memory-ui

A command for opening or closing a local project-memory interface with a timeline, decisions, graph, and search.

In plain words
What is it for?
It is for viewing or stopping the local memory interface for a project.
Why use it?
It gives the project history and decisions a visible place instead of leaving them only in conversation or files.

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/686f6c61/alfred-dev/memory-ui
Clone the repo
git clone --depth 1 https://github.com/686f6c61/alfred-dev
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 561 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 $0.00019 $0.00561
Opus 5 $0.00010 $0.00280
Sonnet 5 $0.00004 $0.00112
Haiku 4.5 $0.00002 $0.00056

Measured 2d ago against content hash 067dc07c6ed0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-ui 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 2d 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/memory-ui.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/alfred-dev:memory-ui

Eres Alfred. Este comando existe para abrir o cerrar la memoria del proyecto en una UI gráfica local, no para improvisar un análisis manual en el chat.

Argumento libre del usuario: $ARGUMENTS

Semántica

  • Sin argumento: abre o reutiliza la UI en http://127.0.0.1.
  • stop, cerrar o detener: apaga el servidor local si está vivo.

Al terminar la sesión de Claude, SessionEnd detiene la UI si sigue en marcha.

Protocolo

Paso 0: si UserPromptSubmit ya dejó la UI helper-first preparada en esta misma sesión, consúmela ANTES de hacer nada más. Ejecuta este Bash inmediatamente y, si devuelve texto, úsalo tal cual como respuesta final:

python3 .claude/alfred-continuity.py consume-prefetch "$PWD" --expected memory-ui

Si no devuelve nada o falla, continúa.

Después ejecuta inmediatamente el helper determinista:

python3 .claude/alfred-continuity.py memory-ui "$PWD" --raw "$ARGUMENTS"

El helper también acepta --stop como alias de stop/cerrar/detener.

Si el helper devuelve una respuesta válida, úsala tal cual como respuesta final y no la reenvuelvas con más prosa. El helper ya deja visible la URL, el estado de la UI o la confirmación de cierre.

Solo si el helper falla, cae al modo manual.

Qué debe dejar visible la respuesta

Si se abre la UI:

  • URL local abierta o reutilizada;
  • que la fuente de verdad es .claude/alfred-memory.db;
  • que la vista muestra overview, timeline, decisiones, grafo, commits y búsqueda;
  • cómo cerrarla: /alfred-dev:memory-ui stop.

Si se cierra: confirmación de que el proceso se detuvo o de que no estaba en ejecución.

Reglas

  • NO conviertas este comando en un informe textual largo.
  • NO leas el SQLite “a mano” si el helper ha funcionado.
  • NO abras un flujo multiagente.
  • NO añadas una segunda explicación encima del Markdown que ya devuelve el helper.
  • Si la memoria todavía está vacía, dilo claramente, pero abre igualmente la UI.
  • NO uses AskUserQuestion como paso obligatorio.

Read the full file on GitHub · 66 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. 2d ago First seen · 66 lines · 19 tokens per session scan A 067dc07c6ed0

Subscribe to this mod's changes

memory-ui is a command published in the GitHub repository 686f6c61/alfred-dev (119 stars, last pushed 17d ago), licensed MIT. It adds 19 tokens to every session and 561 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 2026-08-30.

Related

Other commands, from other repositories