agentmods.dev

codex-agent-core-template AGENTS.md

Project instructions for an AI agent that manages a local knowledge system and separates shared agent rules from project-specific information. A knowledge system is an organized set of files used to store and retrieve information.

In plain words
What is it for?
It is for guiding an agent through reading, organizing, checking, linking, and updating knowledge files safely.
Why use it?
It tells the agent which rules and project context to load, how to handle approvals, and what to do when no project has been selected.

Instructions file for CodexOpenCode

11 2mo ago A scan 2,620 tokens original MIT
View the source file TheMuleA/codex-agent-core-template
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/themulea/codex-agent-core-template/agents-md
Clone the repo
git clone --depth 1 https://github.com/TheMuleA/codex-agent-core-template

Made for: Codex, OpenCode.

Per session 2,620 This file is loaded in full into every session.
When invoked 2,620 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 $0.02620 $0.02620
Opus 5 $0.01310 $0.01310
Sonnet 5 $0.00524 $0.00524
Haiku 4.5 $0.00262 $0.00262

Measured 2d ago against content hash d61c1642bc70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-agent-core-template 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 2d 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 · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Правила локального агента

Миссия

Этот vault — локальная knowledge system для Agent Core и выбираемых project layers. Основной ожидаемый AI host — Codex app; дополнительные hosts могут подключаться через host-specific adapter files и не меняют канон Agent Core.

Цель агента: безопасно читать, структурировать, связывать, проверять и обновлять знания в файлах проекта только через согласованный approval-first протокол.

Project layer по умолчанию не задан. Agent Core загружается всегда, а рабочий project layer выбирается пользователем из реестра projects/index.md.

Агент и проект

  • Агентская часть: правила, протоколы, skills, безопасность, ingest/query/lint, связи, источники, planning и logs. Основной слой: agent/.
  • Проектная часть: предметный контекст текущего применения агента. Основной слой: projects/<project_id>/.
  • Agent Core загружается всегда в начале рабочей сессии.
  • Project Layer выбирается отдельно пользователем после загрузки Agent Core.
  • projects/_template/ не является active project.
  • Если project layer не выбран, агент не входит в проектную роль, кратко показывает доступные project layers из projects/index.md и ждёт выбора пользователя.
  • Агент работает только с выбранным project layer и игнорирует остальные без явного запроса.
  • Перед предложением изменения агент определяет тип: Agent Core change, Project change, Infrastructure change или Output change.
  • Нельзя смешивать агентские и проектные изменения в одной операции без явного подтверждения пользователя.

Язык

Основной язык проекта — русский. Системные названия папок и некоторые термины могут быть на английском, если они описаны в agent/model/terms-and-folders.md.

Зоны файлов

  • agent/ — Agent Core: модель, протоколы, planning, work plans, logs и skills index.
  • .agents/skills/ — локальные procedural skills текущего vault.
  • projects/ — project layers; projects/_template/ является только публичным шаблоном.
  • raw/ — неизменяемые исходники и source assets.
  • output/ — временные результаты, черновики и отчёты.
  • agent/logs/ — журналы Agent Core / infrastructure scope; в публичном шаблоне заполненные log-файлы могут отсутствовать и создаются при первой подтверждённой записи.
  • projects/<project_id>/logs/ — журналы выбранного project scope.
  • .archive/ — локальный исторический архив; не является рабочими инструкциями или project data.
  • .obsidian/ — локальное состояние Obsidian; папку не удалять и не включать в Git.
  • index.md — главный навигационный индекс.

Read the full file on GitHub · 139 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. 2d ago First seen · 139 lines · 2,620 tokens per session scan A d61c1642bc70

Subscribe to this mod's changes

codex-agent-core-template AGENTS.md is an instructions file published in the GitHub repository TheMuleA/codex-agent-core-template (11 stars, last pushed 2mo ago), licensed MIT. It adds 2,620 tokens to every session, about $0.0131 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens