specx-settings

specx-settings is a skill for Codex from maksimzayats/specx. It costs 63 tokens per session (557 once invoked), scanned A, original, MIT.

A guide for adding runtime configuration to a specx Python service with pydantic-settings, a library that reads and validates settings such as environment variables. It covers settings classes, example environment files, dependency injection, and the boundary between configuration and business policy.

In plain words
What is it for?
Use it to add environment-based settings, configure logging or external services, pass settings into web and infrastructure code, and convert configuration into typed business-policy values when needed.
Why use it?
It prevents configuration details from being spread through the application or injected into business code that should remain independent of deployment settings. It also makes required settings easier to document and validate.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to add environment-based settings, configure logging or external services, pass settings into web and infrastructure code, and convert configuration into typed business-policy values when needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/maksimzayats/specx/specx-settings
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 maksimzayats/specx --skill specx-settings
Clone the repo
git clone --depth 1 https://github.com/maksimzayats/specx

Made for: 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 specx-settings

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/maksimzayats/specx/specx-settings"><img src="https://agentmods.dev/badge/skills/maksimzayats/specx/specx-settings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 557 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00063 $0.00557
Opus 5 $0.00032 $0.00279
Sonnet 5 $0.00013 $0.00111
Haiku 4.5 $0.00006 $0.00056

Measured 9d ago against content hash e3514ea4e047, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

specx-settings 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 9d 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.

.agents/skills/specx-settings/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

specx Settings

Use this skill whenever runtime configuration is needed. Read references/settings.md before adding settings code.

Rules

  • Model runtime config with classes that inherit BaseRuntimeSettings.
  • Give each settings class a docstring that explains the configuration scope and includes a concrete Example:.
  • Place settings near the class that consumes them unless the setting is truly application-wide.
  • Logging settings are application-wide and live beside infrastructure/logging/configurator.py and its LoggingConfigurator.
  • Use BaseStrEnum for finite configuration values such as logging levels.
  • Inject settings objects only into delivery, infrastructure, and composition classes. Do not inject BaseRuntimeSettings subclasses into core use cases, services, capabilities, entities, repositories, or gateway ports.
  • When configuration represents a genuine business policy, map it at the composition root into a typed core value or capability that has no dependency on Pydantic or BaseRuntimeSettings.
  • Let diwire auto-register settings as root-scoped singletons. Register a settings instance explicitly only for an intentional override.
  • At operational entrypoints, load required runtime values with SettingsClass.from_environment(). Build explicit test or composition overrides with SettingsClass.model_validate({...}) so strict type checking does not mistake raw input strings for already-validated field types.
  • Do not read os.environ outside settings classes or composition code.
  • Use clear environment variable names and safe defaults only when safe.
  • Type secret fields with SecretStr, keep secrets out of examples, and unwrap them only at the adapter call that needs the raw value.
  • Update .env.example when adding user-provided environment variables.
  • Isolate settings-source tests from a developer's .env by changing to tmp_path, then override environment values with monkeypatch.
  • Do not inherit raw BaseSettings; inherit specx.infrastructure.foundation.settings.BaseRuntimeSettings.

Read the full file on GitHub · 53 lines

Files

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.

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. 9d ago First seen · 53 lines · 63 tokens per session scan A e3514ea4e047

Subscribe to this mod's changes

specx-settings is a skill published in the GitHub repository maksimzayats/specx (201 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 557 once invoked, about $0.0003 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 2026-08-30.