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.
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.
[](https://agentmods.dev/skills/maxvaega/awesome-skills/dream)<a href="https://agentmods.dev/skills/maxvaega/awesome-skills/dream"><img src="https://agentmods.dev/badge/skills/maxvaega/awesome-skills/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/maxvaega/awesome-skills/dream"><img src="https://agentmods.dev/badge/skills/maxvaega/awesome-skills/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 | $0.00070 | $0.03902 |
| Opus 5 | $0.00035 | $0.01951 |
| Sonnet 5 | $0.00014 | $0.00780 |
| Haiku 4.5 | $0.00007 | $0.00390 |
Grade C, and why
dream 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 10d 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.
1. **SessionEnd hook** (queues finished sessions for nightly dreaming): copy `scripts/dream-queue-hook.sh` to `~/.claude/hooks/dream-queue.sh` (`chmod +x`), then add to `~/.claude/settings.json` hooks (merge, don't overw Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
0. **Preflight**: verify `claude -p --help` works and note whether `--max-turns` is supported; verify `jq` is installed; locate this skill's `scripts/` dir (next to this SKILL.md — check both the installed `~/.claude/ski How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dream — distill sessions into memory, consolidate, self-improve
The user runs /dream [mode] to make learnings from sessions persist: preferences, corrections, and standing directions become project-level memories; recurring gaps become improvement proposals for skills and CLAUDE.md; a periodic consolidation pass ("REM sleep") keeps the memory store lean and true. Follow this procedure exactly. Reply in the language the user has been using.
0. Mode dispatch
Parse $ARGUMENTS:
$ARGUMENTS |
Mode |
|---|---|
| (empty) | Capture from the current conversation (§1–§5, then §6) |
history |
Capture from recent transcripts (§1–§5, then §6) |
queued |
Capture from transcripts queued by the SessionEnd hook (§1–§5, then §6) |
rem or rem --dry-run |
REM consolidation pass (§7) — FULL only |
proposals |
Review pending proposals interactively (§8) — FULL only |
setup |
Install opt-in automation on this machine (§9) — FULL only |
0.1 Environment detection (run FIRST, before any mode)
Not every Claude surface has a writable, persistent ~/.claude (Claude Cowork's sandbox mounts it read-only and the sandbox home does not survive between sessions). Probe once:
mkdir -p ~/.claude/projects 2>/dev/null && touch ~/.claude/.dream-probe 2>/dev/null \
&& rm -f ~/.claude/.dream-probe && echo FULL || echo PORTABLE
- FULL (Claude Code on a real machine): follow this document as written.
- PORTABLE (Cowork or any sandbox without writable
~/.claude): only default capture is supported. Persistence is re-routed to the project folder (§3-P); modeshistory,queued,rem,proposals,setupmust refuse with one line naming the missing primitive and pointing to Claude Code, e.g.history→ "session transcripts don't exist in Cowork — run this from Claude Code". The final report (§5) must state which mode ran.
Paths used throughout (FULL mode):
- Project slug: cwd with
/replaced by-(e.g./home/me/proj→-home-me-proj). - Project memory:
~/.claude/projects/<project-slug>/memory/ - Dream state:
~/.claude/dream/containingqueue.tsv,digested.log,reports/,proposals/(create dirs as needed). - Global user profile:
~/.claude/CLAUDE.md(loaded by Claude Code in every session, all projects).
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.
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.
- 10d ago First seen · 217 lines · 70 tokens per session scan C 2e997a572998
dream is a skill published in the GitHub repository maxvaega/awesome-skills (40 stars, last pushed 10d ago), licensed MIT. It adds 70 tokens to every session and 3,902 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.