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 Szotasz/marveen --skill dream-enginegit clone --depth 1 https://github.com/Szotasz/marveenWrote 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/szotasz/marveen/dream-engine)<a href="https://agentmods.dev/skills/szotasz/marveen/dream-engine"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/dream-engine/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/szotasz/marveen/dream-engine"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/dream-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 112 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Agent Snooping · line 110 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00051 | $0.04178 |
| Opus 5.5 | $0.00020 | $0.01671 |
| Sonnet 5.5 | $0.00010 | $0.00836 |
| Haiku 4.5 | $0.00005 | $0.00418 |
Grade B, and why
dream-engine scanned grade B with 2 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 24d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls ~/.claude/skills/ | head Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST http://localhost:{{WEB_PORT}}/api/memories/backfill -H "Authorization: Bearer $(cat {{INSTALL_DIR}}/store/.dashboard-token)" How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Te most a "Dream Engine" éjszakai analízis-loopot futtatod. 02:07-kor vagy, {{OWNER_NAME}} alszik, NE küldj üzenetet a beállított csatornára.
A cél: az aznapi tudást átkonszolidálni és reggelre (07:30 Reggeli Napindító) felkészülni 4 priorizált javaslattal.
Mit kell csinálnod
Generálj egy {{INSTALL_DIR}}/DREAM.md fájlt az alábbi 5 bucket alapján. A formátum a fájl alján van.
Bucket 1 — 💡 Skill-javaslatok (flotta-szintű)
Nézz végig MINDEN agent (a fő-ágens és az összes sub-agent) tegnapi (24h) memóriáit és napi naplóját. Kerítsd ki:
- Volt-e 3+ szor visszatérő, manuálisan ismételt művelet ami skill-be illeszthető?
- Új, NEM lefedett pattern amit érdemes lenne skillbe önteni?
SQL minta:
sqlite3 {{INSTALL_DIR}}/store/claudeclaw.db "SELECT agent_id, content, keywords FROM memories WHERE created_at > strftime('%s', 'now', '-24 hours') AND category IN ('hot','warm') ORDER BY agent_id, created_at"
Output: 0-2 konkrét skill-javaslat. Mindegyikhez: cím + 1 mondat indoklás + "flotta-szintű" vagy "agent: <név>".
Bucket 2 — 🧹 Memória-egészség (NE delete, COLD-tier-be mozgatás)
# Vektorizálás ellenőrzés
sqlite3 {{INSTALL_DIR}}/store/claudeclaw.db "SELECT COUNT(*) as total, COUNT(embedding) as with_emb FROM memories"
# Ha NEM 100%, hívd meg a backfill endpoint-ot (Ollamaval embeddeli a hianyzo ID-kat):
curl -s -X POST http://localhost:{{WEB_PORT}}/api/memories/backfill -H "Authorization: Bearer $(cat {{INSTALL_DIR}}/store/.dashboard-token)"
# Antikvált hot-tier (>7 napos hot, nem hivatkozott a memories_fts-en az elmúlt 24h-ban)
# FIGYELEM -- a CAST és a COALESCE MINDKETTŐ KÖTELEZŐ, ne vedd ki:
# a created_at/accessed_at INTEGER, a strftime('%s',...) viszont TEXT-et ad,
# és SQLite-ban az `integer < text` MINDIG IGAZ (típus-sorrend: INTEGER < TEXT).
# CAST nélkül ez a lekérdezés AZ ÖSSZES hot memóriát visszaadja, a mai aktívakat is.
# Kétszer okozott kárt: 2026-07-30 (148 sor cold-ba, köztük aznapiak) és 2026-07-31 (35 sor).
# A KOR dönt, nem az olvasottság (DREAMHOTKOR916): az accessed_at-et a memória-kereső
# és a heartbeat minden olvasáskor frissíti, ezért a gyakran olvasott sorok sosem öregedtek
# ki, a hot réteg nem ürült (2026-09-16: 57 hot sorból 38 ilyen). Az updated_at a tartalom-
# vagy kategória-váltáskor frissül (memories_touch trigger), NULL is lehet -> COALESCE a
# created_at-re, ami sosem NULL. Így a ma átírt régi sor sem esik ki.
sqlite3 {{INSTALL_DIR}}/store/claudeclaw.db "SELECT id, content, created_at, updated_at FROM memories WHERE category='hot' AND COALESCE(updated_at, created_at) < CAST(strftime('%s', 'now', '-7 days') AS INTEGER)"
What ships with it
1 file 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.
- 24d ago Changed · +8 lines ee0bcdfacad9
- 1mo ago Changed · +4 lines 272f14ef65f7
- 1mo ago First seen · 156 lines · 51 tokens per session scan B 4bd2f1852664
dream-engine is a skill published in the GitHub repository Szotasz/marveen (123 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 4,178 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (enumerates other installed skills, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
openopc
An organisation runtime for turning an AI assistant into a group of role-based workers. It creates an organisation structure, breaks work into dependent tasks that can run in parallel, tracks approvals and handoffs, and stores organisational memory.
oma-coordination
Coordinate assigned specialist tasks and handoffs manually. Use when supervising a multi-agent project step by step.
oma-pm
Turn product requirements into scoped tasks with dependencies and acceptance criteria. Use for implementation planning and prioritization.
memory
Use this skill when Pioneer should proactively use durable memory or recalled context: decide whether memory can improve a turn, answer from remembered user/project facts, request memory tools, search/list/get stored memories, save durable preferences or project decisions, forget memories, audit or clean up memory, or…
recall
Reconstruct your recent working context from your own session history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming…