Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/justnau1020/claude-osnpx agentmods add skills/justnau1020/claude-os/dreamWrote 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.
[](https://agentmods.dev/skills/justnau1020/claude-os/dream)<a href="https://agentmods.dev/skills/justnau1020/claude-os/dream"><img src="https://agentmods.dev/badge/skills/justnau1020/claude-os/dream/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.
<a href="https://agentmods.dev/skills/justnau1020/claude-os/dream"><img src="https://agentmods.dev/badge/skills/justnau1020/claude-os/dream.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.02319 |
| Opus 5.5 | $0.00021 | $0.00928 |
| Sonnet 5.5 | $0.00010 | $0.00464 |
| Haiku 4.5 | $0.00005 | $0.00232 |
Grade B, and why
dream scanned grade B with 1 finding 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find ~/.claude/projects/*/sessions/ -name "*.jsonl" -mtime -7 2>/dev/null | sort -t/ -k6 -r How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dream - Memory Consolidation for Claude Code
Your AI agent dreams like you do. Consolidates memory while you sleep.
How It Works
Dream runs in 4 sequential phases. Execute them in order. Do not skip phases.
ORIENT --> GATHER SIGNAL --> CONSOLIDATE --> PRUNE & INDEX
Auto-trigger flow (native Claude Code hooks)
Session ends
--> Stop hook fires should-dream.sh (~10ms)
--> Checks: 24hrs passed? 5+ sessions?
--> If NO: exits silently, zero overhead
--> If YES: creates ~/.claude/.dream-pending flag
Next session starts
--> Claude reads CLAUDE.md, sees .dream-pending exists
--> Spawns /dream as background subagent
--> Dream runs all 4 phases
--> Writes .last-dream timestamp, deletes .dream-pending
--> Timer resets for next 24hrs
Phase 1: ORIENT
Goal: Understand the current state of memory before changing anything.
Step 0: Read config
cat ~/.claude/skills/dream/.dream-config 2>/dev/null || echo "DREAM_MEMORY_TYPE=native"
This tells you which memory system to target:
native- scan~/.claude/projects/*/memory/openclaw- scan thememory/folder in the project root (daily logs + MEMORY.md)project-root- scan MEMORY.md and topic files in the project root
Steps
- Find memory directories based on type:
# native (default)
ls -d ~/.claude/projects/*/memory/ 2>/dev/null
# openclaw
ls ./memory/ 2>/dev/null
# project-root
ls ./MEMORY.md ./memory/ 2>/dev/null
- Read the memory directory for the detected type:
# native
ls ~/.claude/projects/*/memory/ 2>/dev/null
# openclaw - also list daily logs
ls ./memory/*.md 2>/dev/null
-
Read
MEMORY.md(the index file) in each project's memory directory. Note:- How many topic files exist
- Total line count of MEMORY.md
- Last modified dates
- Any entries that look stale (relative dates like "yesterday", "last week" with no anchor)
-
Read each topic file to understand what's already stored.
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.
- 1mo ago First seen · 266 lines · 52 tokens per session scan B dd7b86b02263
dream is a skill published in the GitHub repository justnau1020/claude-os (3 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 2,319 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dream
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.
memory-consolidation
Weekly synthesis of accumulated notes and memory optimization.
deep-clean
Full-spectrum consolidation of AI agent configuration files. Goes beyond memory-only dream skills: audits and optimizes context files (AGENTS.md/AGENTS.md/GEMINI.md/.cursorrules), rules, skills, and memory. Detects stale references, dead file paths, duplicated rules, stack mismatches, contradictions, vague directives…
brain-periodic-refactor
A periodic cleanup framework for an AI memory store: a collection of saved facts used to retain knowledge between sessions. It sorts, combines, reviews, updates, and reorganizes facts in a chosen area.
agent-dreaming-agnostic
Memory-agnostic background consolidation — reviews sessions, scores candidates, promotes durable insights to the active memory backend (built-in MEMORY.md or Holographic). Three-phase (Light/Deep/Condensation/REM). Run via cron or manually.
agent-dreaming
DEPRECATED — use agent-dreaming-agnostic instead. Background memory consolidation for built-in MEMORY.md only.