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 letrplB/second-brain --skill dreamgit clone --depth 1 https://github.com/letrplB/second-brainWrote 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/letrplb/second-brain/dream)<a href="https://agentmods.dev/skills/letrplb/second-brain/dream"><img src="https://agentmods.dev/badge/skills/letrplb/second-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/letrplb/second-brain/dream"><img src="https://agentmods.dev/badge/skills/letrplb/second-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 | $0.00056 | $0.02610 |
| Opus 5.5 | $0.00022 | $0.01044 |
| Sonnet 5.5 | $0.00011 | $0.00522 |
| Haiku 4.5 | $0.00006 | $0.00261 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dream
Intent. Make the vault talk back. Without this verb, a second-brain is "a very organised way to forget things." /dream is the feedback loop — synthesis pushed at the user without them having to ask.
The output is a brief in inbox/, not a graph node. Briefs are prompts to think, not auto-generated content. If a brief surfaces something load-bearing, the user (or /extract invoked on the brief) promotes it to a synthesis claim in notes/synthesis/.
This separation is deliberate: the model can identify candidate connections; only the user can decide which become atoms in the graph.
Modes
--daily (default)
A 3-second read before the user opens anything else. Three asks — surfaced from claim activity in the last 7 days (configurable via --scope):
- Connections (3) — non-obvious links between recent captures and older notes the user probably forgot about. Each link is one sentence: "[[claim-A]] connects to [[older-claim-B]] because ."
- Pattern (1) — one pattern across the last week's reading. What is your brain working on, even if you haven't said it explicitly?
- Question (1) — one question worth sitting with today. Not a task. A question.
Output: inbox/dream-{YYYY-MM-DD}.md.
--weekly
Deeper, Monday-morning ritual. 15-minute read. Four asks — surfaced from the last 30 days (configurable):
- Emerging thesis — what idea is the vault building toward without it having been stated explicitly? Look at the new claims, the new MOCs, the questions that recur.
- Contradictions — what has been saved recently that contradicts something believed before?
confidence: contestedclaims are the obvious place to look; also flag claims whosecontradicts:arrays are non-empty. - Knowledge gaps — what is clearly not being read that should be? Look at the goals.md active threads vs. recent claim coverage. Where's the gap?
- One action — the single highest-leverage thing to do or think about this week. Not a task list. One sentence.
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 · 182 lines · 56 tokens per session scan A 3af42f600288
dream is a skill published in the GitHub repository letrplB/second-brain (1 stars, last pushed 5mo ago), licensed MIT. It adds 56 tokens to every session and 2,610 once invoked, about $0.0002 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
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
curate
Power-user audit of Wenlan's pending surfaces: accept or dismiss pending revisions (conflicts/merges), or audit pending captures (not yet confirmed). Most users want /brief for revisions; that handles the daily flow. Use /wenlan curate only for explicit deep-walk audits after bulk imports, or to walk the full queue…
pages
Browse, open, or print distilled pages, reusing the wenlan pages CLI for the actual open (one implementation on your PATH, no setup). /wenlan pages opens the page when one matches, or shows a small native picker when 2-4 match. /wenlan pages --print reads the page here instead of opening an editor. /wenlan pages lists…
forget
Delete a memory from Wenlan by ID. Destructive and cannot be undone — prefer /capture with supersedes for corrections. Invoked as /wenlan forget .
llm-wiki
Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate…
raytsystem-save
Stage a cited synthesis as a typed raytsystem DRAFT bundle and escaped preview. Use for SAVE, preserving a verified query answer, preparing a knowledge proposal, or creating a reviewable draft; never treat SAVE as canonical promotion or publication.