init

init is a command for coding agents from mjmorales/claude-prove. It costs 27 tokens per session (3,518 once invoked), scanned A, original, MIT.

A project setup command for Claude projects that detects the technology stack and creates configuration and project-identity files. These can include a project charter, team information, and contributor records.

In plain words
What is it for?
Use it to start or reconfigure a project, select which identity files to create, preserve existing validator settings, and register the project contributor.
Why use it?
It removes the need to identify validators and manually create the basic files that describe how a project is built and maintained.

Command

Part of the prove plugin — 2 skills, 29 commands, 21 agents, 5 hooks, 1 MCP server shipped together

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/mjmorales/claude-prove/init
Clone the repo
git clone --depth 1 https://github.com/mjmorales/claude-prove

Or install prove, the plugin that ships this one along with the rest of its 2 skills, 29 commands, 21 agents, 5 hooks, 1 MCP server.

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/commands/mjmorales/claude-prove/init.svg)](https://agentmods.dev/commands/mjmorales/claude-prove/init)
Your own site
<a href="https://agentmods.dev/commands/mjmorales/claude-prove/init"><img src="https://agentmods.dev/badge/commands/mjmorales/claude-prove/init.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,518 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 $0.00027 $0.03518
Opus 5 $0.00014 $0.01759
Sonnet 5 $0.00005 $0.00704
Haiku 4.5 $0.00003 $0.00352

Measured 4d ago against content hash 04c199ef9461, 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 4d 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 · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize a prove project

Two halves run here:

  1. Stack config — delegate detection and validator emission to claude-prove install init-config, then layer interactive UX for scope, validator review, .gitignore, references, and CLAUDE.md.
  2. Project-identity bootstrap — drive a conversational interview (or honor selection flags) and author charter.md, team.md, and a contributor record, then bring the identity chain live: register the contributor in the scrum registry (minting its CT-UUID) and offer operator-of-record + default-contributor wiring. The CLI runs the mechanical pre-flight checks and scaffolds skip-if-exists skeletons; you author the prose content into them.

claude-prove install init-config is the source of truth for validator detection. It writes <cwd>/.claude/.prove.json, preserves user-custom validators, and carries every other top-level key (scopes, reporters, claude_md, tools, ...) across re-runs.

Invocation modes

Read the slash-command arguments to pick the identity-bootstrap scope. Flags map to the artifact set:

  • --with-charter → charter only (combinable with --with-team)
  • --with-team → team only (combinable with --with-charter)
  • --full → charter + team + contributor
  • --form → full set, but batch every interview question into one form (collect all answers up front), then author all artifacts in one pass
  • (no flag) → ask the operator which artifacts to bootstrap, then proceed

Division of labor: the CLI does the mechanical work — pre-flight checks and skip-if-exists scaffolding; you do the interview and write the prose. Author only into skeletons the CLI just created; never overwrite a skipped (already-existing) artifact, and never re-run or reimplement the pre-flight/scaffolding yourself — call the CLI for it.

Step 0: Guard

  1. Verify $PLUGIN_DIR is set. If not, error: "Cannot resolve plugin directory."
  2. Verify $(pwd) is NOT inside ~/.claude/. If it is, error: "You are inside the plugin directory. Run this command from your project root."

Read the full file on GitHub · 300 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. 4d ago First seen · 300 lines · 27 tokens per session scan A 04c199ef9461

Subscribe to this mod's changes

init is a command published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 24d ago), licensed MIT. It adds 27 tokens to every session and 3,518 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 2026-08-31.