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 sebaskauf/agentic-os --skill session-uebergabegit clone --depth 1 https://github.com/sebaskauf/agentic-osWrote 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/sebaskauf/agentic-os/session-uebergabe)<a href="https://agentmods.dev/skills/sebaskauf/agentic-os/session-uebergabe"><img src="https://agentmods.dev/badge/skills/sebaskauf/agentic-os/session-uebergabe.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 5.1 | $0.00147 | $0.01554 |
| Opus 5 | $0.00073 | $0.00777 |
| Sonnet 5 | $0.00029 | $0.00311 |
| Haiku 4.5 | $0.00015 | $0.00155 |
Grade A, and why
session-uebergabe 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 6d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session-Uebergabe
Dein Job: am Ende einer Arbeits-Session ein kurzes, dichtes Handoff-Dokument schreiben. Ziel ist, dass eine komplett frische Claude-Session (oder du selbst morgen) in 30 Sekunden wieder voll im Bild ist: Was wurde gemacht, wo stehen wir, was kommt als Naechstes, was ist offen, welche Dateien sind wichtig.
Das ist ein READ-ONLY plus EIN-FILE-WRITE Skill. Du liest Kontext und schreibst genau eine Markdown-Datei. Du veraenderst nichts am Projekt, fasst nichts an, loescht nichts.
Grundprinzip
Ein Handoff ist kein Roman. Es ist eine Landekarte fuer die naechste Session. Schreib so, dass jemand der NICHTS von dieser Session weiss sofort weiterarbeiten kann. Konkret statt vage: nicht "Bug gefixt", sondern "Login-Bug in auth/login.ts Zeile 42 gefixt, Token wurde doppelt gesetzt".
Ablauf
1. Kontext sammeln (READ-ONLY)
Bevor du schreibst, sammel was du brauchst. Nutz dazu was vorhanden ist:
- Den Gespraechsverlauf dieser Session ist deine Hauptquelle. Geh durch was tatsaechlich passiert ist: welche Aufgabe, welche Entscheidungen, welche Dateien, welche Sackgassen.
- Glob/Read fuer relevante Dateien, falls du Pfade oder den letzten Stand verifizieren willst. Nur lesen, nie raten. Wenn du einen Pfad nennst, soll er stimmen.
- Falls Git im Spiel war und du es aus dem Verlauf kennst: nenn Branch, letzten Commit-Gedanken, ob etwas uncommitted ist. Erfinde keine Hashes.
Wenn etwas unklar ist (z.B. was wirklich der naechste Schritt sein soll), frag den User kurz nach, statt zu raten. Eine gezielte Rueckfrage ist besser als ein falsches Handoff.
2. Session-Typ erkennen und Sektionen waehlen
Erzwing nicht jede Sektion. Waehl die die passen. Typische Typen:
- Bug-Fix / Debug: Was war der Bug, Root-Cause, Fix, was noch nicht getestet.
- Feature-Build: Was gebaut, was fehlt noch, wie testen.
- Setup / Konfiguration: Was eingerichtet, welche Schritte noch offen, welche Credentials/Platzhalter.
- Planung / Research: Erkenntnisse, Entscheidungen, offene Fragen, naechste Recherche.
- Content / Schreiben: Was produziert, Stand der Drafts, was noch fehlt.
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.
- 6d ago First seen · 99 lines · 147 tokens per session scan A 1b0e437e99cd
session-uebergabe is a skill published in the GitHub repository sebaskauf/agentic-os (2 stars, last pushed 1mo ago), licensed MIT. It adds 147 tokens to every session and 1,554 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.