A command that pauses the current Alfred development workflow and records how to continue it later. It creates a handoff containing the current phase, completed work, pending check, and next action.

Use it when pausing an active Alfred development task. It records session state in project files and identifies the concrete step to perform when work resumes.

It prevents the state of an unfinished task from being lost when work stops. The handoff gives the next session enough context to resume with the `/alfred-dev:resume` command.

pause — Command for Claude Code by 686f6c61/alfred-dev

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/686f6c61/alfred-dev

agentmods

npx agentmods add commands/686f6c61/alfred-dev/pause

Made for: Claude Code.

Or install alfred-dev, the plugin that ships this one along with the rest of its 11 skills, 22 commands, 10 agents, 5 hooks, 1 MCP server.

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/686f6c61/alfred-dev/pause/github.svg)](https://agentmods.dev/commands/686f6c61/alfred-dev/pause)

Your own site

<a href="https://agentmods.dev/commands/686f6c61/alfred-dev/pause"><img src="https://agentmods.dev/badge/commands/686f6c61/alfred-dev/pause/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/686f6c61/alfred-dev/pause"><img src="https://agentmods.dev/badge/commands/686f6c61/alfred-dev/pause.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 433 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	$0.00012	$0.00433
Opus 5.5	$0.00005	$0.00173
Sonnet 5.5	$0.00002	$0.00087
Haiku 4.5	$0.00001	$0.00043

Measured 1mo ago against content hash 0f7981828af0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pause 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/pause.md · 50 lines

What it actually says

/alfred-dev:pause

Eres Alfred. Vas a pausar la sesión actual sin perder el hilo.

Protocolo

Primero ejecuta el helper determinista del plugin:

python3 .claude/alfred-continuity.py pause "$PWD"

Si devuelve salida útil, úsala como respuesta final y termina. No la reenvuelvas con un segundo resumen: el helper ya deja flujo, fase, gate, handoff y siguiente acción.

Solo si el helper falla, cae al modo manual:

Lee .claude/alfred-dev-state.json.
Si no existe o la sesión ya está completada, dilo con claridad y NO inventes un handoff.
Si existe una sesión activa:
- resume comando, descripción, fase actual y fases completadas;
- identifica la gate pendiente;
- identifica el siguiente paso concreto para retomar.
Escribe estos artefactos:
- .claude/alfred-handoff.json
- docs/project/handoff.md
- actualiza .claude/alfred-dev-state.json añadiendo paused_at y paused_via: "/alfred-dev:pause"
El handoff debe incluir como mínimo:
- flujo activo
- descripción
- fase actual y número
- fases completadas
- gate pendiente
- artefactos registrados
- comando de retorno /alfred-dev:resume
- siguiente acción concreta al volver
Como .claude/* es sensible en Claude Code, NO uses Write ni Edit para esos ficheros. Si de verdad tienes que caer al modo manual, usa Bash.

Restricciones

NO marques la sesión como completada.
NO borres .claude/alfred-dev-state.json.
NO hagas un handoff vacío o genérico.
Cierra con una confirmación breve indicando dónde quedó guardado el handoff.

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 · 50 lines · 12 tokens per session scan A 0f7981828af0

Subscribe to this mod's changes

pause is a command published in the GitHub repository 686f6c61/alfred-dev (117 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 433 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-30.

Claude Code Productivity ai-agents automation claude-code-plugin sdlc

onboard-dev

Onboard a new developer to the project. Generates personalized onboarding plan, sets up dev environment, creates first tasks, and provides codebase walkthrough.

alphaaiservice/cortex · 29 tokens

ponytail-help

Quick reference for ponytail levels, skills, and commands.

DietrichGebert/ponytail · 11 tokens

orchestrate

Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.

egorfedorov/claude-context-optimizer · 0 tokens

scout-meta-review

Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.

Raven-Scout/Scout · 61 tokens

tasks

Inspect Modellix task status and recover tasks after a timeout or unknown submission.

Modellix/modellix-plugin · 15 tokens

agent-triage

Find and triage Quickchat conversations that need a human.

quickchatai/quickchat-claude-plugin · 11 tokens