Memory consolidation skill for Claude Code. An agent skill from grandamenium/dream-skill.

No licenceAuto-check passedAgent Workflows

Install Dream

skills CLI
$ npx skills add grandamenium/dream-skill --skill dream -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install grandamenium/dream-skill dream --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
dream
GitHub stars
154
Token cost
~3.5k tokens
SKILL.md length
1,240 words
Files
6
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

Memory consolidation skill for Claude Code. An agent skill from grandamenium/dream-skill.

  • Works in 7 steps: Detect memory system → Install the Stop hook → Install the session-start check → …
  • Via native Stop hook every 24hrs
  • SKILL.md covers ONBOARDING (delete this…, END ONBOARDING, How It Works and Phase 1: ORIENT, plus 4 more sections
  • Runs Shell scripts from its folder; calls python3 and make

What it does

Dream is an agent skill from grandamenium/dream-skill. Memory consolidation skill for Claude Code. Scans session transcripts for corrections, decisions, preferences, and patterns, then merges findings into persistent memory files. Auto-triggers via native Stop hook every 24hrs. Inspired by how sleep consolidates human memory.

Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `README.md`, `dream-hook.sh` and `install.sh`).

It sits in Agent Workflows, covering Agent memory. The repository describes itself as: Memory consolidation skill for Claude Code - replicates Anthropic's unreleased auto-dream feature. 4-phase consolidation with 24hr auto-trigger.

When your agent uses it

  • Via native Stop hook every 24hrs
  • Tasks that involve Agent memory

Example prompts

  • “/dream”

Requirements

  • Python 3
  • A Bash shell

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Detect memory system
  2. Install the Stop hook
  3. Install the session-start check
  4. Make should-dream.sh executable
  5. Test it
  6. Clean up onboarding
  7. Read config

What it can do on your machine

Read from SKILL.md and the folder at commit 2286341. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • make

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dream loads about 3.5k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 1,240 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~3.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,240 words (~3,515 tokens).

“Welcome! Follow these steps in order. After setup is verified, delete everything between ## ONBOARDING and ## END ONBOARDING from this file as the final step.”

— opening of SKILL.md by grandamenium
name
dream
tags
memory, maintenance, consolidation, autonomous, hook

Read the full SKILL.md on GitHub

Files

SKILL.md and 5 other files in the repository root of grandamenium/dream-skill.

  • SKILL.md
  • README.md
  • dream-hook.sh
  • install.sh
  • should-dream.sh
  • test-dream.sh

Open the folder on GitHubat commit 2286341

Compare with similar skills

Dream next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Dream compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dream this skillgrandamenium/dream-skill154—~3.5kAutomated safety check: PassNone
Reflect on Session Learningscursor/plugins11k5 repos~1.2kAutomated safety check: PassNone
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Beads Task Memorygastownhall/beads28k—~1.2kAutomated safety check: PassMIT
MemPalace Memory SearchMemPalace/mempalace60k—~1.4kAutomated safety check: PassMIT
Compound Learning WriterEveryInc/compound-engineering-plugin25k—~2kAutomated safety check: PassMIT

Similar skills

  • Official

    Starts three parallel reviewer subagents over the current conversation transcript, then turns their findings into concrete edits to existing skills.

    11k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed
  • Beads Task Memory

    gastownhall/beads

    Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.

    28k GitHub stars~1.2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • MemPalace Memory Search

    MemPalace/mempalace

    Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.

    60k GitHub stars~1.4k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Compound Learning Writer

    EveryInc/compound-engineering-plugin

    Records one solved and verified problem as a durable learning in the repository, but only when the reasoning is not already clear from the final code, tests or docs.

    25k GitHub stars~2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.

    24k GitHub stars~3.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

Categories

Questions about Dream

What does Dream do?

Memory consolidation skill for Claude Code. An agent skill from grandamenium/dream-skill. Dream is an agent skill from grandamenium/dream-skill. Memory consolidation skill for Claude Code.

When should I use Dream?

Dream fits situations like: via native Stop hook every 24hrs; tasks that involve Agent memory.

How do I install Dream in Claude Code?

Run `npx skills add grandamenium/dream-skill --skill dream -a claude-code`. Or copy the skill folder (the grandamenium/dream-skill repository) into .claude/skills/dream in your project. Claude Code loads it when a task matches its description.

How do I install Dream in Codex?

Run `npx skills add grandamenium/dream-skill --skill dream -a codex`. Or copy the skill folder (the grandamenium/dream-skill repository) into .agents/skills/dream in your project. Codex loads it when a task matches its description.

Can I use Dream in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add grandamenium/dream-skill --skill dream -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dream, .gemini/skills/dream, .github/skills/dream and .opencode/skills/dream in your project.

What does Dream need to run?

Going by SKILL.md and its folder, Dream needs a shell for the scripts in its folder and the command-line tools its instructions call (python3 and make). Our summary lists: Python 3; A Bash shell.

Does Dream access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Dream safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Dream use?

No licence was found for Dream or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Dream use?

About 3.5k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Dream?

Skills that share tags, products or a category with Dream: Reflect on Session Learnings (cursor/plugins, 11k stars), Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars), Beads Task Memory (gastownhall/beads, 28k stars) and MemPalace Memory Search (MemPalace/mempalace, 60k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dream?

grandamenium (a GitHub user) maintains it in grandamenium/dream-skill, which has 154 GitHub stars. The repository was last updated on March 24, 2026.

Source: grandamenium/dream-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.