agentmods.dev

waterfall:quit

waterfall:quit is a command for coding agents from mgallet92i/waterfall. It costs 4 tokens per session (238 once invoked), scanned A, original, MIT.

A command for stopping an active multi-agent workflow while preserving its saved state.

In plain words
What is it for?
Use it when you need to pause work safely, then continue later with the matching resume command.
Why use it?
It shuts down the participating agents and removes session markers without changing the work already recorded.

Command

Part of the waterfall plugin — 6 skills, 3 commands, 8 agents, 1 hook shipped together

not rated 2 1mo ago A scan 4 tokens original MIT
View the source file 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.

agentmods
npx agentmods add commands/mgallet92i/waterfall/quit
Clone the repo
git clone --depth 1 https://github.com/mgallet92i/waterfall

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.

agentmods badge for waterfall:quit

README.md
[![agentmods](https://agentmods.dev/badge/commands/mgallet92i/waterfall/quit.svg)](https://agentmods.dev/commands/mgallet92i/waterfall/quit)
Your own site
<a href="https://agentmods.dev/commands/mgallet92i/waterfall/quit"><img src="https://agentmods.dev/badge/commands/mgallet92i/waterfall/quit.svg" alt="Measured on agentmods" height="20"></a>
Per session 4 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 238 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 $0.00004 $0.00238
Opus 5 $0.00002 $0.00119
Sonnet 5 $0.00001 $0.00048
Haiku 4.5 $0.00000 $0.00024

Measured 4d ago against content hash 248e4fa99464, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

waterfall:quit 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 4d 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/quit.md · 30 lines

What it actually says

Cleanly stops the active workflow (shutdown teammates, marker cleanup, state preservation).

Argument: none. The active session is detected automatically via ~/.claude/wf-session-active.<session_id>.

What this command does

  1. Loads the wf-quit skill via Skill
  2. The skill detects the active session (wf-session-active.<sid>)
  3. Sends shutdown_request to each active teammate of the team
  4. Calls scripts/wf-quit.sh --session-id <sid> to clean up markers
  5. Displays confirmation + /waterfall:resume <need> command to resume

Entry procedure

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

Guarantees

  • .wf-state.json is never modified — the need's state is fully preserved
  • Idempotent: if no workflow is active, neutral message without error
  • Resume available immediately via /waterfall:resume <need>
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. 4d ago First seen · 30 lines · 4 tokens per session scan A 248e4fa99464

Subscribe to this mod's changes

waterfall:quit is a command published in the GitHub repository mgallet92i/waterfall (2 stars, last pushed 1mo ago), licensed MIT. It adds 4 tokens to every session and 238 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.

agent-frameworkagenticclaudeclaude-aiclaude-codeclaude-code-pluginquitsddshutdownwaterfallworkflow
Related

Other commands, from other repositories

token-review

Analyze SDLC token usage from .claude/sdlc/token-log.json (last run) and token-history.jsonl (rolling). Surfaces the biggest cost centers and concrete optimization candidates. Read-only.

lantisprime/claude-sdlc · 41 tokens

start

Activate the SDLC workflow (opt-in), re-enable after suspension, or start a new task when already enabled. On fresh install — auto-detects repo/CI/stack/tracker (≤3 prompts), creates .enabled, takes a one-sentence task description, and auto-generates scope.md and a draft plan. On re-enable — verifies the suspension…

lantisprime/claude-sdlc · 101 tokens

build

Start Phase 4 — implement the approved design with surgical-edit discipline and work-item traceability.

lantisprime/claude-sdlc · 19 tokens

configure

Guided setup for config/tools.json and config/tools.local.json. Replaces manual file editing for first-time setup and common reconfigurations. Auto-invoked on fresh install (Layer 0) and when a command finds its required config missing (Layer 2). Safe to run anytime for proactive changes.

lantisprime/claude-sdlc · 62 tokens

design

Start Phase 3 — produce or update application / data / platform / infrastructure / security / test architecture, technical specs, and test cases.

lantisprime/claude-sdlc · 28 tokens

fix-fast

Compressed SDLC path for small bug fixes only — collapses Plan + Analyze + Design into a single mini-gate. Not for new builds or change requests.

lantisprime/claude-sdlc · 32 tokens