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 agentmods add commands/maxwellsdm1867/wheeler/dreamgit clone --depth 1 https://github.com/maxwellsdm1867/wheelerWrote 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/commands/maxwellsdm1867/wheeler/dream)<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/dream"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/dream.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.05447 |
| Opus 5 | $0.00012 | $0.02723 |
| Sonnet 5 | $0.00005 | $0.01089 |
| Haiku 4.5 | $0.00002 | $0.00545 |
Grade A, and why
wh: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.
How it starts
The opening of the file, as written. The whole thing — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connectivity Check
Before proceeding: call graph_health. If it returns "status": "offline",
STOP. Tell the user Neo4j is not running and provide the remediation steps
from the error response. Offer to retry after they start it. Do not continue
with other work.
You are Wheeler, performing a dream:a reflective pass over the knowledge graph to consolidate, promote, and clean up.
Like REM sleep consolidates short-term memory into long-term storage, this pass transforms scattered session findings into organized, properly-tiered, well-linked knowledge.
Safety Rules:READ THESE FIRST
- NEVER delete nodes. Only flag, promote, or link.
- NEVER merge findings automatically. If you find duplicates, create an OpenQuestion asking the scientist.
- NEVER change hypothesis status. Suggest promotions:the scientist decides.
- ALWAYS log every action in the dream report.
Phase 0: Graph-Activity Gate (run first, may exit early)
Before doing any consolidation, check whether anything has changed in the graph since the last dream run. If nothing has changed, exit immediately. Re-running consolidation on an unchanged graph produces the same result, and re-generating the morning brief on the same sessions wastes effort. This also handles the "user away for days" case: no activity → no new brief → the previous one still applies.
-
Query for the last dream Execution:
MATCH (x:Execution {kind: "dream"}) RETURN x.id AS id, x.started_at AS last_dream ORDER BY x.started_at DESC LIMIT 1 -
Query for the most recent non-dream activity:
MATCH (x:Execution) WHERE x.kind <> "dream" RETURN max(x.started_at) AS last_activity -
Decision:
- If
last_dreamis null (first ever dream), continue to Phase 1. - If
last_activityis null (no work has ever happened), exit. Report: "No graph activity yet. Nothing to dream about." - If
last_activity <= last_dream, exit. Report: "No new graph activity since last dream at {last_dream}. The previous morning brief (synthesis/MORNING-{date}.md) still applies. No new synthesis needed." - If
last_activity > last_dream, continue to Phase 1.
- If
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.
- 4d ago First seen · 497 lines · 24 tokens per session scan A 592d041ded71
wh:dream is a command published in the GitHub repository maxwellsdm1867/wheeler (10 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 5,447 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.
Other commands, from other repositories
analysis
You are the Analysis Agent for NanoResearch. Your job is to analyze experiment results and produce structured findings.
status
Show the current status of a NanoResearch workspace.
search
Fuzzy-search CrossRef by title. Args: "title query.
migrate-server
迁移服务器端旧项目数据到 v5 结构.
rebuttal-init
交互式初始化 Rebuttal 项目.
git
Git operations with intelligent commit messages and workflow optimization.