agentmods.dev

llm-architect

llm-architect is a skill for Claude Code, Codex from johnefemer/skillfish. It costs 0 tokens per session (13,686 once invoked), scanned A, original, no licence file.

A guide to designing systems that use large language models, which are AI systems that generate and understand text. It covers choosing models, adapting them, managing context, routing requests between models, and analysing costs.

In plain words
What is it for?
Use it to plan LLM architectures, fine-tuning, inference performance, context handling, multi-model routing, and cost analysis.
Why use it?
It helps turn model choices and system trade-offs into an explicit design instead of leaving them to trial and error.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

not rated 4repo 4d ago A scan 0 tokens no licence

Good fit Use it to plan LLM architectures, fine-tuning, inference performance, context handling, multi-model routing, and cost analysis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/johnefemer/skillfish/llm-architect
View source ↗ johnefemer/skillfish coach.omazy.ai
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 johnefemer/skillfish --skill llm-architect
Clone the repo
git clone --depth 1 https://github.com/johnefemer/skillfish

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-architect

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/johnefemer/skillfish/llm-architect"><img src="https://agentmods.dev/badge/skills/johnefemer/skillfish/llm-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,686 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00000 $0.13686
Opus 5.5 $0.00000 $0.05474
Sonnet 5.5 $0.00000 $0.02737
Haiku 4.5 $0.00000 $0.01369

Measured 2mo ago against content hash e23d0c2a2a44, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

llm-architect 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
skills/llm-architect/SKILL.md · 1,731 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 2mo ago First seen · 1,731 lines · 0 tokens per session scan A e23d0c2a2a44

Subscribe to this mod's changes

llm-architect is a skill published in the GitHub repository johnefemer/skillfish (4 stars, last pushed 4d ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 13,686 tokens. 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.

Data and AI
Related

llm-architect compared with skills from other repositories

llm-architect next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
llm-architectjohnefemer/skillfishSkill44d agononeA0Claude Code, Codex
agent-platform-model-registrygoogle/skillsSkill22kyesterdayApache-2.0A60Claude Code, Codex
foundry-config-setupmicrosoft/agent-frameworkSkill15kyesterdayMITA65Claude Code, Codex
google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skillsSkill22kyesterdayApache-2.0A132Claude Code, Codex
training-checkwanshuiyin/Auto-claude-code-research-in-sleepSkill19k3d agoMITA35Claude Code
nemo-automodel-launcher-configNVIDIA/skillsSkill3.9kyesterdayApache-2.0A30Claude Code
finetuningmicrosoft/skillsSkill3.2kyesterdayMITA132Claude Code