specx AGENTS.md

specx AGENTS.md is an instructions file for Codex, OpenCode from maksimzayats/specx. It costs 1,697 tokens per session, scanned A, original, MIT.

A repository instruction file explains how to work on Specx, a Python package and skill catalog for building backend services with defined architectural boundaries.

In plain words
What is it for?
Finding the right files, running repository commands, and creating or updating skills according to the project's conventions.
Why use it?
It gives coding agents the project's purpose, layout, commands, and rules in one place.

Instructions file for CodexOpenCode

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 instructions/maksimzayats/specx/agents-md
Clone the repo
git clone --depth 1 https://github.com/maksimzayats/specx

Made for: Codex, OpenCode.

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 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/maksimzayats/specx/agents-md.svg)](https://agentmods.dev/instructions/maksimzayats/specx/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/maksimzayats/specx/agents-md"><img src="https://agentmods.dev/badge/instructions/maksimzayats/specx/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,697 This file is loaded in full into every session.
When invoked 1,697 The same file — it is already loaded in full.
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 $0.01697 $0.01697
Opus 5 $0.00848 $0.00848
Sonnet 5 $0.00339 $0.00339
Haiku 4.5 $0.00170 $0.00170

Measured 5d ago against content hash bbf6d3e9a10b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specx AGENTS.md 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 5d 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.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Repository Purpose

This repo is the specx skill catalog and Python guardrail package. It publishes reusable agent skills and a typed specx package for creating Python backend services with packaged scoped foundation bases, rule-based architecture tests, and clean core / delivery / infrastructure / ioc boundaries.

Repo Map

  • skills/<skill-name>/SKILL.md defines the skill trigger and workflow.
  • skills/<skill-name>/references/*.md contains detailed implementation patterns and examples.
  • skills/<skill-name>/agents/openai.yaml contains OpenAI skill UI metadata.
  • .agents/skills/ is the tracked local-discovery mirror of canonical skills/; update it with make sync-skills rather than editing it directly.
  • docs/ is the self-contained Storybook documentation package; its MDX pages live under docs/pages/.
  • src/specx/core/foundation/ contains reusable core foundation bases.
  • src/specx/delivery/foundation/ contains delivery foundation bases.
  • src/specx/infrastructure/foundation/ contains infrastructure foundation bases.
  • src/specx/testing/ contains the public rule-based architecture test API.
  • src/specx/_internal/ contains package internals that are not public API.
  • tests/ validates the specx package and skill helper scripts.
  • scripts/validate_skills.py validates the skill catalog.

Root Commands

  • Validate everything in the catalog and package: make check
  • Format package code: make format
  • Lint and format-check package code: make lint
  • Type-check package code: make type
  • Run package tests: make test
  • Build package distributions: make build
  • Install the Storybook documentation dependencies: npm --prefix docs ci
  • Run the Storybook documentation locally: make docs
  • Build the static Storybook documentation: make docs-build
  • Verify installed package typing: make verifytypes
  • Validate skill metadata only: make validate-skills
  • Synchronize the local skill mirror: make sync-skills
  • List local installable skills: make list-skills
  • Inspect local skills manually: npx skills add . --list --full-depth
  • Install from GitHub: npx skills add maksimzayats/specx --skill '*' --agent codex -y

Read the full file on GitHub · 133 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. 5d ago First seen · 133 lines · 1,697 tokens per session scan A bbf6d3e9a10b

Subscribe to this mod's changes

specx AGENTS.md is an instructions file published in the GitHub repository maksimzayats/specx (201 stars, last pushed 27d ago), licensed MIT. It adds 1,697 tokens to every session, about $0.0085 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.