init

init is a skill for Claude Code from tim-mccrimmon/structured-context-spec. It costs 33 tokens per session (2,173 once invoked), scanned A, original, Apache-2.0.

A project-initialization workflow that scans a codebase and prepares a .scs directory containing 11 structured context bundles. It also identifies the project's language, framework, and existing documentation.

In plain words
What is it for?
Use it when explicitly starting SCS Team setup for a project. It detects the technology stack, finds key documentation, and proposes the context structure for confirmation.
Why use it?
It gives an agent organized project context before deeper work begins. The confirmation step helps prevent documentation files from being created without approval.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is /scs-team:add ./docs/PRD.md.

Part of the scs-team plugin — 7 skills shipped together

Good fit Use it when explicitly starting SCS Team setup for a project. It detects the technology stack, finds key documentation, and proposes the context structure for confirmation.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/tim-mccrimmon/structured-context-spec
agentmods
npx agentmods add skills/tim-mccrimmon/structured-context-spec/init

Made for: Claude Code.

Or install scs-team, the plugin that ships this one along with the rest of its 7 skills.

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 init

README.md
[![agentmods](https://agentmods.dev/badge/skills/tim-mccrimmon/structured-context-spec/init/github.svg)](https://agentmods.dev/skills/tim-mccrimmon/structured-context-spec/init)
Your own site
<a href="https://agentmods.dev/skills/tim-mccrimmon/structured-context-spec/init"><img src="https://agentmods.dev/badge/skills/tim-mccrimmon/structured-context-spec/init/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for init

Your own site · 80×15
<a href="https://agentmods.dev/skills/tim-mccrimmon/structured-context-spec/init"><img src="https://agentmods.dev/badge/skills/tim-mccrimmon/structured-context-spec/init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,173 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00033 $0.02173
Opus 5.5 $0.00013 $0.00869
Sonnet 5.5 $0.00007 $0.00435
Haiku 4.5 $0.00003 $0.00217

Measured 22d ago against content hash 9352dd5c8d3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

init 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 22d 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/init/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 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:init. Never auto-invoke based on project state or conversation context.
  • Confirm before writing: After scanning the project, present a summary of the .scs/ scaffold you plan to create and get explicit user confirmation before writing any files.

SCS Team Init - Initialize Structured Context

You are scaffolding a new .scs/ directory for this project. This is the entry point for teams adopting structured context.

Your Process

Step 1: Detect Project Info

Scan the project to understand what exists:

Language/Framework Detection (check in order):

  • package.json → Node.js (check for Next.js, React, Express, etc.)
  • requirements.txt or pyproject.toml or setup.py → Python (check for FastAPI, Django, Flask)
  • go.mod → Go
  • Cargo.toml → Rust
  • pom.xml or build.gradle → Java/Kotlin
  • Gemfile → Ruby
  • .csproj or .sln → .NET

Existing Documentation (scan for):

  • docs/, doc/, documentation/ directories
  • Root-level: PRD.md, ARCHITECTURE.md, SECURITY.md, README.md
  • Any *.md files that look like project documentation
  • CLAUDE.md, .claude/rules/ (existing Claude context)

Compliance Signals (look for keywords in docs and code):

  • HIPAA: "PHI", "protected health information", "HIPAA", "healthcare"
  • SOC2: "SOC2", "SOC 2", "trust service criteria"
  • PCI: "PCI", "cardholder", "payment card"
  • GDPR: "GDPR", "personal data", "data subject"
  • CHAI: "clinical AI", "health AI", "CHAI"

Step 2: Determine Project Name

Use the argument if provided. Otherwise:

  1. Check package.json name field
  2. Check pyproject.toml project name
  3. Check go.mod module name
  4. Fall back to directory name

Step 3: Create .scs/ Scaffold

Create the following structure:

.scs/
├── project.yaml              # Project bundle manifest
├── concepts/
│   ├── architecture.yaml
│   ├── security.yaml
│   ├── performance.yaml
│   ├── usability.yaml
│   ├── compliance.yaml
│   ├── data.yaml
│   ├── testing.yaml
│   ├── deployment.yaml
│   ├── safety.yaml
│   ├── ethics.yaml
│   └── business.yaml
└── scds/                     # Empty - populated by add/draft/use

Read the full file on GitHub · 252 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. 22d ago Changed 9352dd5c8d3d
  2. 1mo ago First seen · 252 lines · 33 tokens per session scan A 03de31fe05c2

Subscribe to this mod's changes

init is a skill published in the GitHub repository tim-mccrimmon/structured-context-spec (19 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 2,173 once invoked, about $0.0001 per session on Opus 5.5. 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.