collab-start

collab-start is a skill for Claude Code, Codex from leaf76/session-collab-mcp. It costs 36 tokens per session (702 once invoked), scanned A, original, MIT.

A skill for coordinating multiple coding-agent sessions working on the same project. It uses short shared notes and file claims to reduce conflicts on one machine.

In plain words
What is it for?
Use it before non-trivial shared edits to start or resume a session, claim files, save brief notes, and coordinate work.
Why use it?
It helps agents avoid editing the same files and keeps important in-progress decisions available across sessions.

Skill for Claude CodeCodex

Part of the session-collab plugin — 3 skills, 2 commands, 4 hooks, 1 MCP server shipped together

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 skills/leaf76/session-collab-mcp/collab-start
Any agent
npx skills add leaf76/session-collab-mcp --skill collab-start
Clone the repo
git clone --depth 1 https://github.com/leaf76/session-collab-mcp

Made for: Claude Code, Codex.

Or install session-collab, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 4 hooks, 1 MCP server.

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 collab-start

README.md
[![agentmods](https://agentmods.dev/badge/skills/leaf76/session-collab-mcp/collab-start.svg)](https://agentmods.dev/skills/leaf76/session-collab-mcp/collab-start)
Your own site
<a href="https://agentmods.dev/skills/leaf76/session-collab-mcp/collab-start"><img src="https://agentmods.dev/badge/skills/leaf76/session-collab-mcp/collab-start.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 702 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 $0.00036 $0.00702
Opus 5 $0.00018 $0.00351
Sonnet 5 $0.00007 $0.00140
Haiku 4.5 $0.00004 $0.00070

Measured 3d ago against content hash 012b38267d6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

collab-start 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.

plugin/skills/collab-start/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Collaboration Startup

Prevent file conflicts when multiple agent sessions work on the same machine. Not a remote Git lock. Token-conscious by default.

Roles (do not mix)

Store Use for
session-collab memory Short in-flight notes for this repo/session (finding/decision/state). Over-cap content is rejected.
AI-Memory vault (~/AI-Memory) Durable cross-provider prefs, profile, project decisions

Do not dump transcripts into collab memory.

When to run

Do start when any of:

  • You will edit files in a shared project
  • Multiple agents/sessions may work on the same repo
  • User asks to coordinate, claim files, or resume collab context

Skip entirely for pure Q&A, explanations, planning with no edits, greetings.

Required Actions (when starting)

Step 1: Start (or reuse) Session

Call collab_session_start with:

  • project_root: repo you will edit
  • name: stable descriptive name (enables reuse of same name+project)
  • restore_context: false by default — set true only for prior highlights
  • force_new: true only if you must not reuse

Store session_id. Note reused in the response.

Step 2: Light awareness

From start response only (active_sessions).
If active_sessions > 1 and you need who holds files: collab_session_list without detail first.

Step 3: Claims — prefer atomic create

Before modifying files:

  1. collab_claim action=create with all target files in one call (paths absolute or relative — server normalizes to project_root)
  2. If blocked: do not edit blocked_files; coordinate or wait
  3. action=check is optional probe-only — do not double-trip check→create by default

Batch files. Prefer symbols when sharing a file safely.

Step 4: Memory (optional)

  • Short finding/decision only
  • Skip for trivial sessions

Step 5: Config (optional)

collab_config only if non-default mode needed (strict / smart / bypass).

Read the full file on GitHub · 85 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. 3d ago First seen · 85 lines · 36 tokens per session scan A 012b38267d6a

Subscribe to this mod's changes

collab-start is a skill published in the GitHub repository leaf76/session-collab-mcp (2 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 702 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

aba-precision-protocol

FOUNDATIONAL BEHAVIORAL PROTOCOL — ABA-based precision execution rules. Every prompt processed must follow these rules. Mistakes caught late create intermittent reinforcement of wrong patterns. Stop-fix-verify before proceeding.

dcostenco/prism-coder · 48 tokens

notebooklm

This skill should be used when the user wants to query their Google NotebookLM notebooks for citation-backed, source-grounded answers, or manage notebooks, sources, and Studio content (audio, report, video, infographic, presentation, data table, flashcards, quiz, mind map). It drives the @roomi-fields/notebooklm-mcp…

roomi-fields/notebooklm-mcp · 118 tokens

frontmcp-guides

Tutorials, end-to-end walkthroughs, and complete reference projects for FrontMCP. Use when you want a getting-started guide, a full worked example, or to learn best practices by following a step-by-step build rather than a single API reference. Includes a beginner weather-API server (tool plus static resource, Zod…

agentfront/frontmcp · 157 tokens

review-agents-md

Reviews an AGENTS.md or CLAUDE.md file against best practices and reports concrete fixes. Use when the user asks to review, audit, lint, or improve an AGENTS.md / CLAUDE.md / context file, or says "review my agents file".

dominik1001/caldav-mcp · 59 tokens

frontmcp-observability

Use when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server. Covers zero-config OpenTelemetry distributed tracing across all flows; the this.telemetry API for custom spans, events, and attributes in tools, plugins, agents, and skills; structured JSON logging with trace correlation and…

agentfront/frontmcp · 177 tokens

frontmcp-auth-ui

Use when customizing, branding, or replacing the built-in FrontMCP OAuth pages (the login, consent, federated-select, incremental-authorization, and error pages) with your own React components. Covers the auth.ui slot-to-file map and auth.extras name-to-handler map on the auth config (no decorator, no class); the…

agentfront/frontmcp · 184 tokens