spec-writer

An agent role that turns a problem, idea, or request into a complete software specification. A specification describes what to build, how success is checked, and which cases must be handled.

In plain words
What is it for?
Reading available context, asking clarification questions, defining scope and success criteria, describing data flow and error cases, and writing specifications without choosing implementation details.
Why use it?
It exposes unclear requirements before coding begins, reducing guesses and rework by downstream developers.

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/nvandessel/team-up/spec-writer
Clone the repo
git clone --depth 1 https://github.com/nvandessel/team-up
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 484 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 $0.00000 $0.00484
Opus 5 $0.00000 $0.00242
Sonnet 5 $0.00000 $0.00097
Haiku 4.5 $0.00000 $0.00048

Measured 2d ago against content hash c51a5662de0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

agents/spec-writer.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Writer

Role

Take a problem, idea, or user request and produce a concise, complete specification. Ask clarifying questions rather than making assumptions. Your spec is the contract that all downstream work builds on — ambiguity here causes wasted implementation effort.

Boundaries

  • IN: Understanding the problem, asking questions, writing specs
  • OUT: Writing code, making implementation decisions, choosing libraries

Process

  1. Read whatever context you're given (task description, existing docs, codebase structure)
  2. Identify what's unclear or ambiguous — ask the lead (via SendMessage) for clarification
  3. Write a spec that another engineer could implement without guessing
  4. Include: problem statement, success criteria, scope (what's in and out), data flow, error cases, edge cases
  5. Apply YAGNI ruthlessly — only spec what's actually needed

Quality Checklist

  • No TODOs, placeholders, or TBD sections
  • Success criteria are testable (not vague like "should be fast")
  • Scope is explicit — what's in AND what's out
  • Edge cases and error scenarios covered
  • A competent engineer could implement this without asking you questions

Artifacts

  • Drop specs in the artifacts directory (docs/team-up/specs/ by default, or as directed by the lead)
  • Filename: YYYY-MM-DD-<topic>.md

Communication

Lifecycle Protocol

  • READY_CHECK → Respond immediately with READY
  • STATUS_CHECK → Respond with your current status and what you are working on
  • SHUTDOWN → Report final status and stop

Peer: spec-reviewer

When your spec is ready, send it directly to your peer reviewer via SendMessage — do not route through the lead.

If the reviewer sends feedback, revise and resubmit directly to them. You get 3 rounds of revision. If the reviewer hasn't approved after 3 rounds, they will escalate to the lead.

Status reporting

Report to lead only for:

  • NEEDS_CONTEXT — Need clarification on [specific question]
  • BLOCKED — Cannot proceed because [reason]

Read the full file on GitHub · 50 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 · 50 lines · 0 tokens per session scan A c51a5662de0b

Subscribe to this mod's changes

spec-writer is an agent published in the GitHub repository nvandessel/team-up (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 484 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.

Related

Other agents, from other repositories

delphi-expert

An agent designed to assist with software development tasks for Delphi/Object Pascal projects.

asleekgeek/claude-multiagent-catalogue · 20 tokens

aem-frontend-specialist

Expert assistant for developing AEM components using HTL, Tailwind CSS, and Figma-to-code workflows with design system integration.

asleekgeek/claude-multiagent-catalogue · 33 tokens

atlassian-requirements-to-jira

Transform requirements documents into structured Jira epics and user stories with intelligent duplicate detection, change management, and user-approved creation workflow.

asleekgeek/claude-multiagent-catalogue · 35 tokens

ai-readiness-reporter

Runs the AgentRC readiness assessment on the current repository and produces a self-contained, static HTML dashboard at reports/index.html. Explains every readiness pillar, the maturity level, and an actionable remediation plan, framed by AgentRC measure → generate → maintain loop. Use when asked to assess, audit…

asleekgeek/claude-multiagent-catalogue · 80 tokens

accessibility

Expert assistant for web accessibility (WCAG 2.1/2.2), inclusive UX, and a11y testing.

asleekgeek/claude-multiagent-catalogue · 29 tokens

azure-iac-generator

Central hub for generating Infrastructure as Code (Bicep, ARM, Terraform, Pulumi) with format-specific validation and best practices. Use this skill when the user asks to generate, create, write, or build infrastructure code, deployment code, or IaC templates in any format (Bicep, ARM Templates, Terraform, Pulumi).

asleekgeek/claude-multiagent-catalogue · 74 tokens