A command that creates a structural-discipline scaffold in a new repository. It writes an AGENTS.md file and documentation ledgers that guide an autonomous coding loop, a process where an agent repeatedly implements and checks planned work.

Use it at the start of a fresh project to create the required project files, then draft the first section of the game design document before implementation.

It establishes project rules, planning records, dependency tracking, and quality checks before feature code is written. It also refuses to overwrite a repository that already has AGENTS.md.

spiral-init — Command for Claude Code by Randroids-Dojo

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add Randroids-Dojo/skills

Claude Code

/plugin install spiral

Made for: Claude Code.

Or install spiral, the plugin that ships this one along with the rest of its 1 skill, 2 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/randroids-dojo/skills/spiral-init.svg)](https://agentmods.dev/commands/randroids-dojo/skills/spiral-init)

Your own site

<a href="https://agentmods.dev/commands/randroids-dojo/skills/spiral-init"><img src="https://agentmods.dev/badge/commands/randroids-dojo/skills/spiral-init.svg" alt="Measured on agentmods" height="20"></a>

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 381 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.

Model	Per session	Once invoked
Fable 5.1	$0.00010	$0.00381
Opus 5	$0.00005	$0.00191
Sonnet 5	$0.00002	$0.00076
Haiku 4.5	$0.00001	$0.00038

Measured 3d ago against content hash d14f6e2e260d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

spiral-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 3d 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/spiral/commands/spiral-init.md · 40 lines

What it actually says

/spiral init

Bootstrap the structural-discipline scaffold into the current repo.

When to use

At the start of a fresh project, before any feature code. Writes the canonical files (AGENTS.md plus the docs/ ledger set, including docs/DEPENDENCY_LEDGER.md and the qualitative-gate docs) so an autonomous PR loop can run against the repo.

Refuses to run if AGENTS.md already exists. Use /spiral audit on existing repos instead.

How to invoke

Ask the user three questions via AskUserQuestion before running:

Project name. Used in headers and substituted as {{PROJECT_NAME}}.
One-line pitch. Substituted as {{PITCH}}. Used in AGENTS.md and the GDD index.
Stack. Substituted as {{STACK}}. Used in AGENTS.md Rule 3. Free text. Examples: "Next.js + Three.js + Vercel KV", "Godot 4.x + GDScript", "Rust + axum + Postgres".

Then run:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/init.sh "<name>" "<pitch>" "<stack>"

After the script completes:

Print the list of written files.
Tell the user the next step is to draft the first GDD section under docs/gdd/<n>-<title>.md.
Suggest /randroid:loop implement once the first GDD section exists.

Output

The script prints every written file path, plus a one-line note for the user about next steps.

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.

3d ago Changed · +6 lines · +10 tokens per session d14f6e2e260d
7d ago First seen · 34 lines · 0 tokens per session scan A fe4f511bcb5c

Subscribe to this mod's changes

spiral-init is a command published in the GitHub repository Randroids-Dojo/skills (46 stars, last pushed 7d ago), licensed MIT. It adds 10 tokens to every session and 381 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.

spiral-init

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/spiral init

When to use

How to invoke

Output

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

analyze