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 nap-zarogit 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/nap-zaro)<a href="https://agentmods.dev/skills/szotasz/marveen/nap-zaro"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/nap-zaro/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/nap-zaro"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/nap-zaro.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00068 | $0.03284 |
| Opus 5.5 | $0.00027 | $0.01314 |
| Sonnet 5.5 | $0.00014 | $0.00657 |
| Haiku 4.5 | $0.00007 | $0.00328 |
Grade C, and why
nap-zaro scanned grade C with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
| curl -s -X POST "http://localhost:$PORT/api/daily-log" -H "Content-Type: application/json" -H "Authorization: Bearer $TOKEN" -d @- Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find ~/.claude/skills ~/.claude/scheduled-tasks {{INSTALL_DIR}}/.claude/skills -name 'SKILL.md' -newermt "@$SINCE" 2>/dev/null Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
find ~/.claude/skills ~/.claude/scheduled-tasks {{INSTALL_DIR}}/.claude/skills -name 'SKILL.md' -newermt "@$SINCE" 2>/dev/null Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer $TOKEN" "http://localhost:$PORT/api/daily-log?agent={{MAIN_AGENT_ID}}&date=$TODAY" \ How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Napzáró bejegyzés a napi naplóba
Miért van ez a kör
A napi naplót a hajnali és reggeli körök írják (dream-engine, reggeli-napindító), ezért a naplóban a nap délben véget ér, pedig délután és este is folyik a munka (NAPLODELUTAN916, mért 2026-09-12..16: egyetlen napon sem volt bejegyzés 12:45 után). Az információ nem veszett el, csak az emlékek és a kanban között szóródik szét. Ez a kör naponta egyszer összegyűjti és egy bejegyzésben beírja.
Csendes kör: a beállított csatornára NEM küld üzenetet, AKKOR SEM, ha a prompt elején
kézbesítési utasítás áll (pl. "Az eredményt küldd el "). A kör terméke egy
POST /api/daily-log írás, nem egy üzenet, és a 3-4. lépésben nincs is jelentés-lépés.
Ez a bekezdés szándékosan NEM hivatkozik a task-config.json-ra: a frissítés a két fájlt
külön-külön cseréli, és a gazda által szerkesztett config (ütemezés, enabled) a régi
"type" értékkel maradhat, miközben ez a fájl frissül. A csendet ezért ennek a szövegnek kell
kimondania, függetlenül attól, mit mond a config. (A másik irány -- valódi esti jelentés a
gazdának -- védhető, de ahhoz a skillbe egy jelentés-lépés is kellene, és az termék-döntés,
nem dokumentáció-javítás.)
Eljárás
- Előkészítés, és kilépés, ha ma már lefutott. Ez a kör NEM idempotens (a napló
append-only), ezért egy kétszer kézbesített prompt két bejegyzést írna. Ha a mai naplóban
már van
Napzáróbejegyzés, állj meg, és ne írj semmit.
PORT="$(sed -n 's/^WEB_PORT=//p' {{INSTALL_DIR}}/.env 2>/dev/null | head -1 | tr -d '"')"; PORT="${PORT:-3420}"
TOKEN="$(cat {{INSTALL_DIR}}/store/.dashboard-token)"
TODAY="$(date +%F)"
curl -s -H "Authorization: Bearer $TOKEN" "http://localhost:$PORT/api/daily-log?agent={{MAIN_AGENT_ID}}&date=$TODAY"
| python3 -c "import json,sys; rows=json.load(sys.stdin); print('MAR_LEFUTOTT' if any('Napzáró' in r['content'] for r in rows) else 'last_ts=%d' % max([r['created_at'] for r in rows] or [0]))"
A dátumot MINDIG add meg (`date=`): a végpont alapértéke UTC-nap, este 22 és éjfél között
az a holnapi nap lenne.
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.
- today Changed · +52 lines d7e3409a3667
- 22d ago Changed · +10 lines db66109fe176
- 29d ago First seen · 86 lines · 68 tokens per session scan C 2caf1ab66cd4
nap-zaro is a skill published in the GitHub repository Szotasz/marveen (120 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 3,284 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 4 findings (sends data to an external url, reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-18.
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…
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…
family-knowledge
Family knowledge base for recording and retrieving household facts (members, allergies, dietary rules, doctors, schedules, house rules, pets, important dates).
user-memory
Remember and recall durable facts about the current user across sessions. Stores preferences, ongoing context, and things the user asked you to remember — scoped to each individual user.
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.
openakashic
Persistent memory for AI agents across sessions. Search what others figured out, write what you learn, publish what deserves a wider audience.