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.
npx skills add X-Arc-ai/brain-cli --skill brain-dreamgit clone --depth 1 https://github.com/X-Arc-ai/brain-cliWrote 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/x-arc-ai/brain-cli/brain-dream)<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/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/x-arc-ai/brain-cli/brain-dream"><img src="https://agentmods.dev/badge/skills/x-arc-ai/brain-cli/brain-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 | $0.00016 | $0.00299 |
| Opus 5.5 | $0.00006 | $0.00120 |
| Sonnet 5.5 | $0.00003 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
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 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.
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.
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
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.
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 · 58 lines · 16 tokens per session scan A ff70294f146e
brain-dream is a skill published in the GitHub repository X-Arc-ai/brain-cli (5 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 299 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
omnigraph
Operate OmniGraph graphs and deployments. Use for .pg schemas, .gq queries, OmniGraph CLI commands, file:///s3:///az:// graph URIs, cluster.yaml, operator config, bearer-authenticated servers, graph-backed knowledge or memory, Blob values, embeddings, branches, commits, and change feeds. Apply especially before schema…
brainctl
Unified agent memory CLI — read, write, search, and maintain the shared memory spine (brain.db). Use for persistent cross-session memory, knowledge graph, event logging, decisions, affect tracking, and consolidation.
sibyl
Persistent memory and task coordination for this project. Invoke for any prompt about past work, project state, in-progress tasks, prior decisions, gotchas, or capturing a non-obvious learning. Also covers semantic search across project knowledge and external docs.
graft
Persistent graph memory shared across conversations and agents. Graft is a prompter, not a cache: it hands you notes that may be close to the problem in front of you, and a close note is already a win - it gives you a starting point and reminds you what was decided before. Search it before non-trivial work, and write…
memory-audit
Maintenance pass + health check of the graft graph. Runs the graft maintain loop: checks what is due, applies the mechanical cleanup, then adjudicates every maintenance candidate (near duplicates, supersessions, contradictions, memories whose source file changed or disappeared, keyword variants, stale low-value notes)…
memoryze
Distill the current conversation (or a specified excerpt) into N high-quality graft nodes and save them. Triggered by /memoryze, "save this to memory", "ricorda questo", "memorize this", or whenever the user explicitly wants the agent to commit knowledge to the persistent graph. The user can hint at granularity…