claude-codex-settings is a collection of configurations and reusable extensions for Claude Code, OpenAI Codex, Cursor, and related coding tools. Developers use its skills, commands, hooks, agents, plugins, and MCP servers to shape coding-agent workflows and connect alternative model APIs. The catalogue entries are components of this collection that can be installed into supported coding tools.
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 skills/fcakyon/claude-codex-settings/yolo-trainingnpx skills add fcakyon/claude-codex-settings --skill yolo-traininggit clone --depth 1 https://github.com/fcakyon/claude-codex-settingsWrote 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/skills/fcakyon/claude-codex-settings/yolo-training)<a href="https://agentmods.dev/skills/fcakyon/claude-codex-settings/yolo-training"><img src="https://agentmods.dev/badge/skills/fcakyon/claude-codex-settings/yolo-training.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 | $0.00124 | $0.01410 |
| Opus 5 | $0.00062 | $0.00705 |
| Sonnet 5 | $0.00025 | $0.00282 |
| Haiku 4.5 | $0.00012 | $0.00141 |
Grade A, and why
yolo-training 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YOLO26 training
Read the run before changing anything. The results.csv and confusion matrix usually name the
problem already.
Order of operations
Ordered by cost to try, cheapest first, not by size of the potential win.
- Epochs and schedule. Undertrained looks like every other problem, and it costs nothing but time to rule out.
- Augmentation. The knob for the generalization gap, at no extra compute per epoch.
- Loss weights and LR. Cheap, and the curves usually say which one is wrong.
- Model size. Scale up when train loss is still falling at the end of the schedule and the train and val curves sit close together. That is underfitting, and it is the only case a bigger model reliably fixes.
- Resolution. Compute scales with the square of
imgsz, so 640 to 1280 is roughly 4x the training budget, and pretrained weights transfer worse the further you move from the size they were fit at. Justify it with the object sizes in your data, not as a default first move. - Data, label quality and class balance. The highest ceiling and the slowest to move. The package ships no dataset-analysis tooling, so any audit here is your own script plus looking at images. Worth it once the cheap knobs are spent.
Diagnostic loop
import pandas as pd
df = pd.read_csv("runs/detect/train/results.csv")
df.columns = df.columns.str.strip()
print(df.tail(10)[["epoch", "train/box_loss", "val/box_loss", "metrics/mAP50(B)", "metrics/mAP50-95(B)"]])
print("best epoch:", df["metrics/mAP50-95(B)"].idxmax(), "of", len(df))
Then read, in this order:
| Read | Question it answers |
|---|---|
| best epoch vs total epochs | undertrained, overtrained, or right |
| train loss vs val loss trend | which side of the generalization gap |
| mAP50 vs mAP50-95 | classification and recall vs localization |
| P vs R at the operating point | over-suppression vs over-firing |
| per-class AP spread | one broken class or a general weakness |
| confusion matrix background row and column | false positives vs missed detections |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 97 lines · 124 tokens per session scan A 583bc50d6995
yolo-training is a skill published in the GitHub repository fcakyon/claude-codex-settings (1,127 stars, last pushed today), licensed Apache-2.0. It adds 124 tokens to every session and 1,410 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
voiceprint-tech
你是一位声纹识别系统架构师,以《声纹技术》的工程视角帮助用户完成从算法选型到产品落地的技术决策。声纹识别的成败不只在模型结构,更在预处理、后端评分、部署架构与反欺诈的完整链路。.
sqlite-vec-skilld
ALWAYS use when writing code importing "sqlite-vec". Consult for debugging, best practices, or modifying sqlite-vec, sqlite vec.
sgc-install-ai
为现有或新 App 快速初始化可上线的 AI 功能，可选择本地 Agent Client、MaaS 中转渠道、模型偏好和配套 UI。用户说集成 AI、给 App 加聊天/生成能力、Agent Client、MaaS 或模型选择时使用。.
template-autoresearch-project
AutoResearch loop exemplar — deterministic ML candidate evaluation, evidence registries, claim ledgers, artifact manifests, readiness gates.
doc-to-lora-evaluator
Evaluate whether Doc-to-LoRA is the right path for turning documents into parametric memory, and guide a safe proof-of-concept before investing in a full plugin or training pipeline. Use when a user wants to internalize long documents, reduce repeated context costs, compare Doc-to-LoRA against RAG or long-context…
bioinformatics-scientist
Use when a task needs the judgment of a Bioinformatics Scientist — designing a differential-expression or GWAS analysis with correct multiple-testing correction, calling and triaging variants from NGS data using genotype-likelihood confidence rather than raw allele counts, interpreting a BLAST/DIAMOND homology search…