draft

A conversation-based workflow for creating structured context documents called SCDs when existing documentation does not cover a concern.

In plain words
What is it for?
Use it to document areas such as architecture, security, performance, usability, compliance, and data practices; it must be started explicitly and confirmed before writing files.
Why use it?
It helps turn missing project knowledge into organised documentation by asking focused questions before proposing files to create or change.

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/tim-mccrimmon/structured-context-spec/draft
Any agent
npx skills add tim-mccrimmon/structured-context-spec --skill draft
Clone the repo
git clone --depth 1 https://github.com/tim-mccrimmon/structured-context-spec

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,313 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 $0.00025 $0.02313
Opus 5 $0.00013 $0.01156
Sonnet 5 $0.00005 $0.00463
Haiku 4.5 $0.00003 $0.00231

Measured 2d ago against content hash 3cd76dcc9049, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

draft 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.

plugins/scs-team/skills/draft/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Invocation Rules

  • User-initiated only: Do NOT invoke this skill unless the user explicitly runs /scs-team:draft. Never auto-invoke based on project state or conversation context.
  • Confirm before writing: After the conversation, present a summary of the SCDs you plan to generate and the files you'll create/modify. Get explicit user confirmation before writing any files.

SCS Team Draft - Conversational Context Creation

You are helping the user create structured context for a specific concern area through conversation. Use this when they don't have existing documentation.

The 11 Concerns

# Concern Slug What It Covers
1 Architecture architecture System structure, components, boundaries, tech stack
2 Security security Auth, data protection, threats, access control
3 Performance & Reliability performance Response times, availability, fault tolerance, scaling
4 Usability & Accessibility usability UX principles, accessibility, error handling patterns
5 Compliance & Governance compliance Regulatory requirements, audit, governance
6 Data & Provenance data Data models, data flow, retention, provenance
7 Testing & Validation testing Test strategy, coverage requirements, validation approach
8 Deployment & Operations deployment Infrastructure, CI/CD, environments, monitoring
9 Safety & Risk safety Risk assessments, safety checklists, mitigation strategies
10 Ethics & AI Accountability ethics AI usage policies, bias detection, audit trails
11 Business Context business Problem definition, stakeholders, objectives, success criteria

Your Process

Step 1: Understand Current State

Before asking questions:

  • Check what context already exists (.scs/ directory)
  • Scan the codebase to understand what's already built
  • Note any existing patterns or choices

Step 2: Ask Targeted Questions

Read the full file on GitHub · 224 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 · 224 lines · 25 tokens per session scan A 3cd76dcc9049

Subscribe to this mod's changes

draft is a skill published in the GitHub repository tim-mccrimmon/structured-context-spec (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 2,313 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.