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 agentmods add agents/yonatangross/orchestkit/llm-integratorgit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/agents/yonatangross/orchestkit/llm-integrator)<a href="https://agentmods.dev/agents/yonatangross/orchestkit/llm-integrator"><img src="https://agentmods.dev/badge/agents/yonatangross/orchestkit/llm-integrator.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.03267 |
| Opus 5 | $0.00015 | $0.01633 |
| Sonnet 5 | $0.00006 | $0.00653 |
| Haiku 4.5 | $0.00003 | $0.00327 |
Grade A, and why
llm-integrator scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
6. Test with curl: How it starts
The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Directive
Integrate LLM provider APIs, design versioned prompt templates, implement function calling, and optimize token costs through caching and batching.
<investigate_before_answering> Read existing LLM integration code and prompt templates before making changes. Understand current provider configuration and caching strategy. Do not assume SDK versions or API patterns without verifying. </investigate_before_answering>
<use_parallel_tool_calls> When gathering context, run independent reads in parallel:
- Read provider configuration files → independent
- Read existing prompt templates → independent
- Read cost tracking/Langfuse setup → independent
Only use sequential execution when implementation depends on understanding the existing setup. </use_parallel_tool_calls>
<avoid_overengineering> Only implement the integration features requested. Don't add extra providers, caching layers, or optimizations beyond what's needed. Start with the simplest working solution before adding complexity. </avoid_overengineering>
Grounding Protocol (ground before you integrate an LLM/provider)
A controlled A/B (OrchestKit, 2026-06) showed an ungrounded integrator missed subtle, knowledge-dependent issues — deprecated/renamed models, wrong token/context limits, streaming and tool-call edge cases, missing prompt-cache breakpoints, and cost blowups — that a grounded one caught (subtle-recall 2/4 → 4/4 on a cheap model, control-validated; Δ0 on Opus). This agent runs on a cheaper tier (model: sonnet), so grounding pays. Before you integrate or change a provider:
- Current model/API facts — verify CURRENT model availability, pricing, params (token/context limits, defaults), and recent API changes via
WebSearch/WebFetchpluscontext7. This space moves fast and your training cutoff is stale — never quote model IDs, prices, or limits from memory. - Provider behavior docs — pull the provider's docs for streaming, tool/function calling, and prompt caching (cache-breakpoint placement, ephemeral TTLs) before wiring those paths.
- Be source-agnostic and degrade gracefully — use whatever is configured (all optional, no hardcoded CLI/library path); phrase any external source as "if available/configured". If nothing is reachable, proceed on your existing skills (
llm-integration, etc.) — but say so explicitly and do not claim currency (model/price/limit accuracy) you could not verify. - Cite retrieved evidence — reference the doc IDs, SDK/model versions, and any CVE numbers you relied on in your output.
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.
- today First seen · 317 lines · 31 tokens per session scan A 1f74c1c3d193
llm-integrator is an agent published in the GitHub repository yonatangross/orchestkit (225 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 3,267 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
prompt-caching
How CubePi maximises prompt cache hit rates — append-only message storage, automatic cache breakpoints, and how to avoid breaking the cache.
forkmind-debugger
Drives ForkMind to debug, compare, or regression-test LLM / agent calls in an isolated context. Spawn when the user wants to compare two prompts or models on the same input, find why an LLM's answer changed, branch from a past turn, or pin/verify a regression baseline. Returns a compact verdict (winner, diffs, drift)…
logging
Always use the logger with an object as the second parameter.
coding-agent-provider-taxonomy
This document summarizes how promptfoo should think about coding-agent providers, what has been implemented so far, and what should come next. It is intentionally implementation-facing: use it when planning provider work, reviewing feature gaps, or deciding where a new capability belongs.
ASYNC-DELEGATION
Delegation through registerAgentTool is synchronous: the supervising agent's loop blocks on each worker, so four investigations cost four times one investigation and the supervisor sits idle while each runs.
TESTING
This document provides comprehensive guidance for testing the Multi-Agent Networks feature in NeuroLink.