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/leaf76/session-collab-mcp/statusgit clone --depth 1 https://github.com/leaf76/session-collab-mcpWhat 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 | $0.00015 | $0.00463 |
| Opus 5 | $0.00008 | $0.00231 |
| Sonnet 5 | $0.00003 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
status 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 2d 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.
What it actually says
Session Collaboration Status
Display the current state of session collaboration.
Actions
1. List Active Sessions
Call mcp__session-collab__collab_session_list with:
project_root: Current working directoryinclude_inactive: falsedetail: false by default (counts only). Usetrueonly when you need full claims/coordination.
2. List Current Session Claims
If you know the current session ID and need file-level detail, call mcp__session-collab__collab_claim with:
action:"list"session_id: Current session ID
3. Load Session Summary
If you know the current session ID, call mcp__session-collab__collab_status with:
session_id: Current session IDdetail: false by default;truefor full claim/coordination payloads
Output Format
Provide a clear status report:
Session Collaboration Status
Your Session
| Item | Value |
|---|---|
| Session ID | xxx or "Not started" |
| Session Name | xxx |
| Status | Active / Not initialized |
Active Sessions (N total)
| Session | Name | Last Active |
|---|---|---|
id-1 |
name-1 | X min ago |
id-2 |
name-2 | Y min ago |
Active Claims (for current session, if available)
| File/Symbol | Session | Intent | Scope |
|---|---|---|---|
src/file.ts |
session-1 | "description" | medium |
Session Summary (if available)
- Active claims count
- Restored memories or current context
- Other active sessions in the same project
Quick Actions
- Start session: Call
collab_session_start - Check file: Call
collab_claimwithaction="check" - Claim file: Call
collab_claimwithaction="create" - End session: Call
collab_session_end
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.
- 2d ago First seen · 64 lines · 15 tokens per session scan A b566b2338c25
status is a command published in the GitHub repository leaf76/session-collab-mcp (2 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 463 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.
Other commands, from other repositories
global-shortcuts
Global shortcuts do not use the renderer command registry. Electron main registers them with globalShortcut.register, so they can run while the app is unfocused.
octospec-plan
Draft an octospec task brief (goal / load-bearing list / out-of-scope / acceptance).
octospec-check
You are running the octospec Verify phase for task $ARGUMENTS.
join
Join a shared backchannel room from a link.
comm
Relay a human-typed message straight onto the active claude-comms net.
doctor
Check backchannel setup (Node, relay, command-sandbox grants) and print any fixes.