A command that creates a new application workspace with a predefined governance structure, starter files, and a Git repository. It takes an application name and can also take a short description or skip Git setup.

Use it when starting a new governed application from a workspace directory, with an optional description and optional Git initialisation.

It removes the manual setup needed to start an application with the expected folders, templates, and initial project rules.

init — Command by xiaolai

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/xiaolai/eou-foundry/init

Clone the repo

git clone --depth 1 https://github.com/xiaolai/eou-foundry

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,000 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.

Model	Per session	Once invoked
Fable 5	$0.00039	$0.01000
Opus 5	$0.00019	$0.00500
Sonnet 5	$0.00008	$0.00200
Haiku 4.5	$0.00004	$0.00100

Measured 2d ago against content hash 45ecfda18a53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

commands/init.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/eou-foundry:init

You are scaffolding a new EOU-governed application. The user invoked this from a workspace directory and supplied an app name.

1. Parse arguments

Read $ARGUMENTS. Required: the first positional token is the app name (slug: lowercase, alphanumeric + hyphen). Optional flags:

--description "..." — one-line application purpose; defaults to the slug.
--no-git — skip git init in the new application directory.

If no app name is supplied, ask the user:

AskUserQuestion:
  question: "What is the application's slug name? (lowercase, alphanumeric + hyphen)"
  header: "App name"
  options:
    - label: "Other"
      description: "Enter a slug name"

Validate the slug. Reject names containing /, \, .., leading ., or any character outside [a-z0-9-]. Refuse to overwrite an existing directory.

2. Refuse if target exists

Run bash "${CLAUDE_PLUGIN_ROOT}/scripts/init_app.sh" "$APP_NAME" "$DESCRIPTION" $([ "$NO_GIT" = "1" ] && echo "--no-git") and let the script handle the existence check + scaffolding atomically. Report what it produced.

3. What the script does (for reference)

scripts/init_app.sh is idempotent in the sense of "refuse to clobber":

Refuses if ./<app-name>/ already exists.
Creates ./<app-name>/ and inside it:
- foundry/ populated from templates/ — constitution, governance, registry (empty), maturity-model, failure-taxonomy, refactoring-patterns, runtime-contract, meta-eous/, templates/eou-template, templates/generating-eou-template.
- foundry/eous/, foundry/incidents/, foundry/audits/, foundry/runs/, foundry/self-evolution/{ecp/{proposed,approved,implemented,rejected},regression/cases,upstream/proposed-to-plugin}/ empty.
- CLAUDE.md, AGENTS.md, GEMINI.md minimal starters.
- .claude/settings.json minimal scaffold (no hooks).
- .gitignore with the standard AI-tool ignores.
- README.md one-paragraph application overview.
Substitutes {{APP_NAME}} and {{DESCRIPTION}} placeholders in the template files.
Unless --no-git, runs git init and makes a single initial commit.
Runs python3 "${CLAUDE_PLUGIN_ROOT}/scripts/validate_foundry.py" against the new app to confirm the scaffold passes the schema check.

Read the full file on GitHub · 88 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.

2d ago First seen · 88 lines · 39 tokens per session scan A 45ecfda18a53

Subscribe to this mod's changes

init is a command published in the GitHub repository xiaolai/eou-foundry (10 stars, last pushed 8d ago), licensed ISC. It adds 39 tokens to every session and 1,000 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.

Git and workflow

init

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/eou-foundry:init

1. Parse arguments

2. Refuse if target exists

3. What the script does (for reference)

What this file has done since we first saw it

Other commands, from other repositories

git

checklist

clarify

specify

analyze

constitution