help

A help command for the Full Dev Workflow plugin, a feature-development process that maps code, writes tests before implementation, reviews changes, and manages pull requests. TDD means writing tests before the code they check.

In plain words
What is it for?
Use it to start or resume a full feature workflow, view available commands, and learn what happens in each phase.
Why use it?
It explains the plugin’s commands and the stages of its development process, so you know how to start, resume, or understand a workflow.

Command

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/rahswe/claude-code-full-dev-workflow/help
Clone the repo
git clone --depth 1 https://github.com/RahSwe/claude-code-full-dev-workflow
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 708 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 $0.00008 $0.00708
Opus 5 $0.00004 $0.00354
Sonnet 5 $0.00002 $0.00142
Haiku 4.5 $0.00001 $0.00071

Measured yesterday against content hash 738c7273b8b8, 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.

plugins/full-dev-workflow/commands/help.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full Dev Workflow Plugin

A comprehensive feature development workflow with code mapping, TDD, multi-agent review, and PR management.

Commands

Command Description
/full-dev-workflow:full-dev <feature> Start the full development workflow
/full-dev-workflow:resume Resume an interrupted workflow
/full-dev-workflow:help Show this help message

Workflow Phases

Phase Name Description
0 Plan Mode Create feature specification and get user approval
1 Code Mapping Explore codebase and identify affected files
2 Test Creation Write E2E, integration, and unit tests (TDD)
3 Implementation (Tasks) Parallel sub-agent execution with task groups until tests pass
4 Code Review Multi-agent review (5 perspectives)
5 Auto Fixes Automatically fix high-confidence issues
6 Code Simplification Refactor for clarity and maintainability
7 UI Verification Browser testing for UI features
8 Push PR Create well-documented pull request
9-10 PR Review Loop Address feedback until approval

Bundled Agents

This plugin includes specialized agents for each phase:

  • full-dev-workflow:code-explorer - Phase 1 code mapping
  • full-dev-workflow:test-architect - Phase 2 test design
  • full-dev-workflow:reviewer-conventions - Phase 4 convention compliance
  • full-dev-workflow:reviewer-bugs - Phase 4 bug detection
  • full-dev-workflow:reviewer-quality - Phase 4 code quality
  • full-dev-workflow:reviewer-security - Phase 4 security review
  • full-dev-workflow:reviewer-performance - Phase 4 performance review
  • full-dev-workflow:code-simplifier - Phase 6 code simplification (uses Opus model)

Read the full file on GitHub · 79 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 · 79 lines · 8 tokens per session scan A 738c7273b8b8

Subscribe to this mod's changes

help is a command published in the GitHub repository RahSwe/claude-code-full-dev-workflow (6 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 708 once invoked, about $0.0000 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.