What is llm-inference-integration?

Guidance for building and operating software that calls or hosts large language models, the systems behind many text-generating AI tools. It covers model calls, agents, retrieval, streaming, evaluation, routing, and usage tracking.

Use it when designing, implementing, reviewing, debugging, or operating AI inference features such as model gateways, prompt versions, tool-using agents, fallback paths, evaluations, replays, and batch processing.

It helps teams handle model behavior, failures, costs, versions, and comparisons as part of a real product rather than as isolated prompts.

llm-inference-integration — Skill for Claude Code and Codex by ccoalm

Install

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.

Any agent

npx skills add ccoalm/ccl-skills --skill llm-inference-integration

Clone the repo

git clone --depth 1 https://github.com/ccoalm/ccl-skills

Made for: Claude Code, Codex.

Or install ccl-skills, the plugin that ships this one along with the rest of its 33 skills, 4 commands, 7 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ccoalm/ccl-skills/llm-inference-integration/github.svg)](https://agentmods.dev/skills/ccoalm/ccl-skills/llm-inference-integration)

Your own site

<a href="https://agentmods.dev/skills/ccoalm/ccl-skills/llm-inference-integration"><img src="https://agentmods.dev/badge/skills/ccoalm/ccl-skills/llm-inference-integration/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ccoalm/ccl-skills/llm-inference-integration"><img src="https://agentmods.dev/badge/skills/ccoalm/ccl-skills/llm-inference-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,601 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00119	$0.04601
Opus 5	$0.00060	$0.02301
Sonnet 5	$0.00024	$0.00920
Haiku 4.5	$0.00012	$0.00460

Measured 4d ago against content hash f79872e12ba6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

llm-inference-integration 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.

skills/llm-inference-integration/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Inference Integration

Use this for product backend work that calls, hosts, evaluates, or operates LLM and inference systems. Keep the skill generic: extract reusable mechanics only, not business-specific prompts, datasets, provider names, repository paths, or domain nouns.

Code/test changes require self-checks; invoke code-review automatically before completion.

Skill Routing

Use this skill for LLM gateway/client design, model registry, prompt versioning, agent/tool orchestration, streaming APIs, fallback, token/cost accounting, evals, replay, shadow comparison, batch inference, and inference observability.
Use go-microservice-architecture or go-microservice-dev when the work is mainly a Go service with ordinary storage/RPC/MQ concerns and only minor LLM integration.
Use python-service-architecture or python-service-dev when the work is mainly a Python service, AI-service host, worker, SDK/package, or batch job with ordinary API/storage/Redis/queue/pytest/packaging concerns and only minor inference integration.
Use nodejs-service-dev on the same terms when that host is mainly a Node.js service, worker, or CLI/tooling with ordinary API/storage/queue/runner/packaging concerns and only minor inference integration; its architecture decisions must go to product-rd-workflow, never to a Node architecture sibling, which does not exist by decision.
Use defect-diagnosis first when a model output, flaky eval, timeout, regression, fallback failure, or prompt/version issue must be reproduced and root-caused.
Use product-rd-workflow first when the request spans product goal, PRD, architecture, implementation plan, release, and learning loop.
Use product-rd-workflow first for AI/algorithm product launch SOPs, business acceptance baselines, build-vs-buy ROI, new-vs-iteration launch gates, or multi-algorithm product quality gates. This skill owns inference implementation/evaluation mechanics after the product gate is defined.
For high-impact answers or decisions where wrong output can mislead users, affect money/rights/access, or create support/compliance risk, use product-rd-workflow high-risk resilience gates before fallback, downgrade, or launch decisions.
When a change can alter what a client renders or which state, action, or decision path it offers—including strings/templates/config/flags and API/event/schema fields, enums, status/progress, permission/capability signals, defaults, or result shapes—you must load ../product-ui-ux-design/references/delivery-contract.md, create the applicable full or lightweight record in that contract, and follow its canonical consumer-universe classification, design/test/client handoffs, and terminal-status rules.
This inference owner returns only its producer_record delta: immutable binding, prompt/model/config/artifact identity, exact command/environment, and API/event/log/output observation.

Read the full file on GitHub · 127 lines

Files

What ships with it

22 files 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.

Changes

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 Changed · +2 lines f79872e12ba6
9d ago Changed · +4 lines 6877a538dc32
12d ago First seen · 121 lines · 119 tokens per session scan A 2b42442d8412

Subscribe to this mod's changes

llm-inference-integration is a skill published in the GitHub repository ccoalm/ccl-skills (6 stars, last pushed today), licensed Apache-2.0. It adds 119 tokens to every session and 4,601 once invoked, about $0.0006 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.

Backend and APIs Claude Code Data and AI agent-skills ai-agents anthropic codex developer-tools

mcp-builder

Guide the creation of high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when the user wants to build an MCP server to integrate an external API or service, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

waybarrios/opencode-power-pack · 68 tokens

huggingface-community-evals

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .evalresults publication, or community-evals automation.

waybarrios/opencode-power-pack · 71 tokens

huggingface-datasets

Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.

waybarrios/opencode-power-pack · 43 tokens

mle-workflow

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

affaan-m/ECC · 44 tokens

django-patterns

Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.

affaan-m/ECC · 32 tokens

api-design

REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs. Use when designing or reviewing REST endpoints, resource names, status codes, pagination, or versioning.

affaan-m/ECC · 51 tokens