A command for starting a new end-to-end Waterfall workflow, a staged process that moves from requirements through design, implementation, review, and testing.

Use it to name a new work item, initialize its saved state and logs, and begin the requirements phase with agents added as needed.

It creates the initial work area and brings in the first coordinating agent, so the workflow can build and manage the rest of its team.

new — Command for Claude Code by mgallet92i/waterfall

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.

Clone the repo

git clone --depth 1 https://github.com/mgallet92i/waterfall

Made for: Claude Code.

Or install waterfall, the plugin that ships this one along with the rest of its 6 skills, 3 commands, 8 agents, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/mgallet92i/waterfall/new/github.svg)](https://agentmods.dev/commands/mgallet92i/waterfall/new)

Your own site

<a href="https://agentmods.dev/commands/mgallet92i/waterfall/new"><img src="https://agentmods.dev/badge/commands/mgallet92i/waterfall/new/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/mgallet92i/waterfall/new"><img src="https://agentmods.dev/badge/commands/mgallet92i/waterfall/new.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 551 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00000	$0.00551
Opus 5.5	$0.00000	$0.00220
Sonnet 5.5	$0.00000	$0.00110
Haiku 4.5	$0.00000	$0.00055

Measured 1mo ago against content hash 30ef034d3c2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

new 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 1mo 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.

commands/new.md · 43 lines

What it actually says

Starts a new end-to-end need (preflight, team, spawn OR).

Input: <name> (kebab-case, optional). If omitted, PM will ask the HO to describe the need and propose 3 kebab-case names to choose from.

Prerequisite: CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 must be set in the environment. The skill checks this automatically via scripts/wf-check-teams.sh and will fail fast with a clear message if missing.

What this command does

Loads the wf-new skill via Skill({name: "wf-new", args: "$ARGUMENTS"})
wf-new runs the preflight check (scripts/wf-check-teams.sh)
PM resolves the need name (uses $ARGUMENTS if valid kebab-case, otherwise asks HO)
PM spawns OR via Agent — the implicit team forms at the first spawn (one team per session, enforced by the platform — CLI v2.1.178+, no TeamCreate)
PM spawns OR as the sole first teammate with a bootstrap brief
OR initialises sdd/besoins/<name>/, state file, and or.log
OR emits brief_complete to PM → PM enters its reactive loop
All subsequent teammates (PO, TL, RV, QA, DS, DV) are spawned dynamically by PM on spawn_request from OR

Workflow phases

BOOTSTRAP → REQUIREMENTS → FUNCTIONAL_SPECS → TECHNICAL_DESIGN
    → REVIEW → PLANNING → IMPLEMENTATION → VALIDATION → CLOSURE

Entry procedure

Skill({name: "wf-new", args: "$ARGUMENTS"})

The skill handles everything from here. Do NOT run orchestration logic directly from this command — always delegate to the skill.

Reminders (enforced by wf-pm)

Only PM spawns teammates (Agent) and calls AskUserQuestion — never teammates
Teammates communicate via SendMessage only
PM never writes application code — DV handles implementation (spawned by TL via OR → PM)
EnterPlanMode before IMPLEMENTATION to present taches.md to HO
git commit only after HO validation in CLOSURE — no Co-Authored-By
One question at a time for HO

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.

1mo ago First seen · 43 lines · 0 tokens per session scan A 30ef034d3c2a

Subscribe to this mod's changes

new is a command published in the GitHub repository mgallet92i/waterfall (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 551 tokens. 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.

Claude Code Multi-Agent Planning agent-framework agent-teams agentic claude claude-ai sdd spec-driven waterfall workflow

context

A project-context command that manages a .context directory containing decision notes, session logs, and history. It helps keep a record of why changes were made across Git branches and commits.

fengshao1227/ccg-workflow · 23 tokens

spec-impl

An implementation command that follows an approved specification and task checklist, uses multiple analysis models, and archives the completed work. It keeps changes within the defined scope and requires external suggestions to be reviewed before use.

fengshao1227/ccg-workflow · 12 tokens

new