help

A guide to the PM Adaptive Workflow, a task-management process that scales planning and checking to the size of the software task.

In plain words
What is it for?
Learning the workflow from product requirements through tasks, implementation, verification, and release, including its complexity modes.
Why use it?
It explains which commands and workflow level to use, so small tasks do not receive unnecessary process while larger tasks get more structure.

Command for Claude Code

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/dtannen/pm/help
Clone the repo
git clone --depth 1 https://github.com/dtannen/pm

Made for: Claude Code.

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 2,920 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 $0.02920
Opus 5 $0.00006 $0.01460
Sonnet 5 $0.00003 $0.00584
Haiku 4.5 $0.00001 $0.00292

Measured yesterday against content hash 6d3d1b8660d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

.claude-plugin/commands/help.md · 361 lines

How it starts

The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM Adaptive Workflow Help

Comprehensive guide to the PM Adaptive Workflow - an intelligent task management system that automatically adjusts complexity handling based on task requirements.

Usage

/pm:help [command]

PM Adaptive Workflow Overview

The PM Adaptive Workflow transforms software development from one-size-fits-all to intelligent complexity scaling:

PRD → Epic → Tasks → Adaptive Execution → Quality-Matched Verification → Shipping

Core Philosophy

  1. Intelligent Scaling: Automatically match workflow rigor to task complexity
  2. No Wasted Effort: Simple tasks get simple treatment, complex tasks get thorough handling
  3. Assumption Awareness: Track and validate uncertainties in complex work
  4. Learning System: Get smarter over time through pattern recognition
  5. Quality Assurance: Appropriate verification for each complexity level

Adaptive Modes

The system automatically selects from four workflow modes:

Simple Mode (Complexity 1-3)

For: Bug fixes, simple UI changes, single-file modifications Process: Direct implementation → Basic testing → Done Duration: < 4 hours Overhead: Minimal

Standard Mode (Complexity 4-6)

For: Multi-file features, basic integrations, moderate complexity Process: Plan → Implement → Test → Verify → Done Duration: 4-8 hours
Overhead: Structured approach

RA-Light Mode (Complexity 7-8)

For: Cross-domain work, API integrations, significant refactoring Process: Assess → Plan → Tagged Implementation → Assumption Verification → Done Duration: 8-16 hours Overhead: Response Awareness tags and verification

RA-Full Mode (Complexity 9-10)

For: Architecture changes, complex integrations, mission-critical features Process: Survey → Multi-agent Planning → Synthesis → Orchestrated Implementation → Full Verification → Done Duration: > 16 hours Overhead: Complete Response Awareness orchestration

Command Reference

🚀 Getting Started

  • /pm:init - Initialize adaptive workflow with intelligent templates
  • /pm:help - Show this help (or /pm:help <command> for details)

Read the full file on GitHub · 361 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. yesterday First seen · 361 lines · 13 tokens per session scan A 6d3d1b8660d3

Subscribe to this mod's changes

help is a command published in the GitHub repository dtannen/pm (0 stars, last pushed 10mo ago), licensed MIT. It adds 13 tokens to every session and 2,920 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.