llm-integration-review

llm-integration-review is a skill for Claude Code, Codex from woliveiras/geremmyas. It costs 49 tokens per session (332 once invoked), scanned A, original, MIT.

A review procedure for services that call large language models, which are AI systems that generate or analyse text and structured data. It examines where model calls, tools, prompts, retries, outputs, and operational settings belong.

In plain words
What is it for?
Use it when adding or reviewing model calls, tool use, structured outputs, retries, timeouts, rate limits, and fallbacks in a service. It guides validation, data minimisation, authorisation, audit records, and contract tests.
Why use it?
It helps prevent fragile model integrations from spreading through route handlers and business logic. It also addresses invalid inputs, leaked private data, unreliable output parsing, failed requests, rate limits, and unsafe tool actions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when adding or reviewing model calls, tool use, structured outputs, retries, timeouts, rate limits, and fallbacks in a service. It guides validation, data minimisation, authorisation, audit records, and contract tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/woliveiras/geremmyas/llm-integration-review
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 woliveiras/geremmyas --skill llm-integration-review
Clone the repo
git clone --depth 1 https://github.com/woliveiras/geremmyas

Made for: Claude Code, Codex.

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.

agentmods badge for llm-integration-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/woliveiras/geremmyas/llm-integration-review/github.svg)](https://agentmods.dev/skills/woliveiras/geremmyas/llm-integration-review)
Your own site
<a href="https://agentmods.dev/skills/woliveiras/geremmyas/llm-integration-review"><img src="https://agentmods.dev/badge/skills/woliveiras/geremmyas/llm-integration-review/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.

agentmods 80×15 button for llm-integration-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/woliveiras/geremmyas/llm-integration-review"><img src="https://agentmods.dev/badge/skills/woliveiras/geremmyas/llm-integration-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 332 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.00332
Opus 5 $0.00024 $0.00166
Sonnet 5 $0.00010 $0.00066
Haiku 4.5 $0.00005 $0.00033

Measured 12d ago against content hash 2ab4e032135c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

llm-integration-review 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 12d 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.

content/skills/llm-integration-review/SKILL.md · 43 lines

What it actually says

LLM Integration Review

Review LLM service boundaries before code spreads across handlers and domain logic.

Process

  1. Identify the user-facing capability, model provider, model, latency target, cost risk, and data sensitivity.
  2. Find the service boundary that owns model calls, prompts, tools, retries, and structured outputs.
  3. Verify inputs are validated and private data is minimized or redacted before logging/tracing.
  4. Prefer structured outputs for machine-read results.
  5. Define timeout, retry, backoff, rate limit, and fallback behavior.
  6. Treat tool calls as side effects: authorize, make idempotent where possible, and record audit context.
  7. Add contract tests for prompt inputs, tool schemas, structured outputs, refusals, provider errors, and retry behavior.
  8. Document operational knobs: model, temperature, token limits, and cost controls.

Rules

  • Do not put provider SDK calls directly in route handlers.
  • Do not parse critical machine-readable results from free-form prose.
  • Do not log secrets, credentials, full private documents, or raw user data.
  • Do not let model output authorize itself or choose privileged operations without application checks.

Output

  • Boundary and data-flow summary
  • Risk checklist
  • Required tests
  • Operational settings and follow-ups
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.

  1. 12d ago First seen · 43 lines · 49 tokens per session scan A 2ab4e032135c

Subscribe to this mod's changes

llm-integration-review is a skill published in the GitHub repository woliveiras/geremmyas (10 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 332 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 2026-08-31.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens