auto-dream

auto-dream is a skill for Claude Code from notque/vexjoy-agent. It costs 20 tokens per session (2,042 once invoked), scanned A, original, MIT.

An automatic memory-consolidation skill reviews memory files in the background, finding stale, duplicate, or conflicting entries and combining them. It prepares information for the next session and writes a dated report.

In plain words
What is it for?
Use it for scheduled or manual memory maintenance, including deduplication, conflict cleanup, cross-session summaries, and testing unattended overnight runs.
Why use it?
It keeps long-term agent memory more current and reduces repeated or contradictory notes between sessions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/feedgen/vexjoy-agent/scripts/auto-dream-cron.sh.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

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 auto-dream

README.md
[![agentmods](https://agentmods.dev/badge/skills/notque/vexjoy-agent/auto-dream.svg)](https://agentmods.dev/skills/notque/vexjoy-agent/auto-dream)
Your own site
<a href="https://agentmods.dev/skills/notque/vexjoy-agent/auto-dream"><img src="https://agentmods.dev/badge/skills/notque/vexjoy-agent/auto-dream.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,042 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00020 $0.02042
Opus 5 $0.00010 $0.01021
Sonnet 5 $0.00004 $0.00408
Haiku 4.5 $0.00002 $0.00204

Measured 2d ago against content hash 8d582f495e07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

auto-dream scanned grade A 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 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.

Reads agent configuration directorieslowAgent snooping

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

cat ~/.claude/state/last-dream.md

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/meta/auto-dream/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Background memory consolidation cycle. Scans memory files, finds stale, duplicate, and conflicting entries, consolidates them, synthesizes cross-session insights, builds an injection-ready payload for the next session start, and writes a dated dream report.

When to invoke

  • User says "run dream", "consolidate memories", "clean up memories", "memory maintenance", "deduplicate memories"
  • Cron job at 2 AM nightly via wrapper script: scripts/auto-dream-cron.sh --execute
  • Manual trigger for testing: ./scripts/auto-dream-cron.sh (dry-run by default)

Reference Loading Table

Signal Load These Files Why
Debugging failed cron run, silent failure, empty log, wrong exit code headless-cron-patterns.md Routes to the matching deep reference
Setting up or modifying wrapper script (flock, --permission-mode, envsubst, PIPESTATUS) headless-cron-patterns.md Routes to the matching deep reference
Budget cap, --max-budget-usd, unattended Claude invocation headless-cron-patterns.md Routes to the matching deep reference
Writing, updating, or archiving memory files memory-file-operations.md Routes to the matching deep reference
Updating MEMORY.md index, atomic write, .tmp rename memory-file-operations.md Routes to the matching deep reference
Staleness detection, duplicate merging, conflict flagging memory-file-operations.md Routes to the matching deep reference
YAML frontmatter structure, merged_from, memory file format memory-file-operations.md Routes to the matching deep reference
Testing the dream cycle safely, dry-run validation, output file verification dream-cycle-testing.md Routes to the matching deep reference
Reading and interpreting cron run logs, detecting silent failures logging-patterns.md Routes to the matching deep reference
Log rotation, log directory structure, phase completion markers in logs logging-patterns.md Routes to the matching deep reference
last-dream.md stale, missing injection payload, cron log empty logging-patterns.md Routes to the matching deep reference
Concurrent dream runs, lockfile already held, duplicate cron invocations concurrency.md Routes to the matching deep reference
MEMORY.md.tmp left behind, partial write recovery, atomic rename failure concurrency.md Routes to the matching deep reference

Read the full file on GitHub · 152 lines

Files

What ships with it

6 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. 2d ago First seen · 152 lines · 20 tokens per session scan A 8d582f495e07

Subscribe to this mod's changes

auto-dream is a skill published in the GitHub repository notque/vexjoy-agent (419 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 2,042 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

digital-brain

This skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly review", "track goals", or mentions personal brand, content creation, network management, or voice consistency.

foryourhealth111-pixel/Vibe-Skills · 57 tokens

agent-expert-creation

Create specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building domain-specific agents that maintain mental models via expertise files and self-improve prompts.

majiayu000/claude-skill-registry · 43 tokens

agent-assistant

Agent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agents Trigger terms: agent stuck, loop detected, session memory, agent learning, condense memory, stuck detection, agent memory, session learnings, extraction Use when: User reports agent is stuck…

majiayu000/claude-skill-registry · 72 tokens

ac-memory-manager

Manage persistent memory for autonomous coding. Use when storing/retrieving knowledge, managing Graphiti integration, persisting learnings, or accessing episodic memory.

majiayu000/claude-skill-registry · 35 tokens

ac-knowledge-graph

Manage knowledge graph for autonomous coding. Use when storing relationships, querying connected knowledge, building project understanding, or maintaining semantic memory.

majiayu000/claude-skill-registry · 31 tokens

godot-optimization

Use when optimizing Godot games — profiler, draw calls, physics tuning, memory management, and common bottlenecks.

jame581/GodotPrompter · 28 tokens