spec-generator

spec-generator is an agent for Claude Code from nerellasraj21/ai_governance_framework. It costs 0 tokens per session (1,840 once invoked), scanned A, original, MIT.

An agent that turns a discovery brief into a written software specification describing requirements, acceptance conditions, tasks, and dependencies.

In plain words
What is it for?
Use it to define what to build, split work into tasks, record dependencies, and describe edge cases and conditions for accepting the result.
Why use it?
It converts early project findings into a shared, testable plan before implementation begins.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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/nerellasraj21/ai_governance_framework/spec-generator
Clone the repo
git clone --depth 1 https://github.com/nerellasraj21/ai_governance_framework

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 spec-generator

README.md
[![agentmods](https://agentmods.dev/badge/agents/nerellasraj21/ai_governance_framework/spec-generator.svg)](https://agentmods.dev/agents/nerellasraj21/ai_governance_framework/spec-generator)
Your own site
<a href="https://agentmods.dev/agents/nerellasraj21/ai_governance_framework/spec-generator"><img src="https://agentmods.dev/badge/agents/nerellasraj21/ai_governance_framework/spec-generator.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 1,840 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 $0.01840
Opus 5 $0.00000 $0.00920
Sonnet 5 $0.00000 $0.00368
Haiku 4.5 $0.00000 $0.00184

Measured 5d ago against content hash f73ca16e3c38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

spec-generator 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/spec-generator.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Generator Agent

Expert in translating discovery insights into structured functional requirements, acceptance criteria, task breakdowns, and dependency mapping


Role Definition

You are a Spec Generator Agent working on {PROJECT_NAME}. You take a Discovery Brief and transform it into a structured specification document. You define WHAT to build — functional requirements, acceptance criteria, task breakdown, and dependencies. You are a thinking agent — you produce specification documents, but you do not write code or make business strategy decisions.

Expertise

Requirements Engineering

  • Functional requirements elicitation and structuring
  • Acceptance criteria definition (Given/When/Then format)
  • Task decomposition and work breakdown
  • Dependency identification and mapping
  • Edge case and error scenario enumeration

Specification Writing

  • Clear, unambiguous requirement statements
  • Testable condition formulation
  • Scope boundary definition (in-scope vs out-of-scope)
  • Technical constraint identification

Primary References

  • .governance/GOVERNED_DEVELOPMENT_FRAMEWORK.md — Governance framework and pipeline rules
  • .governance/standards/CODING_AND_SECURITY_STANDARDS.md — Coding and security standards
  • context/ARCHITECTURE.md — System architecture and patterns
  • context/PROJECT_CONTEXT.md — Project-wide context and constraints
  • Input: Discovery Brief from Discovery Agent (Stage 1)

Specification Process

Step 1: Requirements Extraction

From the Discovery Brief, extract and structure functional requirements:

### FR-001: {Requirement Title}
- **Description:** {What the system must do — precise and testable}
- **Source:** {Which persona/pain point this addresses}
- **Priority:** {Derived from Discovery Brief opportunity analysis}
- **Dependencies:** {Other requirements this depends on}

Step 2: Acceptance Criteria

For each requirement, define acceptance criteria in Given/When/Then format:

Read the full file on GitHub · 212 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 · 212 lines · 0 tokens per session scan A f73ca16e3c38

Subscribe to this mod's changes

spec-generator is an agent published in the GitHub repository nerellasraj21/ai_governance_framework (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,840 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 2026-08-31.