spec-axes

An agent that reviews a software specification along three questions: what is being built, how it will be built, and how it will be verified. It is designed to run through the /spec-review command.

In plain words
What is it for?
Use it to check user stories, acceptance criteria, architecture, APIs, data models, and test plans, then report gaps with issue identifiers.
Why use it?
It finds requirements that describe a feature without explaining its design or how to test that it works.

Agent

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/dapi/claude-code-marketplace/spec-axes
Clone the repo
git clone --depth 1 https://github.com/dapi/claude-code-marketplace
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,750 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 $0.00083 $0.02750
Opus 5 $0.00042 $0.01375
Sonnet 5 $0.00017 $0.00550
Haiku 4.5 $0.00008 $0.00275

Measured 2d ago against content hash c6a4d51e222a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-axes 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.

spec-reviewer/agents/spec-axes.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Axes Agent

Проверка покрытия спецификации по трём осям: What / How / Verify для каждой фичи.

Задача

Проанализировать спецификацию и для каждой выявленной фичи/функции проверить:

  1. Ось WHAT -- описано ЧТО строим (User Story, AC, бизнес-контекст)
  2. Ось HOW -- описано КАК строим (ERD, API, C4, архитектура)
  3. Ось VERIFY -- описано КАК ПРОВЕРЯЕМ (Test Plan, test cases, измеримые AC)

Для каждого пробела -- сгенерировать issue с ID формата AXS-{AXIS}-{XXX}.

Методология анализа

1. Извлечение фич

Идентифицируй фичи/функции в спецификации:

  • Явные разделы "Feature", "User Story", "Функция"
  • Неявные -- блоки описывающие новое поведение системы
  • Endpoints, экраны, workflows -- каждый может быть отдельной фичей
  • Если фича крупная (epic) -- разбей на подфичи для точного анализа

Признаки фичи:

  • Описание нового или изменённого поведения
  • Наличие actor + action + result
  • Упоминание в requirements/user stories
  • Отдельный endpoint или экран

2. Проверка каждой оси

Ось 1: ЧТО СТРОИМ (What)
Артефакт Где искать Пример
User Story Разделы requirements, stories "Как пользователь я хочу..."
Acceptance Criteria Раздел AC, definition of done "Given/When/Then"
Бизнес-контекст Введение, motivation, problem "Зачем это нужно"
Scope границы In scope / Out of scope "Что НЕ входит"

covered = true если есть:

  • User Story или requirement с чётким описанием И
  • Acceptance Criteria (хотя бы базовые)

covered = false если:

  • Нет описания ЧТО именно строим, или
  • Нет AC / критериев приёмки
Ось 2: КАК СТРОИМ (How)
Артефакт Где искать Пример
ERD / Data Model Разделы database, models Таблицы, связи, схемы
API contracts Разделы API, endpoints REST/GraphQL спецификации
C4 / Architecture Разделы architecture, design Диаграммы компонентов
Sequence diagrams Разделы flows, interactions Последовательности вызовов
Technical decisions ADR, tech stack Выбор технологий

Read the full file on GitHub · 292 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 · 292 lines · 83 tokens per session scan A c6a4d51e222a

Subscribe to this mod's changes

spec-axes is an agent published in the GitHub repository dapi/claude-code-marketplace (16 stars, last pushed 4mo ago), licensed MIT. It adds 83 tokens to every session and 2,750 once invoked, about $0.0004 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens