sessions

A command set for managing running Sprite sessions, which are persistent remote command executions that can be detached and reconnected later.

In plain words
What is it for?
It is for listing active sessions, reconnecting to a detached session, and terminating a session when it is no longer needed.
Why use it?
It lets long-running commands continue while disconnected and makes it possible to inspect or stop them afterward.

Command

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/superfly/claude-plugins/sessions
Clone the repo
git clone --depth 1 https://github.com/superfly/claude-plugins
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 303 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 $0.00012 $0.00303
Opus 5 $0.00006 $0.00151
Sonnet 5 $0.00002 $0.00061
Haiku 4.5 $0.00001 $0.00030

Measured yesterday against content hash 5b37c74ab14b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sessions 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 yesterday.

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.

sprite-handoff/commands/sessions.md · 62 lines

What it actually says

Manage Sprite Sessions

Manage running sessions in the active sprite. Sessions are persistent command executions that can be detached and reattached.

Actions

List Sessions (default)

Show all running sessions:

sprite sessions list

Attach to Session

Reconnect to a detached session:

sprite sessions attach <session-id>

Kill Session

Terminate a running session:

sprite sessions kill <session-id>

Behavior

  1. Get the active sprite with sprite use
  2. If no active sprite, inform user to run /sprite:create first
  3. Parse the action from arguments (default: list)
  4. Run the appropriate sprite sessions command
  5. Display results

Session Lifecycle

  1. Start with sprite exec -detachable "command"
  2. Detach with Ctrl+\ (keeps running in background)
  3. Reattach with sprite sessions attach <id>
  4. Kill with sprite sessions kill <id> when done

Output

For list:

  • Session ID
  • Command being run
  • Status (running, stopped)
  • Duration

For attach:

  • Reconnect to session output stream
  • Note: Ctrl+\ to detach again

For kill:

  • Confirmation of termination
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. yesterday First seen · 62 lines · 12 tokens per session scan A 5b37c74ab14b

Subscribe to this mod's changes

sessions is a command published in the GitHub repository superfly/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 303 once invoked, about $0.0001 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.