spec

A guided interview that creates a detailed feature specification from the project's product requirements. The specification records what the feature should do and becomes the reference for implementation.

In plain words
What is it for?
Defining a feature's users, behavior, acceptance criteria, test cases, and data needs.
Why use it?
It turns an unfinished idea into agreed requirements, reducing uncertainty before development and testing begin.

Skill for Claude CodeCodex

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 skills/mountainunicorn/add/spec
Any agent
npx skills add MountainUnicorn/add --skill spec
Clone the repo
git clone --depth 1 https://github.com/MountainUnicorn/add

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,103 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 $0.00014 $0.01103
Opus 5 $0.00007 $0.00551
Sonnet 5 $0.00003 $0.00221
Haiku 4.5 $0.00001 $0.00110

Measured 2d ago against content hash 18834e446e0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec 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.

core/skills/spec/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADD Spec Command v{{VERSION}}

Create a feature specification through a structured interview. The spec becomes the source of truth for implementation.

Pre-Flight

  1. Verify docs/prd.md exists. If not, tell the user to run /add:init first.
  2. Read docs/prd.md to understand the project context
  3. Read .add/config.json to understand environment and quality settings
  4. If --from-prd-section is provided, pre-populate answers from that PRD section
  5. If feature-name argument is provided, use it. Otherwise, ask.

Phase 1: Feature Interview

Estimate questions upfront. Typical spec interview is 6-10 questions, ~5 minutes.

Let's define a specification for this feature.
This will take approximately {N} questions (~5 minutes).

The spec will include acceptance criteria, user test cases,
data models, and everything needed to start TDD.

Core Questions (ask 1-by-1)

Q1: "Describe the feature in one or two sentences. What should it do?" → Captures: feature description, feature name/slug

Q2: "Who uses this feature, and what's their goal?" → Captures: user story (As a {role}, I want {what}, so that {why})

Q3: "What are the must-have behaviors? List the things that MUST work for this feature to be complete." → Captures: acceptance criteria (AC-001, AC-002, etc.)

Q4: "Walk me through the happy path — step by step, what does the user do and see?" → Captures: primary user test case (TC-001)

Q5: "What should happen when things go wrong? Think about invalid input, network errors, missing data." → Captures: error handling, edge cases, additional test cases

Q6: "What data does this feature need? Think entities, fields, relationships." (Default: "I'll infer from the acceptance criteria") → Captures: data model

Q7 (if applicable): "Does this feature need API endpoints? If so, what operations?" → Captures: API contract

Q8 (if UI): "Describe the key UI states — loading, empty, error, success." → Captures: UI behavior, screenshot checkpoints

Read the full file on GitHub · 118 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 · 118 lines · 14 tokens per session scan A 18834e446e0a

Subscribe to this mod's changes

spec is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 1,103 once invoked, about $0.0001 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.