draft-story

A command that turns business requirements or design documents into complete software tickets after examining the relevant codebase.

In plain words
What is it for?
Use it to ask clarifying questions, find relevant code patterns, identify documentation needs, split large designs into tickets, and draft implementation-ready requirements.
Why use it?
It helps turn incomplete feature ideas into clearer work items and exposes missing details, gaps, and open questions before development begins.

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/bostonorange/claude-code-framework/draft-story
Any agent
npx skills add BostonOrange/claude-code-framework --skill draft-story
Clone the repo
git clone --depth 1 https://github.com/BostonOrange/claude-code-framework

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,098 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 $0.00034 $0.01098
Opus 5 $0.00017 $0.00549
Sonnet 5 $0.00007 $0.00220
Haiku 4.5 $0.00003 $0.00110

Measured 2d ago against content hash 7c5524cbd2d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

draft-story 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.

skills/draft-story/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Draft Story

Create complete, refined tickets from business requirements or design documents. Write for a technical audience — direct, concise, specific identifiers over display names.

When to use this vs /refine-story:

  • /draft-story — New requirements or design document → create new tickets
  • /refine-story — Existing ticket that needs improvement or gap analysis

Input Sources

1. Business Requirements (ad-hoc)

User describes a business need or feature request verbally. Follow the full interview process.

2. Design Documents (pasted or fetched)

User provides a structured design document. These typically include:

  • Objective / Overview
  • Open Questions
  • Technical Design (data flows, endpoint specs, field mappings)
  • Data Model Changes
  • Business Logic
  • Integration Details

Design docs may cover multiple tickets — propose how to split.

Process

From business requirements:

  1. User describes business need
  2. Ask clarifying questions (Who, What, Why, When, Where)
  3. Explore codebase for relevant patterns
  4. Fetch documentation using the /fetch-docs skill pattern (resolve-library-id then get-library-docs) when the solution involves external dependencies — verify actual API capabilities before committing to a technical approach
  5. Propose solution options if multiple approaches exist
  6. Draft complete ticket
  7. Present open questions for stakeholder follow-up
  8. Save to docs/stories/TICKET-{id}/ or docs/stories/DRAFT-{name}/

From design documents:

  1. User provides design document content
  2. Parse all sections — identify scope, TBDs, and open questions
  3. Clarify architecture early: sync vs async, data flow direction
  4. Explore codebase to verify existing components
  5. Identify gaps: what the doc leaves unresolved
  6. If doc covers multiple tickets, propose split and ask which to draft
  7. Draft complete ticket with design doc section references
  8. Surface open questions — grouped by source (doc TBDs vs codebase gaps)
  9. Resolve open questions interactively — work through each one
  10. Save to docs/stories/TICKET-{id}/ or docs/stories/DRAFT-{name}/

Read the full file on GitHub · 129 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 · 129 lines · 34 tokens per session scan A 7c5524cbd2d7

Subscribe to this mod's changes

draft-story is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,098 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 2026-08-31.