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.
git clone --depth 1 https://github.com/air-gapped/skillsWrote 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/plugins/air-gapped/skills/inference-apis)<a href="https://agentmods.dev/plugins/air-gapped/skills/inference-apis"><img src="https://agentmods.dev/badge/plugins/air-gapped/skills/inference-apis/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/plugins/air-gapped/skills/inference-apis"><img src="https://agentmods.dev/badge/plugins/air-gapped/skills/inference-apis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
inference-apis 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 23d 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
{
"name": "inference-apis",
"source": "./",
"description": "Inference-API compatibility suite — the three open LLM serving protocols as third-party surfaces: OpenAI Chat Completions + legacy /v1/completions (7 local servers, gateways, 10 cloud compat endpoints, reasoning-field schism, client wire behavior), OpenAI Responses (spec, streaming events, store/previous_response_id semantics, translation), and Anthropic Messages (7 native server implementations, thinking-signature seam, stop_reason divergences, Claude Code/opencode integration). Source-examined at pinned commits with live-verification logs.",
"version": "0.20260922.23",
"author": {
"name": "Jörgen"
},
"license": "MIT",
"skills": [
"./.claude/skills/chat-completions-api",
"./.claude/skills/responses-api",
"./.claude/skills/messages-api"
],
"strict": false,
"category": "inference",
"tags": [
"chat-completions",
"responses-api",
"anthropic-messages",
"openai-compatible",
"vllm",
"sglang",
"llama-cpp",
"ollama",
"litellm",
"claude-code",
"opencode"
]
}What it installs
The manifest is a name and a version. 3 skills travel with it, and installing the plugin installs all of them — 449 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside marketplace.json#inference-apis 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.
- 23d ago Changed d2724cb81373
- 1mo ago Changed 96a16b1f2051
- 1mo ago Changed 5242dc6ba0a8
- 1mo ago First seen · 30 lines scan A 80eec38a841b
inference-apis is a plugin published in the GitHub repository air-gapped/skills (5 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
data-engineering
ETL pipeline construction, data warehouse design, batch processing workflows, and data-driven feature development.
data-validation-suite
Schema validation, data quality monitoring, streaming validation pipelines, and input validation for backend APIs.
data-validation-suite
Schema validation, data quality monitoring, streaming validation pipelines, and input validation for backend APIs.
preset-snowflake-cortex-skills
Snowflake Cortex Agent skills for explicit direct Snowflake Cortex REST and SQL workflows only: account and authentication context, agent management, and confirmation-gated agent runs. Requires a Snowflake account; does not use Preset credentials. Do not use for MCP-only work.
backend-ai-skills
AI/ML data engineering and model serving.
functional-programming
Functional programming with Elixir, OTP patterns, Phoenix framework, and distributed systems.