save-and-switch

save-and-switch is a command for Claude Code from liortesta/ClawdAgent. It costs 0 tokens per session (579 once invoked), scanned A, original, Apache-2.0.

A session handoff command that saves the current conversation's project context to persistent memory before you start a new conversation.

In plain words
What is it for?
Use it when switching to a fresh conversation while continuing the same project. It records what was done, what remains, and which files and technical details matter.
Why use it?
It reduces the need to repeat work when a conversation becomes long or expensive. The next session can use the saved progress, decisions, files, and unfinished tasks.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/liortesta/clawdagent/save-and-switch
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

Made for: Claude Code.

Wrote 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.

agentmods badge for save-and-switch

README.md
[![agentmods](https://agentmods.dev/badge/commands/liortesta/clawdagent/save-and-switch.svg)](https://agentmods.dev/commands/liortesta/clawdagent/save-and-switch)
Your own site
<a href="https://agentmods.dev/commands/liortesta/clawdagent/save-and-switch"><img src="https://agentmods.dev/badge/commands/liortesta/clawdagent/save-and-switch.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 579 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00579
Opus 5 $0.00000 $0.00290
Sonnet 5 $0.00000 $0.00116
Haiku 4.5 $0.00000 $0.00058

Measured 4d ago against content hash 8f44511f1e4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

save-and-switch 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 4d 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.

.claude/commands/save-and-switch.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Save & Switch — Smart Session Handoff

Save the current session context to persistent memory, then tell the user to start a fresh conversation to save costs. The new session will have full access to everything saved here.

Process:

Step 1: Gather Session Context

Analyze the current conversation and extract:

  • What was accomplished (features, fixes, decisions)
  • Current state of the project (what's running, what's pending)
  • Any open tasks or loose ends
  • Key file paths and line numbers that matter
  • Important technical details the next session needs

Step 2: Save to Memory Graph

Use the Memory MCP server (mcp__memory__create_entities and mcp__memory__create_relations) to persist:

Entity: Session Record

  • Name: session-{YYYY-MM-DD-HHmm} (use current timestamp)
  • Type: session
  • Observations: accomplished items, decisions, current state, open tasks

Entity: Active Project Context (update if exists)

  • Name: The project/feature name being worked on
  • Type: project-context
  • Observations: current branch, running servers, key files, pending work

Relations:

  • session → continues → previous session (if known)
  • session → works-on → project context

Step 3: Generate Session ID

The session ID is the entity name from Step 2: session-{YYYY-MM-DD-HHmm}

Step 4: Output to User

Print EXACTLY this format (in Hebrew since the user prefers Hebrew):

-------------------------------------------
  SESSION SAVED
-------------------------------------------

 Saved:    [bullet list of what was saved]
 Session:  session-{ID}
 Memory:   Persistent (available in all future sessions)

-------------------------------------------
 NEXT STEP
-------------------------------------------

 Start a new conversation and say:

   "Load session session-{ID} and continue from where we left off"

   OR just describe what you want — I remember everything.

 Why switch? This conversation has ~{estimate}K tokens of
 context. A fresh start = faster responses + lower cost.
-------------------------------------------

Read the full file on GitHub · 75 lines

Changes

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.

  1. 4d ago First seen · 75 lines · 0 tokens per session scan A 8f44511f1e4a

Subscribe to this mod's changes

save-and-switch is a command published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 8d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 579 tokens. 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.