A structured workflow for developing a software feature from planning through review and pull-request management. It includes code mapping, test-driven development (writing tests before or alongside code), task tracking, and interface checks.

Use it to plan and implement features, run tests, check the user interface, review changes with multiple agents, and prepare or manage a pull request.

It keeps a large feature implementation organized and records progress so interrupted work can continue. It also brings testing and several review passes into one process.

full-dev — Command by RahSwe

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/full-dev

Clone the repo

git clone --depth 1 https://github.com/RahSwe/claude-code-full-dev-workflow

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 5,393 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.

Model	Per session	Once invoked
Fable 5	$0.00025	$0.05393
Opus 5	$0.00013	$0.02697
Sonnet 5	$0.00005	$0.01079
Haiku 4.5	$0.00003	$0.00539

Measured yesterday against content hash b4f82c57e305, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

full-dev 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/full-dev.md · 745 lines

How it starts

The opening of the file, as written. The whole thing — 745 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full Development Workflow

You are executing a comprehensive feature development workflow. Follow each phase systematically, using the TodoWrite tool to track progress throughout.

Feature to implement: $ARGUMENTS

Workflow State Management

State File: .claude/full-dev.local.md

Initialization (BEFORE Phase 0)

Check if .claude/full-dev.local.md exists:
- If exists and active: true: Ask user if they want to /full-dev-workflow:resume or start fresh
- If user wants fresh start: Delete existing state file
Get current git branch: git branch --show-current
Create new state file with this structure:

---
active: true
feature: "$ARGUMENTS"
branch: "<current-branch>"
started_at: "<ISO-8601 timestamp>"
updated_at: "<ISO-8601 timestamp>"

# Phase tracking
current_phase: 0
completed_phases: []
user_approved_plan: false
approval_timestamp: ""

# Plan info
plan_file: ""

# Modified files (for Phase 6 code simplifier)
modified_files:

# Test status
test_status: unknown
last_test_run: ""
test_pass_count: 0
test_fail_count: 0

# Review status
review_agents_completed: 0
review_issues_found: 0

# PR Review Loop (Phase 9-10)
pr_url: ""
pr_review_iterations: 0
max_pr_iterations: 10
---

After Each Phase Completion

Update the state file:

Add current phase number to completed_phases array
Increment current_phase to next phase
Update updated_at timestamp
Update phase-specific fields (e.g., plan_file, test_status, pr_url)

Phase-Specific State Updates

Phase 0: Set plan_file, wait for user_approved_plan: true (detected by hook)
Phase 2: Update test_status: failing after running initial tests
Phase 3: Update test_status: passing when the implementation Task completes
Phase 4: Update review_agents_completed and review_issues_found
Phase 6: Read modified_files for code simplifier input
Phase 8: Set pr_url after PR creation
Phase 9-10: Increment pr_review_iterations each cycle

Read the full file on GitHub · 745 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.

yesterday First seen · 745 lines · 25 tokens per session scan A b4f82c57e305

Subscribe to this mod's changes

full-dev is a command published in the GitHub repository RahSwe/claude-code-full-dev-workflow (6 stars, last pushed 7mo ago), licensed MIT. It adds 25 tokens to every session and 5,393 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.

Code review Frontend Testing

full-dev

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Full Development Workflow

Workflow State Management

Initialization (BEFORE Phase 0)

After Each Phase Completion

Phase-Specific State Updates

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement