agentmods.dev

paul:init

A conversational project setup command for PAUL, a project-planning workflow. It asks about the project and creates its planning files automatically.

In plain words
What is it for?
Use it to start PAUL in a new or existing codebase, record the project's purpose and description, and create an initial roadmap and project state.
Why use it?
It removes the need to fill in planning templates by hand and gives a new project a clear starting structure.

Command

1.2k 11d ago A scan 13 tokens original MIT
View the source file ChristopherKahler/paul
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/christopherkahler/paul/init
Clone the repo
git clone --depth 1 https://github.com/ChristopherKahler/paul
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 419 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 $0.00013 $0.00419
Opus 5 $0.00006 $0.00210
Sonnet 5 $0.00003 $0.00084
Haiku 4.5 $0.00001 $0.00042

Measured 2d ago against content hash c3aa22d199e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

paul: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.

src/commands/init.md · 55 lines

What it actually says

When to use: Starting a new project with PAUL, or adding PAUL to an existing codebase.

Creates PROJECT.md, STATE.md, and ROADMAP.md populated from conversation - user does not manually edit templates.

<execution_context> @/.claude/paul-framework/workflows/init-project.md @/.claude/paul-framework/templates/PROJECT.md @/.claude/paul-framework/templates/STATE.md @/.claude/paul-framework/templates/ROADMAP.md </execution_context>

The workflow implements conversational setup:

  1. Check for existing .paul/ (route to resume if exists)
  2. Create directory structure
  3. Ask: "What's the core value this project delivers?"
  4. Ask: "What are you building?"
  5. Confirm project name (infer from directory)
  6. Populate PROJECT.md, ROADMAP.md, STATE.md from answers
  7. Display ONE next action: /paul:plan

Key behaviors:

  • Ask ONE question at a time
  • Wait for response before next question
  • Populate files from answers (user doesn't edit templates)
  • End with exactly ONE next action
  • Build momentum into planning phase

<success_criteria>

  • .paul/ directory created
  • PROJECT.md populated with core value and description from conversation
  • STATE.md initialized with correct loop position
  • ROADMAP.md initialized (phases TBD until planning)
  • User presented with ONE clear next action </success_criteria>
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 · 55 lines · 13 tokens per session scan A c3aa22d199e8

Subscribe to this mod's changes

paul:init is a command published in the GitHub repository ChristopherKahler/paul (1,212 stars, last pushed 11d ago), licensed MIT. It adds 13 tokens to every session and 419 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.

PlanningProductivityai-developmentai-toolsclaudeclaude-codedevelopment-frameworkproject-orchestration
Related

Other commands, from other repositories

test

Smart test runner with filtering, coverage, and health monitoring.

PaulDuvall/ai-development-patterns · 11 tokens

safe-refactor

Safe refactoring with automated review, testing, and rollback capabilities.

PaulDuvall/ai-development-patterns · 12 tokens

security-review

Comprehensive security analysis with multi-layer vulnerability detection.

PaulDuvall/ai-development-patterns · 9 tokens

implement-spec

Implement specification with full traceability and test-driven development.

PaulDuvall/ai-development-patterns · 10 tokens

refactor

Interactive refactoring assistant based on Martin Fowler's refactoring catalog.

PaulDuvall/ai-development-patterns · 12 tokens

deploy_to_docker

Build Docker image and start/redeploy the MCP Task Orchestrator container, reusing the last-used config by default.

jpicklyk/task-orchestrator · 23 tokens