dream

dream is a skill for Claude Code, Codex from hyperb1iss/hyperskills. It costs 59 tokens per session (2,057 once invoked), scanned A, original, MIT.

A conversation-review skill that looks across recent coding-agent sessions and adds repeated lessons and connections to Sibyl, a knowledge store.

In plain words
What is it for?
Use it for nightly reviews, session summaries, transcript mining, and maintaining shared knowledge from past work.
Why use it?
It helps recover useful patterns and recurring problems that may be missed when each conversation is considered alone.

Skill for Claude CodeCodex

Part of the hyperskills plugin — 14 skills shipped together

Install

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.

agentmods
npx agentmods add skills/hyperb1iss/hyperskills/dream
Any agent
npx skills add hyperb1iss/hyperskills --skill dream
Clone the repo
git clone --depth 1 https://github.com/hyperb1iss/hyperskills

Made for: Claude Code, Codex.

Or install hyperskills, the plugin that ships this one along with the rest of its 14 skills.

Wrote 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.

agentmods badge for dream

README.md
[![agentmods](https://agentmods.dev/badge/skills/hyperb1iss/hyperskills/dream.svg)](https://agentmods.dev/skills/hyperb1iss/hyperskills/dream)
Your own site
<a href="https://agentmods.dev/skills/hyperb1iss/hyperskills/dream"><img src="https://agentmods.dev/badge/skills/hyperb1iss/hyperskills/dream.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,057 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00059 $0.02057
Opus 5 $0.00030 $0.01028
Sonnet 5 $0.00012 $0.00411
Haiku 4.5 $0.00006 $0.00206

Measured today against content hash 794b4bf4043b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 today.

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.

skills/dream/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dream: Conversation Review and Knowledge Consolidation

Recover decisions and lessons that inline capture missed, then connect repeated observations across the authorized sessions. Preserve what a future session needs to know, with its provenance and limits. A conversation contains claims and proposed actions as well as results; repetition does not turn a claim into a fact.

Scope and depth

Use the requested projects and time span. When unspecified, start with recent sessions for the current project and say what you covered. Cross-project discovery is appropriate for an explicitly broad dream; access to a transcript is not permission to move its contents into another project's memory.

Mode Scope and result
Quick Recent work in the current project; capture the useful missed lessons
Default Sessions since the previous checkpoint; consolidate recurring decisions and failures
Deep Requested projects and interval; add cross-session synthesis and staleness checks
Lucid Named sessions or topic; targeted extraction
Mining run Explicit corpus-scale request; partition independent session sets when delegation is authorized

These modes set depth, not output quotas. A short session can contain a decisive correction; a large transcript can contain only duplicated context and tool output. Do not infer value from byte size or require a fixed number of captures.

Orient and discover

Load the installed sibyl skill and version-matched contract. Recall prior dream coverage and relevant knowledge:

sibyl skill get contract
sibyl context "dream report and uncaptured lessons for this project" --intent review

Inspect the returned report when its coverage is needed. Track source session IDs and processed positions, not only a wall-clock date. An ongoing session can append useful material after a previous dream; a fork or compaction can repeat older material under new records.

Read the full file on GitHub · 135 lines

Files

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.

Changes

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.

  1. today Changed · -146 lines · -7 tokens per session scan B → A 794b4bf4043b
  2. 5d ago First seen · 281 lines · 66 tokens per session scan B b7270207e24b

Subscribe to this mod's changes

dream is a skill published in the GitHub repository hyperb1iss/hyperskills (30 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 2,057 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

comet-memory

使用于 Comet 需要根据有界语义评审包判断是否值得保存个人记忆、候选、更新、遗忘或跳过时。.

rpamis/comet · 38 tokens

recall-memory

Recall relevant long-term memories on demand. Given a topic or question, judges relevance from pre-loaded metadata, loads only relevant files, and returns a concise summary to the main agent.

clacky-ai/openclacky · 40 tokens

agent-expert-creation

Create specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building domain-specific agents that maintain mental models via expertise files and self-improve prompts.

majiayu000/claude-skill-registry · 43 tokens

relevance-coarse-filter

Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.

elvisun/newsjack · 57 tokens

self-improve

Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…

tobihagemann/turbo · 125 tokens

ac-memory-manager

Manage persistent memory for autonomous coding. Use when storing/retrieving knowledge, managing Graphiti integration, persisting learnings, or accessing episodic memory.

majiayu000/claude-skill-registry · 35 tokens