memory

A guide for managing an assistant's short-term and long-term memory stored in local files. It also explains automatic recall and nightly organization of those memories.

In plain words
What is it for?
Use it to inspect or edit remembered information, understand how recall works, and enable or manage nightly memory consolidation.
Why use it?
It gives the assistant a way to retain durable facts across resets while keeping temporary working notes separate, without an external service or API key.

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/dgatom/dg-claw/memory
Any agent
npx skills add DGatoM/DG-Claw --skill memory
Clone the repo
git clone --depth 1 https://github.com/DGatoM/DG-Claw

Made for: Claude Code, Codex.

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 737 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00080 $0.00737
Opus 5 $0.00040 $0.00368
Sonnet 5 $0.00016 $0.00147
Haiku 4.5 $0.00008 $0.00074

Measured 2d ago against content hash d77ea82dfe26, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

memory scanned grade C with 2 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo bash "$PLUGIN_ROOT/scripts/install-panel-service.sh" "$CONFIG" 8200

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$(d=$(find "$HOME/.claude/plugins" -path '*dgclaw*/.claude-plugin/plugin.json' | head -1); cd "$(dirname "$(dirname "$d")")" && pwd)}"`.
skills/memory/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dgclaw:memory — Memoria do assistente

Ajuda a entender e operar a memoria de um assistente DG Claw. Tudo local, no proprio Claude — sem API externa nem chave.

Localizar o assistente

ls -d "$HOME"/dgclaw/*/ 2>/dev/null

Se houver mais de um, pergunte qual (SLUG); defina WORKSPACE="$HOME/dgclaw/$SLUG" e CONFIG="$WORKSPACE/.dgclaw/config.sh". O plugin: descubra com PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$(d=$(find "$HOME/.claude/plugins" -path '*dgclaw*/.claude-plugin/plugin.json' | head -1); cd "$(dirname "$(dirname "$d")")" && pwd)}".

Explicar (se perguntarem "como funciona")

  1. Curto prazo — working-memory.md: o "agora". Ele le e escreve sozinho.
  2. Longo prazo — MEMORY.md: fatos duraveis. Sobrevive a /reset.
  3. Recall automatico: antes de responder, um hook procura nesses arquivos linhas relacionadas a mensagem (busca por palavra-chave, local, instantanea) e injeta como lembrete. Sem chave, sem servico externo.
  4. Consolidacao noturna: o proprio Claude organiza a memoria toda madrugada (promove o duradouro pro MEMORY.md, limpa o working-memory).

Ver o que ele lembra

echo "--- curto prazo ---"; cat "$WORKSPACE/working-memory.md"
echo "--- longo prazo ---"; cat "$WORKSPACE/MEMORY.md"
ls "$WORKSPACE/memory/" 2>/dev/null

Editar memoria

Edite os arquivos direto (Edit/Write) ou use o painel (mais facil pro leigo):

sudo bash "$PLUGIN_ROOT/scripts/install-panel-service.sh" "$CONFIG" 8200
# mostra a URL com token: http://SEU_IP:8200/?t=...

O que for salvo no painel grava direto nos arquivos e vale na proxima conversa.

Consolidacao noturna

# ligar (default 04:00; pode passar outro horario, ex 03:30)
sudo bash "$PLUGIN_ROOT/scripts/install-consolidate-timer.sh" "$CONFIG" 04:00
# rodar agora pra testar
sudo systemctl start "dgclaw-$(basename "$WORKSPACE")-consolidate.service"
cat "$WORKSPACE/.dgclaw/logs/consolidate.log"
# ver agendamento
systemctl list-timers "dgclaw-*consolidate*" --no-pager

Read the full file on GitHub · 65 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 · 65 lines · 80 tokens per session scan C d77ea82dfe26

Subscribe to this mod's changes

memory is a skill published in the GitHub repository DGatoM/DG-Claw (5 stars, last pushed 12d ago), licensed MIT. It adds 80 tokens to every session and 737 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens