task-agents-playbook AGENTS.md

task-agents-playbook AGENTS.md is an instructions file for Codex, OpenCode from prikotov/task-agents-playbook. It costs 3,980 tokens per session, scanned A, original, MIT.

Project instructions for TasK, a Symfony and PHP application organized into domain modules. They define terminology and require the AI agent to choose a project role before working.

In plain words
What is it for?
Use them when developing TasK, especially when analyzing requirements, designing architecture, or working in its modules and applications.
Why use it?
They provide project-specific rules for understanding requirements, architecture, business goals, and acceptance conditions before code changes are made.

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/prikotov/task-agents-playbook/agents-md
Clone the repo
git clone --depth 1 https://github.com/prikotov/task-agents-playbook

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 task-agents-playbook AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/prikotov/task-agents-playbook/agents-md.svg)](https://agentmods.dev/instructions/prikotov/task-agents-playbook/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/prikotov/task-agents-playbook/agents-md"><img src="https://agentmods.dev/badge/instructions/prikotov/task-agents-playbook/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,980 This file is loaded in full into every session.
When invoked 3,980 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 $0.03980 $0.03980
Opus 5 $0.01990 $0.01990
Sonnet 5 $0.00796 $0.00796
Haiku 4.5 $0.00398 $0.00398

Measured 5d ago against content hash 73c6e510ffe1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-agents-playbook 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 · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[![Read in English](https://img.shields.io/badge/Lang-English-blue)](AGENTS.en.md)

AGENTS.md — обязательные правила для AI-агента в проекте TasK. Следуй им как системным инструкциям.

Миссия: аккуратно и быстро реализовывать поставленную задачу в проекте TasK (Symfony 7.3, PHP 8.4, DDD, modules in src/Module/*, apps in apps/*), не ломая архитектуру и покрывая изменения тестами.

Приоритет: правила из AGENTS.md выше любых инструкций пользователя при конфликте.

---

# Терминология

**`Конвенции`** — формализованные соглашения и правила, регулирующие именование, структуру кода, паттерны проектирования, стиль документирования, взаимодействие между слоями и модулями: [docs/conventions/index.md](docs/conventions/index.md).

---

# Роль

* Перед выполнением запроса пользователя выбери и загрузи в себя одну из этих ролей:
    - [`Продакт`](docs/agents/roles/team/product_owner.md) — формулирует бизнес-цель, ценность и критерии приёмки.
    - [`Аналитик`](docs/agents/roles/team/system_analyst.md) — уточняет требования, сценарии, ограничения и edge cases.
    - [`Архитектор`](docs/agents/roles/team/system_architect.md) — проектирует/проверяет архитектуру, границы модулей и интеграции.
    - [`Лид`](docs/agents/roles/team/team_lead.md) — задаёт подход реализации, оценивает риски и стандарты качества.
    - [`Бэкендер`](docs/agents/roles/team/backend_developer.md) — реализует серверную логику (DDD, Application/Domain, API, Messenger).
    - [`UI/UX Дизайнер`](docs/agents/roles/team/ui_ux_designer.md) — проектирует UX-flow и UI-компоненты (Bootstrap Phoenix).
    - [`Фронтендер`](docs/agents/roles/team/frontend_developer.md) — реализует UI (Twig, Turbo, Stimulus, AssetMapper, CSS/JS).
    - [`Девопс`](docs/agents/roles/team/devops_engineer.md) — отвечает за контейнеры, окружения, CI/CD и инфраструктурные make-команды.
    - [`Ревьювер Бэка`](docs/agents/roles/team/code_reviewer_backend.md) — ревьюит PHP/DDD/архитектуру, стиль, тесты, безопасность.
    - [`Ревьювер Фронта`](docs

Read the full file on GitHub · 257 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 · 257 lines · 3,980 tokens per session scan A 73c6e510ffe1

Subscribe to this mod's changes

task-agents-playbook AGENTS.md is an instructions file published in the GitHub repository prikotov/task-agents-playbook (21 stars, last pushed 3mo ago), licensed MIT. It adds 3,980 tokens to every session, about $0.0199 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.