memory

A project-memory tool for recording and finding design decisions, project milestones, handoffs, and other saved project history through Alfred's memory service.

In plain words
What is it for?
Use it to save a design decision, search previous decisions, inspect the project's memory timeline, or check memory-service health and statistics.
Why use it?
It prevents the agent from inventing past decisions and makes earlier project context available when the memory service is connected.

Skill for Claude CodeCodex

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 skills/686f6c61/alfred-dev/memory
Any agent
npx skills add 686f6c61/alfred-dev --skill memory
Clone the repo
git clone --depth 1 https://github.com/686f6c61/alfred-dev

Made for: Claude Code, Codex.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 605 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 $0.00053 $0.00605
Opus 5 $0.00026 $0.00302
Sonnet 5 $0.00011 $0.00121
Haiku 4.5 $0.00005 $0.00060

Measured 2d ago against content hash ba29034f4254, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory 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.

skills/memory/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memoria persistente de Alfred

Registrar y consultar decisiones del proyecto a través del servidor MCP alfred-memory. No inventar historial. Si la herramienta no está disponible, decirlo y no simular resultados.

Nombres reales de las tools

Claude Code expone las tools del plugin con prefijo MCP. Usar estos nombres, no los cortos:

  • mcp__plugin_alfred-dev_alfred-memory__memory_search
  • mcp__plugin_alfred-dev_alfred-memory__memory_get_decisions
  • mcp__plugin_alfred-dev_alfred-memory__memory_get_iteration
  • mcp__plugin_alfred-dev_alfred-memory__memory_get_timeline
  • mcp__plugin_alfred-dev_alfred-memory__memory_stats
  • mcp__plugin_alfred-dev_alfred-memory__memory_log_decision
  • mcp__plugin_alfred-dev_alfred-memory__memory_update_decision
  • mcp__plugin_alfred-dev_alfred-memory__memory_link_decisions
  • mcp__plugin_alfred-dev_alfred-memory__memory_health

Si el runtime muestra un prefijo distinto, usar el que aparezca en la lista de tools, siempre del servidor alfred-memory.

Qué se escribe y qué no

Sí: decisiones de diseño, resultado de gates, handoffs, UAT y commits hechos en una sesión de Alfred.

No: historial antiguo de Git, cada Read/Glob/Grep, consejos operativos ni kanban vacío.

Llamar a memory_log_decision solo cuando haya una elección real de diseño, seguridad o entrega. No registrar cada edit. Si la decisión es de arquitectura o compliance, el Markdown vivo (docs/adr/, docs/project/compliance.md) es lo que lee un humano; la memoria no lo sustituye.

Campos mínimos: título, contexto, alternativas descartadas, justificación, etiquetas.

Consulta

Para "por qué decidimos X" o "qué hicimos la última vez": memory_search o memory_get_decisions con el término y, si aplica, rango o tags.

Si no hay filas, responder que no hay registros. No inferir.

No existe el agente librarian. Esta skill y /alfred-dev:memory-ui son la vía de consulta histórica.

UI

La vista gráfica es /alfred-dev:memory-ui. Esta skill no arranca el servidor HTTP. Para cerrarla: /alfred-dev:memory-ui stop. Al terminar la sesión de Claude se detiene sola.

Read the full file on GitHub · 47 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 · 47 lines · 53 tokens per session scan A ba29034f4254

Subscribe to this mod's changes

memory is a skill published in the GitHub repository 686f6c61/alfred-dev (119 stars, last pushed 18d ago), licensed MIT. It adds 53 tokens to every session and 605 once invoked, about $0.0003 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.