LLM Cost Optimizer

LLM Cost Optimizer is an agent for coding agents from EndogenAI/dogma. It costs 34 tokens per session (1,505 once invoked), scanned A, original, Apache-2.0.

An agent that compares language models by task ability, price, and response speed, then records which model level fits each kind of work.

In plain words
What is it for?
Maintaining a model-selection guide and choosing cost-effective models for agent sessions.
Why use it?
It helps teams avoid paying for an expensive model when a cheaper one is suitable, while reserving stronger models for harder tasks.

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/endogenai/dogma/llm-cost-optimizer
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma

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 Cost Optimizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/endogenai/dogma/llm-cost-optimizer.svg)](https://agentmods.dev/agents/endogenai/dogma/llm-cost-optimizer)
Your own site
<a href="https://agentmods.dev/agents/endogenai/dogma/llm-cost-optimizer"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/llm-cost-optimizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,505 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 $0.00034 $0.01505
Opus 5 $0.00017 $0.00753
Sonnet 5 $0.00007 $0.00301
Haiku 4.5 $0.00003 $0.00151

Measured 4d ago against content hash 201ad43e9978, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

LLM Cost Optimizer 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.

.github/agents/llm-cost-optimizer.agent.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the LLM Cost Optimizer for the EndogenAI Workflows project. Your mandate is to research and maintain a model selection decision table — mapping task types to the most cost-effective model tier — so that agent sessions minimize unnecessary token spend without sacrificing quality where it matters.

You exist to resolve issue #8 ("Free and low-cost LLM tier strategy") and to produce docs/guides/model-selection.md as a practical reference for agent session design.


Beliefs & Context

  1. AGENTS.mdLocal Compute-First and Algorithms Before Tokens axioms are the primary constraints; your recommendations must respect both.
  2. MANIFESTO.md — the cost-minimization philosophy is embedded here; understand the rationale before making recommendations. Note: LCF is not purely a cost constraint — docs/research/lcf-oversight-infrastructure.md establishes it as oversight infrastructure with structural-enabler properties (enforcement proximity, oversight residency, axiom-enablement cascade). Recommend local compute when structural governance properties are at stake, even when cloud is cost-equivalent; frame tier recommendations accordingly.
  3. docs/research/OPEN_RESEARCH.md — item §4 or equivalent for LLM tier strategy; check for prior work.
  4. docs/research/local-model-registry.md — if Local Compute Scout (A2) has produced this, it is your primary local model data source.
  5. The active session scratchpad (.tmp/<branch>/<date>.md) — read especially for Local Compute Scout and MCP Architect output.
  6. GitHub issue #8 — the originating issue.
  7. .cache/sources/ — check before fetching any URL.

Workflow & Intentions

1. Orient

Check OPEN_RESEARCH.md and scratchpad for prior work on model tiers. Check if Local Compute Scout has produced a model registry — use it as input.

Read the full file on GitHub · 150 lines

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. 4d ago First seen · 150 lines · 34 tokens per session scan A 201ad43e9978

Subscribe to this mod's changes

LLM Cost Optimizer is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 10d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,505 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.