Zylos is open-source infrastructure that gives an AI agent persistent memory, scheduled activity, communication channels, and the ability to maintain and extend itself. Individuals and teams use it with Claude Code or Codex through Telegram, Lark, or a web console. Its catalogue add-ons define settings, instructions, and skills for operating the agent.
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 zylos-ai/zylos-core --skill new-sessiongit clone --depth 1 https://github.com/zylos-ai/zylos-coreWrote 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/zylos-ai/zylos-core/new-session)<a href="https://agentmods.dev/skills/zylos-ai/zylos-core/new-session"><img src="https://agentmods.dev/badge/skills/zylos-ai/zylos-core/new-session/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/zylos-ai/zylos-core/new-session"><img src="https://agentmods.dev/badge/skills/zylos-ai/zylos-core/new-session.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.00948 |
| Opus 5 | $0.00018 | $0.00474 |
| Sonnet 5 | $0.00007 | $0.00190 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
new-session 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 11d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Session Skill
Start a fresh session with graceful handoff. Use runtime-specific switch commands:
- Claude:
/clear - Codex:
/exit
When to Use
- Context usage exceeds the runtime threshold (triggered automatically by context monitoring)
- User explicitly asks for a new session or context reset
- When you need a clean context but don't need to reload settings/hooks (use restart-claude for that)
Pre-Switch Checklist
Before sending the session switch command, complete these steps in order:
1. Inventory running background tasks
Check for running background agents using the current runtime's available agent/task listing capability. For Claude, this is TaskList.
Runtime behavior differs here:
- Claude: background subagents survive
/clear, so do not stop them. - Codex:
/exitterminates background tasks. Before enqueueing/exit, make sure required background work has finished.
For each running task, note:
- Agent ID (e.g.,
a42c1aabc5b984e69) - What it's doing (brief description)
- Output file path (so the new session can check on it)
This information goes into the handoff summary (step 2).
2. Write a session handoff summary
Write a brief message covering:
- What was being worked on (active tasks, user requests in progress)
- Current state (what's done, what's pending, any blockers)
- Running background tasks (from step 1 — include agent/task IDs and any output file paths or result handles so the new session can check on them with the runtime-appropriate output mechanism)
- What the next session should pick up (if anything)
3. Send the handoff summary
Send the full handoff summary to the internal void channel via C4:
cat <<'EOF' | node ~/zylos/.claude/skills/comm-bridge/scripts/c4-send.js "void" "session-handoff"
<handoff summary>
EOF
The void channel is record-only: the message is stored in C4 conversation
history (so the new session's startup hook, c4-session-init, includes it in
startup context) but is never delivered to any real channel or display
surface.
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.
- 11d ago First seen · 90 lines · 36 tokens per session scan A 46201b12a8f3
new-session is a skill published in the GitHub repository zylos-ai/zylos-core (1,151 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 948 once invoked, about $0.0002 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.
Other skills, from other repositories
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…
compaction-skill
Manage memory compaction by summarizing conversation history when approaching token limits.
memory-skill
Manage conversation memory. Use when user asks to remember something, recall information, view/edit conversation history, or manage short/long-term memory.
openviking-context-database
Use OpenViking from OpenClaw through @openviking/openclaw-plugin: long-term memory, session archives, resource and Agent Skill import, semantic recall, recall trace debugging, and externalized tool-result recovery. Prefer this skill when the user wants to use, query, debug, or operate OpenViking context from an…
ov-experience-memory
Retrieve and apply OpenViking Experience memories through the Agent runtime's generic OpenViking search and read tools. Use before or during executable, multi-step, or tool-based work such as coding, file or data changes, configuration, deployment, workflow execution, and failure recovery when prior operational…
openviking-memory
Recall and persist long-term memory through the OpenViking MCP tools. Use at the start of any substantive task (coding, configuration, debugging, multi-step or tool-based work) to retrieve relevant prior knowledge with find/search/read, and during or after work to persist durable facts, preferences, decisions, and…