dream-memory

dream-memory is a skill for Claude Code, Codex from LearnPrompt/cc-harness-skills. It costs 37 tokens per session (418 once invoked), scanned A, original, MIT.

A memory-maintenance workflow for combining recent logs, conversations, and memory files into a smaller set of lasting topic notes. It also standardizes dates and removes outdated or conflicting information.

In plain words
What is it for?
Use it for scheduled or manual memory cleanup, merging related notes, pruning old information, and keeping `MEMORY.md` as a concise index.
Why use it?
It prevents long-term memory from filling with duplicates, stale notes, or facts that no longer agree.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it for scheduled or manual memory cleanup, merging related notes, pruning old information, and keeping MEMORY.md as a concise index.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/learnprompt/cc-harness-skills/dream-memory
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.

Any agent
npx skills add LearnPrompt/cc-harness-skills --skill dream-memory
Clone the repo
git clone --depth 1 https://github.com/LearnPrompt/cc-harness-skills

Made for: Claude Code, Codex.

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.

agentmods badge for dream-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/learnprompt/cc-harness-skills/dream-memory/github.svg)](https://agentmods.dev/skills/learnprompt/cc-harness-skills/dream-memory)
Your own site
<a href="https://agentmods.dev/skills/learnprompt/cc-harness-skills/dream-memory"><img src="https://agentmods.dev/badge/skills/learnprompt/cc-harness-skills/dream-memory/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.

agentmods 80×15 button for dream-memory

Your own site · 80×15
<a href="https://agentmods.dev/skills/learnprompt/cc-harness-skills/dream-memory"><img src="https://agentmods.dev/badge/skills/learnprompt/cc-harness-skills/dream-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 418 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00037 $0.00418
Opus 5 $0.00018 $0.00209
Sonnet 5 $0.00007 $0.00084
Haiku 4.5 $0.00004 $0.00042

Measured 10d ago against content hash fd70e6c6c114, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dream-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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/dream_memory.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/dream-memory/SKILL.md · 56 lines

What it actually says

Dream Memory

Use this skill when you want a deliberate memory-consolidation pass instead of storing more raw notes.

This bundle is intentionally portable. It borrows the workflow shape from Claude Code's dream system, but it does not depend on Claude Code internals.

Use It For

  • nightly or manual memory cleanup
  • merging overlapping memory notes
  • normalizing relative dates into absolute dates
  • pruning stale or contradicted memories
  • keeping MEMORY.md small and index-like

Avoid It For

  • saving a single new memory from the current turn
  • persisting code facts that should be re-read from source
  • replacing plans, task boards, or issue trackers

Quick Start

Inspect a memory directory before running the consolidation prompt:

python3 {baseDir}/scripts/dream_memory.py --memory-root /path/to/memory --transcripts-dir /path/to/transcripts

Then use the portable prompt in references/prompt-template.md.

Workflow

  1. Inspect MEMORY.md, topic files, and recent logs or transcripts.
  2. Identify durable facts worth keeping.
  3. Merge into topic files instead of creating near-duplicates.
  4. Remove stale or contradicted memory.
  5. Rewrite MEMORY.md as a concise index.

Rules

  • MEMORY.md is an index, not a content dump.
  • Prefer topic merges over new file creation.
  • Convert relative dates to absolute dates.
  • Do not store code-state facts that can drift.

Supporting Files

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 56 lines · 37 tokens per session scan A fd70e6c6c114

Subscribe to this mod's changes

dream-memory is a skill published in the GitHub repository LearnPrompt/cc-harness-skills (233 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 418 once invoked, about $0.0002 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 skills, from other repositories

remem-mcp

Long-term memory for coding agents. Auto-applies at the start of any coding task — recall past context before answering, capture decisions/learnings/fixes after work, use CodeGraph instead of grep for symbol lookup. Invoke when you see [remem-mcp] in your context or when starting any non-trivial coding work.

tinhien11/remem-mcp · 71 tokens

write-terva-lore

Author terva lore. Lore is context that a person authors in files. terva injects it only when it is keyword-relevant, or always-on. Use to create/add/write lore, "world info", a lorebook entry, keyed background, or a book of facts for a character.

terva-sh/terva · 66 tokens

handoff

Compact the current session into a handoff document. A fresh session or another agent can pick it up with no need to re-derive context. Use when asked to hand off, hand over, wrap up for another session or agent, or park work mid-stream.

terva-sh/terva · 56 tokens

retrospective

Distill the reusable lessons of this session into the durable homes that shape future sessions. The lessons are corrections, conventions you discovered, and traps you hit. The homes are the project or global AGENTS.md, a project skill, and memory when available. Use when asked for a retro, to capture or remember…

terva-sh/terva · 76 tokens

create-new-ref

Systematically add a new memory-system reference to AutoMemory's reference hub. Use when analyzing a new agent memory system, adding reference/ /details.md, saving prompts, or updating reference/hub/techniquemap.json.

HKUDS/AutoMemory · 51 tokens

health-memory

Recognize, store, and recall structured health data across sessions.

HKUDS/AutoMemory · 15 tokens