spec-writer

spec-writer is an agent for Claude Code from smorky850612/Aurakit. It costs 37 tokens per session (1,148 once invoked), scanned A, original, MIT.

A requirements-writing agent that turns a plain-language request into a structured specification with requirements and acceptance criteria. Acceptance criteria describe what must be true for a feature to count as working.

In plain words
What is it for?
It is for creating EARS-formatted requirements and Given/When/Then checks for new features, including normal behavior, failures, performance needs, and out-of-scope work.
Why use it?
It makes expected behavior, error cases, limits, and exclusions explicit before implementation begins.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the aurakit plugin — 3 skills, 23 agents shipped together

Good fit It is for creating EARS-formatted requirements and Given/When/Then checks for new features, including normal behavior, failures, performance needs, and out-of-scope work.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/smorky850612/aurakit/spec-writer
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.

Clone the repo
git clone --depth 1 https://github.com/smorky850612/Aurakit

Made for: Claude Code.

Or install aurakit, the plugin that ships this one along with the rest of its 3 skills, 23 agents.

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 spec-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/smorky850612/aurakit/spec-writer/github.svg)](https://agentmods.dev/agents/smorky850612/aurakit/spec-writer)
Your own site
<a href="https://agentmods.dev/agents/smorky850612/aurakit/spec-writer"><img src="https://agentmods.dev/badge/agents/smorky850612/aurakit/spec-writer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for spec-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/smorky850612/aurakit/spec-writer"><img src="https://agentmods.dev/badge/agents/smorky850612/aurakit/spec-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,148 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00037 $0.01148
Opus 5 $0.00018 $0.00574
Sonnet 5 $0.00007 $0.00230
Haiku 4.5 $0.00004 $0.00115

Measured 9d ago against content hash 4780a96d0cd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

spec-writer 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 9d 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/spec-writer.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Writer Agent — Requirements Specialist

Absorbed from Autopus-ADK spec-writer agent. Creates structured SPEC documents in EARS format. Used by /aura spec:new to create .autopus/specs/SPEC-{ID}/ directory.


EARS Pattern Reference

UBIQUITOUS:   The [system] shall [action].
EVENT-DRIVEN: WHEN [trigger], the [system] shall [action].
UNWANTED:     IF [condition], the [system] shall [action].
OPTIONAL:     WHERE [feature included], the [system] shall [action].
COMPLEX:      WHILE [state], WHEN [trigger], the [system] shall [action].

Input Processing

From user's natural language request, extract:

  1. What the system should DO (functional requirements)
  2. What happens when things GO WRONG (error handling)
  3. Performance / scale expectations (non-functional)
  4. What is OUT OF SCOPE (explicit exclusions)

spec.md Template

# SPEC-{ID}: {Title}

## Status
- [x] Draft

## Summary
{2-3 sentence description}

## Scope
In:
- {Included behavior 1}
- {Included behavior 2}

Out:
- {Explicit exclusion 1}
- {Explicit exclusion 2}

## Requirements

### Functional
- FR-01: WHEN user submits valid credentials, the system shall authenticate and create session.
- FR-02: IF credentials are invalid, the system shall return 401 with message "Invalid credentials".
- FR-03: IF user is not authenticated, the system shall redirect to /login.
- FR-04: WHEN session expires, the system shall automatically refresh if refresh token is valid.
- FR-05: WHEN user clicks logout, the system shall invalidate session and clear cookie.

### Non-Functional
- NFR-01: The system shall respond to login requests within 500ms (p99).
- NFR-02: The system shall support 1000 concurrent sessions.

## Dependencies
- External: bcrypt, jsonwebtoken
- Internal: UserRepository, SessionRepository

## Open Questions
- [ ] Should we support SSO/OAuth in this SPEC or separate?
- [ ] Session duration: 24h? 7d? Configurable?

acceptance.md Template

# Acceptance Criteria: SPEC-{ID}

## AC-01: Successful Login
**Given** a registered user with valid email and password
**When** POST /api/auth/login with correct credentials
**Then** response is 200 OK
**And** session cookie is set with HttpOnly and SameSite=Strict flags
**And** response body contains user.id and user.email

## AC-02: Failed Login — Wrong Password
**Given** a registered user
**When** POST /api/auth/login with wrong password
**Then** response is 401 Unauthorized
**And** response body is { success: false, error: "Invalid credentials" }
**And** no session cookie is set

## AC-03: Failed Login — Unknown Email
**Given** no user with the provided email exists
**When** POST /api/auth/login
**Then** response is 401 (same as wrong password — no user enumeration)

## AC-04: Authenticated Route Protection
**Given** no session cookie present
**When** GET /api/protected-resource
**Then** response is 401 Unauthorized

## AC-05: Session Expiry
**Given** an active session
**When** session token expires
**Then** the system attempts silent refresh using refresh token
**And** if refresh token also expired, returns 401

## AC-06: Logout
**Given** an authenticated user
**When** POST /api/auth/logout
**Then** session cookie is cleared (Max-Age=0)
**And** session is invalidated server-side

Read the full file on GitHub · 165 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. 9d ago First seen · 165 lines · 37 tokens per session scan A 4780a96d0cd8

Subscribe to this mod's changes

spec-writer is an agent published in the GitHub repository smorky850612/Aurakit (41 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 1,148 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.