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 simbajigege/book2skills --skill session-dreamgit clone --depth 1 https://github.com/simbajigege/book2skillsWrote 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/simbajigege/book2skills/session-dream)<a href="https://agentmods.dev/skills/simbajigege/book2skills/session-dream"><img src="https://agentmods.dev/badge/skills/simbajigege/book2skills/session-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/simbajigege/book2skills/session-dream"><img src="https://agentmods.dev/badge/skills/simbajigege/book2skills/session-dream.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00097 | $0.01129 |
| Opus 5 | $0.00048 | $0.00564 |
| Sonnet 5 | $0.00019 | $0.00226 |
| Haiku 4.5 | $0.00010 | $0.00113 |
Grade A, and why
session-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 12d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
session-dream
A manual trigger for the memory distillation that Claude Code's autoDream service does automatically in the background. Where autoDream fires after 5+ sessions and 24+ hours, this skill fires on demand — letting you capture a session's insights before they're lost in compaction.
How autoDream works (the source pattern)
From services/autoDream/consolidationPrompt.ts, the autoDream process has 4 phases:
- Orient — scan what memory already exists, avoid creating duplicates
- Gather signal — identify new information worth persisting (logs, session transcripts, drifted facts)
- Consolidate — write or update topic files, merge rather than duplicate, fix contradictions
- Prune and index — keep MEMORY.md under max lines, one pointer per file, remove stale entries
This skill follows the same 4-phase structure but applies it to the current conversation rather than historical transcripts.
Distillation Process
Phase 1 — Orient
Check what memory already exists:
- Read
MEMORY.mdif it exists (or note that it doesn't) - Scan memory topic files mentioned in the index
- Note which topics are already covered so new entries extend rather than duplicate
Phase 2 — Gather signal from this session
Review the current conversation and identify:
High-value (always distill):
- Architectural decisions with reasoning ("chose X over Y because Z")
- Approaches that failed and why ("tried A, hit wall B, abandoned — don't retry")
- Surprising discoveries about the codebase or APIs
- User preferences stated or demonstrated repeatedly
- Constraints or requirements that weren't in any file
- Corrections to prior assumptions
Medium-value (distill if not easily discoverable):
- Naming conventions used in this session
- Test setup patterns discovered
- Environment-specific quirks
- Current blockers and their root causes
Low-value / skip:
- What files were read
- What commands were run
- Implementation details visible in code
- Step-by-step narration of what was done
What ships with it
2 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.
- 12d ago First seen · 116 lines · 97 tokens per session scan A f75d5c93a1e8
session-dream is a skill published in the GitHub repository simbajigege/book2skills (163 stars, last pushed 17d ago), licensed MIT. It adds 97 tokens to every session and 1,129 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
crewai-multi-agent
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
memory-search
Search conversation history and semantic memory to recall previous discussions, decisions, and context. Use when the user asks to "search memory", "what did we discuss", "remember when", "find previous conversation", "check history", or before starting work to recall prior decisions.
agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
agent-memory-systems
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A…
conversation-memory
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.