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/timoncool/dream-skill/dreamnpx skills add timoncool/dream-skill --skill dreamgit clone --depth 1 https://github.com/timoncool/dream-skillWrote 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/timoncool/dream-skill/dream)<a href="https://agentmods.dev/skills/timoncool/dream-skill/dream"><img src="https://agentmods.dev/badge/skills/timoncool/dream-skill/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 | $0.00000 | $0.08304 |
| Opus 5 | $0.00000 | $0.04152 |
| Sonnet 5 | $0.00000 | $0.01661 |
| Haiku 4.5 | $0.00000 | $0.00830 |
Grade B, and why
dream scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$LOCK_DIR" && mkdir "$LOCK_DIR" && echo $$ > "$LOCK_DIR/pid" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dream — режим сна (read-only)
Рефлексивный pass по памяти, заметкам, проектам. Адаптация autoDream из утечки Claude Code (services/autoDream/consolidationPrompt.ts):
- Никаких изменений кроме записи двух файлов отчёта
- Phase Reflect — синтез insights и новых идей
- HTML-чекбоксы для выбора что применить
- Применяет — отдельный skill
wake(не этот)
Объекты skill — что читаем
| Объект | Действие |
|---|---|
Memory dir текущего cwd (~/.claude/projects/<slug>/memory/) |
Read only |
Memory dirs ВСЕХ проектов (~/.claude/projects/*/memory/) — если cross-project обзор полезен |
Read only (опционально) |
Глобальный ~/.claude/CLAUDE.md — user instructions для всех cwd |
Read only (обязательно — помогает dedup feedback'ов) |
Проектный <cwd>/CLAUDE.md если есть |
Read only |
Заметки в cwd (*.md, *.txt в корне рабочей папки) |
Read only |
| Проекты в cwd (подпапки с маркерами) | Read only (README + docs/) |
| JSONL транскрипты сессий | Narrow grep only (не читать целиком) |
Глобальный ~/.claude/skills/ каталог |
List only (orientation, не Read контента) |
Staging satori (~/.claude/satori/staging/) + его state.db |
Read only (если есть — Phase 2 п.7 Skill harvest) |
| Код, исходники, JSON dumps, логи | Не трогаем |
Единственная Write-операция: запись двух файлов отчёта в <cwd>/.
Файлы skill
SKILL.md(этот файл) — workflow + safety rulesreferences/action_types.md— JSON contract для proposals (читай перед Phase 4)assets/template.html— HTML шаблон отчёта (используется build_report.py)assets/build_report.py— helper script: payload JSON → MD + HTML (используется в Phase 4)
Как вычислить пути (Win11 Git Bash)
Memory dir: C:\Users\<user>\.claude\projects\<slug>\memory\
<slug> = Windows-style cwd с заменой : и / на -. Пример: cwd D:\Projects\TEMP\ → D:/Projects/TEMP (через pwd -W) → slug D--Projects-TEMP.
What ships with it
3 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.
- 5d ago First seen · 454 lines · 0 tokens per session scan B d772798a34eb
dream is a skill published in the GitHub repository timoncool/dream-skill (3 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 8,304 tokens. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
takenotes
Saves durable knowledge into permanent storage — typed memory, CLAUDE.md, or a docs/ file — and corrects anything already stored that has gone stale. Handles both a single fact and a whole-session harvest. Use when the user says "takenotes", asks you to remember or record something, asks you to save what was learned…
putdown
Writes a session handoff file that a fresh Claude Code session reads via /pickup, harvests durable knowledge into memory and CLAUDE.md (via /takenotes when installed), then commits and pushes all session work. Use when the user says "putdown", when ending or stepping away from a working session, or when the context…
pickup
Loads the most recent putdown handoff file for the current project and primes the session with full prior context. Use when the user says "pickup", asks "where were we" after opening a fresh window, or wants to resume work from a prior session that ended with /putdown. Do NOT use for reopening a previous Claude…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…
second-brain
When you want to capture into, compile, query, lint, or connect your personal Second Brain. Wraps the Karpathy LLM Wiki schema (Obsidian or any markdown vault) — raw/ (unprocessed sources), wiki/ (AI-compiled interlinked topic pages), outputs/ (generated artifacts). Tool-agnostic in design but defaults to a vault at…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.