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 agentmods add commands/sumulige/sumulige-claude/sessionsgit clone --depth 1 https://github.com/sumulige/sumulige-claudeWrote 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/commands/sumulige/sumulige-claude/sessions)<a href="https://agentmods.dev/commands/sumulige/sumulige-claude/sessions"><img src="https://agentmods.dev/badge/commands/sumulige/sumulige-claude/sessions.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 | $0.00006 | $0.00377 |
| Opus 5 | $0.00003 | $0.00188 |
| Sonnet 5 | $0.00001 | $0.00075 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade B, and why
sessions scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/sessions/active-sessions.json What it actually says
Manage and display information about parallel Claude sessions.
Show Session Status
Display all active parallel sessions:
node .claude/hooks/multi-session.cjs --status
Session Management Best Practices
Based on Boris Cherny's workflow:
Terminal Sessions (Local)
- Number your terminal tabs 1-5
- Use system notifications to know when Claude needs input
- Run different agents in different tabs:
- Tab 1: Conductor (planning/coordination)
- Tab 2: Architect (design/architecture)
- Tab 3: Builder (implementation)
- Tab 4: Reviewer (code review)
- Tab 5: Explorer (research)
Web Sessions (claude.ai/code)
- Run 5-10 web sessions in parallel with local sessions
- Use
&to hand off local sessions to web - Use
--teleportto switch between local and web - Start sessions from mobile Claude app for async work
Session Handoff
To hand off a session to web:
# End local session with summary
# The session context will be available in claude.ai/code
View Session History
cat .claude/sessions/active-sessions.json
Clean Old Sessions
Sessions older than 1 hour are automatically cleaned up. To manually clean:
rm .claude/sessions/active-sessions.json
Tips
- Use Plan mode (Shift+Tab twice) for most sessions
- Switch to auto-accept after approving a plan
- Let sessions run in parallel - don't wait for one to finish
- Check notifications to see when sessions need input
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.
- 5d ago First seen · 63 lines · 6 tokens per session scan B dbef31fb0fe5
sessions is a command published in the GitHub repository sumulige/sumulige-claude (2 stars, last pushed 6mo ago), licensed MIT. It adds 6 tokens to every session and 377 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
doctor
Run read-only health checks on the Kobiton automate plugin (CLI, credentials, profile).
speckit.checklist
Generate a custom checklist for the current feature based on user requirements.
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
speckit.plan
Execute the implementation planning workflow using the plan template to generate design artifacts.
handoff
Force a session catchup or a memory promotion outside the hook lifecycle. Default is catchup (read-only); promote is HITL gated.
gate
You are the Gate System controller. Execute quality gate reviews based on the user's request.