions with generic alternatives.
- Keep any vendor-specific notes in an adapter section, not the core skill.
-
Normalize structure
- Use clear frontmatter when supported.
- Put trigger guidance in the description.
- Keep the body procedural.
- Include verification and output expectations.
-
Add adapter notes
- Claude: can use
SKILL.mdstyle folders when the client supports skills. - ChatGPT: can paste the core instructions into custom instructions or project instructions.
- Gemini: can use the core instructions as Gem or agent guidance.
- Local MCP agents: map capability names to registered MCP tools.
- Claude: can use
-
Validate portability
- Check that the skill still makes sense without exact tool names.
- Check that a model without file tools can still ask for files or explain the blocker.
- Check that a model with tools knows when to inspect, act, and verify.
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.
- 9d ago First seen · 83 lines · 55 tokens per session scan A 5fa01f0e5622
model-portability-adapter is a skill published in the GitHub repository ntaffzii/Skill-Agents (4 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 545 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
gemini-api-dev
Use when build applications using Google Gemini API. Handle chat completions, multimodal inputs, function calling, streaming, and grounding with Google Search. Use when building applications using google gemini api. handle chat completions, multimodal.
claude
Anthropic Claude AI models for analysis and coding. Use for AI assistants.
guidance
Constrain LLM output with grammars; guarantee valid JSON.
outlines
Outlines: structured JSON/regex/Pydantic LLM generation.
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude…