COMPETENCE_MATRIX

COMPETENCE_MATRIX is an agent for Claude Code from prikotov/task-agents-playbook. It costs 0 tokens per session (4,135 once invoked), scanned A, original, MIT.

A scored comparison of AI agents and the language models connected to them, based on the agents' self-assessments. It rates skills from 1 to 10 across areas such as PHP, Symfony, testing, Git, Docker, and web development.

In plain words
What is it for?
Reviewing agent strengths by technology, comparing model profiles, and identifying areas such as TDD, which means writing tests as part of the development process.
Why use it?
It provides a quick reference for choosing an agent for a particular technology or type of work, while showing that the scores are self-reported.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions Codex; mentions Gemini CLI; mentions OpenCode.

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

Made for: Claude Code.

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 COMPETENCE_MATRIX

README.md
[![agentmods](https://agentmods.dev/badge/agents/prikotov/task-agents-playbook/competence_matrix.svg)](https://agentmods.dev/agents/prikotov/task-agents-playbook/competence_matrix)
Your own site
<a href="https://agentmods.dev/agents/prikotov/task-agents-playbook/competence_matrix"><img src="https://agentmods.dev/badge/agents/prikotov/task-agents-playbook/competence_matrix.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,135 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00000 $0.04135
Opus 5 $0.00000 $0.02067
Sonnet 5 $0.00000 $0.00827
Haiku 4.5 $0.00000 $0.00413

Measured 6d ago against content hash 082ed7b047bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

COMPETENCE_MATRIX 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 6d 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.

docs/agents/COMPETENCE_MATRIX.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Матрица компетенций AI-агентов

Этот документ содержит структурированную оценку компетенций различных AI-агентов и подключенных к ним LLM моделей, используемых в проекте TasK. Оценки основаны на самодиагностике агентов, приведенной в их профилях. Шкала оценки: от 1 до 10.

1. Antigravity (Claude Sonnet 4.5)

Агент: Antigravity
Модель: Claude Sonnet 4.5 (Anthropic)
Описание: Мощный агент с глубоким пониманием контекста и визуальными возможностями.

Технологии

Компетенция Оценка Комментарий
PHP 8/10 Глубокие знания PHP 8.3+, readonly, enums, fibers.
Symfony 8/10 DI, Messenger, Events, Doctrine, Security.
HTML 8/10 Семантика, доступность (ARIA), современные стандарты.
CSS 7/10 Flexbox, Grid, Custom Properties.
Bootstrap 7/10 Bootstrap 5, темизация через SASS.
JS / Stimulus 7/10 ES6+, Stimulus, Turbo.
Git 8/10 Conventional Commits, Git Flow, сложные операции.
Тестирование 8/10 Unit, Integration, E2E, TDD, Mockery.
Docker 7/10 Docker Compose, работа с контейнерами.

DDD (Domain-Driven Design)

Компетенция Оценка Комментарий
Ubiquitous Language 8/10 Умение выявлять доменную терминологию.
Bounded Contexts 7/10 Понимание границ и Context Mapping.
Aggregates 8/10 Транзакционные границы, инварианты.
Entities & VOs 8/10 Проектирование неизменяемых VO и богатых сущностей.
Domain Services 8/10 Stateless сервисы для бизнес-логики.
Application Services 8/10 Оркестрация Use Cases.
Domain Events 8/10 Публикация и подписка для развязки модулей.
Repositories 8/10 Интерфейсы в Domain, реализация в Infrastructure.
Integration Patterns 7/10 ACL, Shared Kernel и др.

Архитектура и Принципы

Компетенция Оценка Комментарий
Clean Architecture 8/10 Разделение слоев, Dependency Inversion.
SOLID 9/10 Глубокое понимание, умение рефакторить нарушения.
DRY / KISS / YAGNI 8/10 Баланс между чистотой и простотой.
CQRS 7/10 Разделение команд и запросов.
12-Factor App 7/10 Принципы построения SaaS.

Read the full file on GitHub · 268 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. 6d ago First seen · 268 lines · 0 tokens per session scan A 082ed7b047bc

Subscribe to this mod's changes

COMPETENCE_MATRIX is an agent published in the GitHub repository prikotov/task-agents-playbook (21 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,135 tokens. 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.