init-project

A project setup command that creates eight planning documents covering areas such as architecture, technology, data, APIs, deployment, and workflow.

In plain words
What is it for?
Use it to answer a project questionnaire and generate design documents for a new or existing application.
Why use it?
It gathers project decisions in one place, whether you are starting from scratch or documenting an existing codebase.

Command for Claude Code

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 commands/marcusgoll/spec-flow/init-project
Clone the repo
git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

Made for: Claude Code.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,053 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 $0.00030 $0.05053
Opus 5 $0.00015 $0.02527
Sonnet 5 $0.00006 $0.01011
Haiku 4.5 $0.00003 $0.00505

Measured 2d ago against content hash 34e0d66fc6a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init-project 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.

.claude/commands/project/init-project.md · 551 lines

How it starts

The opening of the file, as written. The whole thing — 551 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/init-project — Project Documentation Generator (Hybrid Pattern)

v11.0 Architecture: Uses hybrid pattern - questionnaire in main context (good UX), document generation isolated via Task() (saves ~5-10k tokens).

Existing project docs: !ls -1 docs/project/*.md 2>/dev/null | wc -l file(s)

Package manager detected: !test -f package.json && echo "npm/pnpm" || test -f pyproject.toml && echo "python" || test -f Cargo.toml && echo "rust" || test -f go.mod && echo "go" || echo "unknown"

Brownfield indicators: !ls package.json requirements.txt Cargo.toml go.mod docker-compose.yml 2>/dev/null | tr '\n' ', ' || echo "greenfield"

User: /init-project "My App"
         │
         ▼
┌──────────────────────────────────────────────────────┐
│ MAIN CONTEXT (questionnaire - good UX)               │
│                                                      │
│ 1. Detect brownfield/greenfield                      │
│ 2. Run 15-48 questions via AskUserQuestion           │
│ 3. Save answers to temp config                       │
│    → .spec-flow/temp/init-answers.yaml               │
└──────────────────────────────────────────────────────┘
         │
         ▼
┌──────────────────────────────────────────────────────┐
│ Task(init-project-agent) ← ISOLATED                  │
│                                                      │
│ 1. Read answers from temp config                     │
│ 2. Generate 8 project docs                           │
│ 3. Run quality gates                                 │
│ 4. Create ADR                                        │
│ 5. Return summary                                    │
│ 6. EXIT                                              │
└──────────────────────────────────────────────────────┘
         │
         ▼
┌──────────────────────────────────────────────────────┐
│ MAIN CONTEXT (results - minimal tokens)              │
│                                                      │
│ 1. Display success summary                           │
│ 2. Show generated files                              │
│ 3. Suggest next steps                                │
└──────────────────────────────────────────────────────┘

Read the full file on GitHub · 551 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 · 551 lines · 0 tokens per session scan A 34e0d66fc6a9

Subscribe to this mod's changes

init-project is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 5,053 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 2026-08-30.