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 skills/aiocean/claude-plugins/aio-dreamnpx skills add aiocean/claude-plugins --skill aio-dreamgit clone --depth 1 https://github.com/aiocean/claude-pluginsWrote 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/aiocean/claude-plugins/aio-dream)<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-dream"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-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 | $0.00023 | $0.01113 |
| Opus 5 | $0.00012 | $0.00557 |
| Sonnet 5 | $0.00005 | $0.00223 |
| Haiku 4.5 | $0.00002 | $0.00111 |
Grade A, and why
aio-dream scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dream: Memory Consolidation
You are performing a dream — a reflective pass over your memory files. Synthesize what you've learned recently into durable, well-organized memories so that future sessions can orient quickly.
Environment
- Memory directory: !
echo "${CLAUDE_MEMORY_DIR:-$HOME/.claude/projects/$(pwd | sed 's|/|-|g')/memory}" - Session transcripts: !
echo "${CLAUDE_PROJECT_DIR:-$HOME/.claude/projects/$(pwd | sed 's|/|-|g')}"(JSONL files — each file is one past session)
Phase 1 — Orient
lsthe memory directory to see what already exists- Read
MEMORY.mdto understand the current index - Skim existing topic files so you improve them rather than creating duplicates
- If
logs/orsessions/subdirectories exist (assistant-mode layout), review recent entries there
Phase 2 — Gather recent signal
Look for new information worth persisting. Sources in rough priority order:
- Daily logs (
logs/YYYY/MM/YYYY-MM-DD.md) if present — these are the append-only stream - Existing memories that drifted — facts that contradict something you see in the codebase now
- Session transcripts — the transcript directory contains JSONL files of past sessions. Grep them for relevant context:
Use narrow, specific terms relevant to what you found in Phase 1 (e.g., a project name, a tool, a decision topic). Read surrounding lines when a match looks valuable.grep -rn "<narrow term>" <transcript-dir>/ --include="*.jsonl" | tail -50
Phase 3 — Consolidate
For each thing worth remembering, write or update a memory file at the top level of the memory directory.
Memory file format
---
name: {{memory name}}
description: {{one-line description — used to decide relevance in future conversations, so be specific}}
type: {{user | feedback | project | reference}}
---
{{memory content}}
Memory types
| Type | What to store | Scope |
|---|---|---|
| user | Role, goals, preferences, knowledge | Always private |
| feedback | User's guidance on approach — corrections AND confirmations | Private or team |
| project | Ongoing work, goals, bugs, incidents — NOT derivable from code/git | Bias toward team |
| reference | Pointers to external systems (Linear, Grafana, Slack, etc.) | Usually team |
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.
- 5d ago First seen · 119 lines · 23 tokens per session scan A 1e93abaa15e7
aio-dream is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 1,113 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 skills, from other repositories
catchup
Restore context after /clear by summarizing recent work and project state.
project-brain
Triggers (all require explicit user request — do NOT activate just because a brain/ folder exists): (1) The user wants to set up project-level memory ("set up project brain", "scaffold project context", "init project brain", "建项目脑"). (2) The user is in a directory containing brain/ AND explicitly asks to resume /…
align-context
Update all context files (task, spec, task-context, worklog) to reflect current state of work — fixes stale entries, fills missing knowledge, reports what changed.
vellum-memory-v3-migration
One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles with a stand-alone lead and queryable sections — with loss-proof staging, assistant-reviewed authoring, and a retrieval-eval gate before cutover.
mnemos
Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/handoffs as distinct node types with per-type eviction policies.
grimoire
Use when the user says 'update context', 'update claude', 'save library', or after significant project changes.