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.
npx agentmods add commands/christopherkahler/paul/helpgit clone --depth 1 https://github.com/ChristopherKahler/paulWhat 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 | $0.00013 | $0.03079 |
| Opus 5 | $0.00006 | $0.01540 |
| Sonnet 5 | $0.00003 | $0.00616 |
| Haiku 4.5 | $0.00001 | $0.00308 |
Grade A, and why
paul:help 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.
How it starts
The opening of the file, as written. The whole thing — 527 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Output ONLY the reference content below. Do NOT add:
- Project-specific analysis
- Git status or file context
- Next-step suggestions
- Any commentary beyond the reference
PAUL (Plan-Apply-Unify Loop) is a structured AI-assisted development framework for Claude Code.
The Loop
Every unit of work follows this cycle:
┌─────────────────────────────────────┐
│ PLAN ──▶ APPLY ──▶ UNIFY │
│ │
│ Define Execute Reconcile │
│ work tasks & close │
└─────────────────────────────────────┘
Never skip UNIFY. Every plan needs a summary.
Quick Start
/paul:init- Initialize PAUL in your project/paul:plan- Create a plan for your work/paul:apply- Execute the approved plan/paul:unify- Close the loop with summary
Commands Overview
| Category | Commands |
|---|---|
| Core Loop | init, plan, apply, unify, help, status |
| Session | pause, resume, progress, handoff |
| Roadmap | add-phase, remove-phase |
| Milestone | milestone, complete-milestone, discuss-milestone |
| Pre-Planning | discuss, assumptions, discover, consider-issues |
| Research | research, research-phase |
| Specialized | flows, config, map-codebase |
| Quality | verify, plan-fix, audit |
Core Loop Commands
/paul:init
Initialize PAUL in a project.
- Creates
.paul/directory structure - Creates PROJECT.md, STATE.md, ROADMAP.md
- Prompts for project context and phases
- Optionally configures integrations (SonarQube, etc.)
Usage: /paul:init
/paul:plan [phase]
Enter PLAN phase - create an executable plan.
- Reads current state from STATE.md
- Creates PLAN.md with tasks, acceptance criteria, boundaries
- Populates skills section from SPECIAL-FLOWS.md (if configured)
- Updates loop position
Usage: /paul:plan (auto-detects next phase)
Usage: /paul:plan 3 (specific phase)
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 · 527 lines · 13 tokens per session scan A 42cb3904c664
paul:help 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 3,079 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.
Other commands, from other repositories
safe-refactor
Safe refactoring with automated review, testing, and rollback capabilities.
security-review
Comprehensive security analysis with multi-layer vulnerability detection.
test
Smart test runner with filtering, coverage, and health monitoring.
implement-spec
Implement specification with full traceability and test-driven development.
refactor
Interactive refactoring assistant based on Martin Fowler's refactoring catalog.
deploy_to_docker
Build Docker image and start/redeploy the MCP Task Orchestrator container, reusing the last-used config by default.