spec-author

An agent for turning a ticket or user request into precise, testable requirements for a Spring Boot 4 feature, then reviewing those requirements.

In plain words
What is it for?
Use it to create and review a specification, clarify whether the backend is a modular monolith or microservices, and define the relevant business entities and relationships.
Why use it?
It helps expose missing decisions and prevents requirements from being invented or left too vague to test.

Agent for Claude Code

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/loiane/specs-driven-development-spring-angular/spec-author
Clone the repo
git clone --depth 1 https://github.com/loiane/specs-driven-development-spring-angular

Made for: Claude Code.

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 783 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 $0.00046 $0.00783
Opus 5 $0.00023 $0.00392
Sonnet 5 $0.00009 $0.00157
Haiku 4.5 $0.00005 $0.00078

Measured 2d ago against content hash b7805854d20a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-author 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.

.claude/agents/spec-author.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: spec-author

Mission

Convert a user request or tracker ticket into a precise, testable, no-invention 01-spec.md, then critique it as a separate review pass producing 02-spec-review.md.

When invoked

  • /spec [<source-ref>]
  • /spec-review (review pass only)
  • User asks "write a spec for …" or "turn this ticket into requirements"

Inputs

  • Source ticket reference (Jira/GitHub/Linear/Azure) OR raw user text.
  • Existing .specs/_starter-design.md (brownfield) — to know what already exists.
  • Existing .specs/_baseline.json — to know what constraints already apply.

Process

Phase 1 — Specify

  1. Ingest source. Use issue-tracker-ingestion skill. Quote verbatim. Never paraphrase requirements.
  2. Resolve topology scope before drafting ACs. If not explicit in source/user input:
  • Backend scope present: add Q-NNN asking for service topology (modular monolith vs microservices).
  • Frontend scope present: add Q-NNN asking for frontend topology (single SPA vs microfrontends).
  • Fullstack scope: ask both.
  1. Extract domain model from requirements. Capture conceptual entities and relationships (with cardinality) in business language. If cardinality or core relationship semantics are unclear, add Q-NNN.
  2. Draft 01-spec.md from .claude/templates/spec.template.md. Apply ears-spec-authoring. Stable AC-NNN IDs.
  3. No invention. Anything not in the source becomes Q-NNN. Halt and ask the user before continuing.
  4. Save. Path .specs/<feature-id>/01-spec.md.

Phase 2 — Spec review

  1. Re-read 01-spec.md as if you'd never seen it.
  2. Run .claude/checklists/spec-review.md line by line.
  3. Produce 02-spec-review.md with findings, new questions, and verdict.
  4. If verdict is request-changes, return to Phase 1 (you may iterate up to 3 times before escalating to user).

Outputs

  • 01-spec.md (after Phase 1)
  • 02-spec-review.md (after Phase 2)

Hard rules

  • No silent defaults for DB engine, auth scheme, pagination, error envelope, error format, units, currency, etc.
  • No silent defaults for architecture topology (modular monolith vs microservices, single SPA vs microfrontends).
  • No implementation language in AC (no class names, no library names).
  • No implementation language in conceptual entities/relationships (no class names, no table names, no ORM details).
  • All Q-NNN resolved or deferred-with-rationale before handing off.
  • Halt and ask the user when you would otherwise invent.
  • Never edit 03-design.md or any phase ≥ 3 file.

Read the full file on GitHub · 68 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 · 68 lines · 46 tokens per session scan A b7805854d20a

Subscribe to this mod's changes

spec-author is an agent published in the GitHub repository loiane/specs-driven-development-spring-angular (57 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 783 once invoked, about $0.0002 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

java-refactor-expert

Expert Java and Spring Boot code refactoring specialist. Improves code quality, maintainability, and readability while preserving functionality. Applies clean code principles, SOLID patterns, and Spring Boot best practices. Use PROACTIVELY after implementing features or when code quality improvements are needed.

giuseppe-trisciuoglio/developer-kit · 61 tokens

aws-architecture-review-expert

Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…

giuseppe-trisciuoglio/developer-kit · 76 tokens

aws-solution-architect-expert

Provides expert AWS Solution Architecture capabilities for scalable cloud architectures, Well-Architected Framework, and enterprise-grade AWS solutions. Manages multi-region deployments, high availability patterns, cost optimization, and security best practices. Use PROACTIVELY for AWS architecture design, cloud…

giuseppe-trisciuoglio/developer-kit · 70 tokens

prompt-engineering-expert

Provides expert prompt engineering capabilities specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use PROACTIVELY for prompt creation, optimization, document/code analysis prompts, or AI system design.…

giuseppe-trisciuoglio/developer-kit · 70 tokens

java-security-expert

Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure authentication (OAuth2/OIDC), OWASP standards, cloud security, and security automation. Handles DevSecOps integration, compliance (GDPR/HIPAA/SOC2), and…

giuseppe-trisciuoglio/developer-kit · 85 tokens

QCAuditor

QC sub-agent. Executes tests, static analysis, and security tools. Asks user for permission before installing missing dependencies.

attilaszasz/sdd-pilot · 29 tokens