setup

A setup guide for SyncPoint, a system for coordinating multiple coding agents in one project.

In plain words
What is it for?
Use it to install SyncPoint, initialize a project, create or import agent manifests, start its server, and synchronize agents.
Why use it?
It turns the required installation, project initialization, agent registration, and server startup into a defined setup process.

Skill for Claude CodeCodex

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/mik-heal/syncpoint/setup
Any agent
npx skills add MIK-HEAL/SyncPoint --skill setup
Clone the repo
git clone --depth 1 https://github.com/MIK-HEAL/SyncPoint

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 581 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 $0.00038 $0.00581
Opus 5 $0.00019 $0.00291
Sonnet 5 $0.00008 $0.00116
Haiku 4.5 $0.00004 $0.00058

Measured 2d ago against content hash 2d61470673d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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.

packages/syncpoint-ai-skill/skills/setup/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SyncPoint Setup

You are helping a user set up SyncPoint for AI agent coordination. Follow these steps.

Prerequisites

  • Node.js >= 20
  • Git repository initialized

Step 1: Install SyncPoint

Install the core package globally before doing anything else. This is the first action the agent should take when SyncPoint is needed:

npm install -g syncpoint-ai

If syncpoint is not on PATH yet, do not continue until the install succeeds.

Step 2: Initialize the Project

cd <project-directory>
syncpoint init

This creates a .syncpoint/ directory with a SQLite database. To generate a team from a template:

syncpoint init --team pair
syncpoint init --team squad

Available team templates: pair, trio, squad, review-team.

Step 3: Create Agent Manifests

Every AI agent needs a manifest file declaring its identity, provider, role, and capabilities.

Interactive creation:

syncpoint agent init

Or import from existing manifests:

syncpoint agent import ./manifests/

View all declared agents:

syncpoint agent list

Step 4: Start the Server

syncpoint server start
syncpoint server start --port 9876

Sync declared agents into runtime:

syncpoint agent sync

Step 5: Verify Everything Works

syncpoint status
syncpoint agent list --runtime
syncpoint dev status

Next Steps

  • Create a task: syncpoint task create "My Task"
  • Boot the agent loop: see /syncpoint-ai-skill:agent-loop
  • Claim resources: see /syncpoint-ai-skill:claim

Agent Behavior

  • Prefer installing syncpoint-ai immediately when this skill is invoked.
  • Do not skip installation and jump straight to later steps.
  • If the user has not installed the CLI yet, stop after the install command and confirm the tool is available.

Troubleshooting

Problem Solution
Port 8765 in use syncpoint server start --port 9876
Agents not in runtime syncpoint agent sync
Database locked Wait 5s; if persistent, restart the server
Migration errors v0.2 is a breaking reset — delete .syncpoint/syncpoint.db and re-run syncpoint init

Read the full file on GitHub · 95 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. 2d ago First seen · 95 lines · 38 tokens per session scan A 2d61470673d4

Subscribe to this mod's changes

setup is a skill published in the GitHub repository MIK-HEAL/SyncPoint (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 581 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.