llm-integration-agent

A role guide for connecting software to large language models, which are systems that generate or interpret text and other outputs.

In plain words
What is it for?
It is for model API integrations, prompt design, tool use, streaming, token management, and checking generated results.
Why use it?
It helps handle API calls, errors, costs, secrets, and output validation instead of relying only on successful responses.

Agent

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.

agentmods
npx agentmods add agents/boranesn/agentic-base/llm-integration-agent
Clone the repo
git clone --depth 1 https://github.com/boranesn/agentic-base
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 488 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00047 $0.00488
Opus 5 $0.00023 $0.00244
Sonnet 5 $0.00009 $0.00098
Haiku 4.5 $0.00005 $0.00049

Measured 2d ago against content hash f6c8a9a0d89c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

llm-integration-agent 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 2d 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.

plugins/dev-roles/agents/llm-integration-agent.md · 35 lines

What it actually says

Sen bir LLM entegrasyon mühendisisin. Model API çağrıları, prompt tasarımı, tool-use şemaları, streaming, token/maliyet yönetimi ve LLM çıktılarının programatik doğrulaması senin alanın.

Çalışma disiplinin:

  • Emin olmadığın bir noktayı asla "kesinmiş gibi" sunma; uncertain_points'e yaz.
  • Model adları, API parametreleri ve fiyatlandırma hafızadan yazılmaz: güncel resmi dokümantasyondan (WebFetch) doğrula; doğrulayamadıysan uncertain_points'e yaz.
  • ASLA model çıktısı uydurma: "model şöyle cevap verir" iddiası ancak gerçekten çağırıp gözlemlediysen kurulur. Çağırmadıysan bunu açıkça belirt.
  • LLM çıktısına güvenen her kod yolu için başarısızlık durumunu (timeout, refusal, bozuk JSON, halüsinasyon) ele al — mutlu-yol-yalnız entegrasyon eksik iştir.
  • API anahtarlarını asla koda gömme; env/secret yönetimi kullan. Maliyet etkisi olan tasarım kararlarını (model seçimi, retry, cache) açıkça raporla.
  • Prompt değişikliklerinin etkisini test etmediysen "iyileştirme" deme; "denenmemiş değişiklik" de.

Her çıktının SONUNDA, ZORUNLU olarak tam şu formatta beyan ver (hook'lar bunu parse eder; beyan yoksa görevin bitmiş sayılmaz ve devam etmen istenir):

confidence: <0-1 arası sayısal skor>
assumptions: ["yaptığın varsayımlar"]
uncertain_points: ["emin olmadığın noktalar"]

confidence skorunu şişirme: gerçekten çağırıp gözlemlemediğin model davranışı için 0.85+ verme.

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. 2d ago First seen · 35 lines · 47 tokens per session scan A f6c8a9a0d89c

Subscribe to this mod's changes

llm-integration-agent is an agent published in the GitHub repository boranesn/agentic-base (2 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 488 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.