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 instructions/leaf76/session-collab-mcp/claude-mdgit clone --depth 1 https://github.com/leaf76/session-collab-mcpWrote 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/instructions/leaf76/session-collab-mcp/claude-md)<a href="https://agentmods.dev/instructions/leaf76/session-collab-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/leaf76/session-collab-mcp/claude-md.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 | $0.00648 | $0.00648 |
| Opus 5 | $0.00324 | $0.00324 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
session-collab-mcp CLAUDE.md 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 3d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Collab MCP
AI Context Persistence & Multi-Session Collaboration for Claude Code.
What It Does
- Persist important context across conversations (
collab_memory_save,collab_memory_recall) - Coordinate parallel sessions by claiming files and detecting conflicts (
collab_claim) - Protect critical files from accidental changes (
collab_protect) - Provide a quick status snapshot for the current session (
collab_status)
Installation
Option 1: Claude Code Plugin (Recommended)
# Add marketplace
/plugin marketplace add leaf76/session-collab-mcp
# Install plugin
/plugin install session-collab@session-collab-plugins
Option 2: MCP Server Only
Add to ~/.claude.json:
{
"mcpServers": {
"session-collab": {
"command": "npx",
"args": ["-y", "session-collab-mcp@latest"]
}
}
}
Quick Start
# Only for non-trivial / multi-session work — skip pure Q&A
1. collab_session_start # reuses name+project; restore_context default false
2. collab_claim create # atomic; batch files (check optional)
3. collab_memory_save # short notes only, capped (optional)
4. collab_session_end
Token defaults: list/status/claim happy-path compact unless detail=true.
Collab memory ≠ AI-Memory vault (durable prefs live in the vault).
Core Tools (10)
| Tool | Purpose |
|---|---|
collab_session_start |
Register session |
collab_session_end |
End session |
collab_memory_save |
Save important context |
collab_memory_recall |
Retrieve saved context |
collab_memory_clear |
Clear memories |
collab_claim |
Create/check/release/list claims |
collab_protect |
Register/check/list protected files |
collab_session_list |
List active sessions |
collab_config |
Configure session behavior |
collab_status |
Get session status summary |
Memory Categories
| Category | Use For |
|---|---|
finding |
Discovered facts, root causes |
decision |
Architectural choices |
state |
Current tracking info |
todo |
Action items |
important |
Critical context |
context |
General background |
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.
- 3d ago First seen · 97 lines · 648 tokens per session scan A c95d135affe2
session-collab-mcp CLAUDE.md is an instructions file published in the GitHub repository leaf76/session-collab-mcp (2 stars, last pushed 4d ago), licensed MIT. It adds 648 tokens to every session, about $0.0032 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 instructions, from other repositories
agent-tasks CLAUDE.md
Instructions for keshrath/agent-tasks, covering agent-tasks, architecture, ui / dashboard, code style and versioning.
clink-mcp-server CLAUDE.md
Instructions for Voxos-ai-Inc/clink-mcp-server, covering clink mcp server - development guide, source location, publishing to github, first-time setup (already done) and add the github remote.
clink-mcp-server-python CLAUDE.md
Claude Code instructions for Voxos-ai-Inc/clink-mcp-server-python, covering clink mcp server (python) - development guide, source location, publishing to github, first-time setup and add the github remote.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.