brain-dream

brain-dream is a skill for Claude Code, Codex from X-Arc-ai/brain-cli. It costs 16 tokens per session (299 once invoked), scanned A, original, Apache-2.0.

A maintenance skill for a project's knowledge graph and conversation memory. It imports new conversations, checks the graph for quality problems, fixes deterministic issues, and reports useful signals.

In plain words
What is it for?
Use it to run memory ingestion, find duplicate or orphaned items, check missing links and file paths, review graph readiness, and see active project signals and statistics.
Why use it?
It helps keep stored project knowledge connected, complete, and free of simple structural errors. Judgment-based issues are reported for review instead of being changed automatically.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/x-arc-ai/brain-cli/brain-dream
Any agent
npx skills add X-Arc-ai/brain-cli --skill brain-dream
Clone the repo
git clone --depth 1 https://github.com/X-Arc-ai/brain-cli

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 brain-dream

README.md
[![agentmods](https://agentmods.dev/badge/skills/x-arc-ai/brain-cli/brain-dream.svg)](https://agentmods.dev/skills/x-arc-ai/brain-cli/brain-dream)
Your own site
<a href="https://agentmods.dev/skills/x-arc-ai/brain-cli/brain-dream"><img src="https://agentmods.dev/badge/skills/x-arc-ai/brain-cli/brain-dream.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 299 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00016 $0.00299
Opus 5 $0.00008 $0.00150
Sonnet 5 $0.00003 $0.00060
Haiku 4.5 $0.00002 $0.00030

Measured 4d ago against content hash ff70294f146e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brain-dream 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 4d 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.

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.

src/brain_cli/data/skills/brain-dream/SKILL.md · 58 lines

What it actually says

Brain Dream

Run graph maintenance. Triggered automatically on session boundaries or manually via brain dream.

Phases

Phase 1: Ingest

If agent-memory is available, index new conversations:

memory ingest 2>/dev/null || true

Phase 2: Hygiene

Run all quality checks:

brain hygiene dedup
brain hygiene orphans
brain hygiene completeness
brain hygiene file-paths
brain hygiene verbs
brain hygiene readiness

Collect all violations into a fix list.

Phase 3: Fix

For deterministic issues (missing edges, broken file_paths, verb duplicates):

  • Propose fixes as a brain write batch
  • Execute the batch

For judgment calls (potential duplicates, thin content):

  • Add to "Needs Attention" list for the user

Phase 4: Signal

Compute and display signals:

brain signals

Phase 5: Report

Output a summary:

  • Issues found and fixed
  • Items needing attention
  • Active signals
  • Graph stats (node/edge counts, embedding coverage)

Rules

  • NEVER modify project code files
  • ONLY modify brain database and memory files
  • Be conservative -- when in doubt, flag for attention instead of fixing
  • Skip nodes updated in the last 24 hours
Files

What ships with it

7 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. 4d ago First seen · 58 lines · 16 tokens per session scan A ff70294f146e

Subscribe to this mod's changes

brain-dream is a skill published in the GitHub repository X-Arc-ai/brain-cli (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 299 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

omnigraph

Store, retrieve, and query knowledge, memory, and relationships in an Omnigraph graph, and operate a local or remote Omnigraph deployment. Use when the user wants to capture or recall facts, notes, or entities, build or query a knowledge graph or agent memory, or run Omnigraph — and whenever you see Omnigraph CLI…

ModernRelay/omnigraph · 236 tokens

openclaw

Persistent memory for agents. Stores preferences, decisions, facts, and events as a connected knowledge graph. Recalled by who, what, when, or why.

hypabase/hypabase · 32 tokens

cognee-permissions

Use when working with cognee's permission system — understanding or changing how users, roles, and tenants get access to datasets, how ACL grants work, where permissions are enforced in add/cognify/search/delete, and how the grant records surface in the memory-provenance view.

topoteretes/cognee · 62 tokens

cognee-cli

Use when the user wants to drive cognee from the terminal with cognee-cli — remember/recall/forget/improve memory commands, managing datasets and config, or database migrations.

topoteretes/cognee · 42 tokens

cognee-install

Use when the user wants to install cognee and run their first remember → recall flow with the Python SDK — fresh setup, virtual env, extras selection, or a minimal working example.

topoteretes/cognee · 42 tokens

understand-knowledge

Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.

Egonex-AI/Understand-Anything · 32 tokens