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.
git clone --depth 1 https://github.com/alona-iaig/overboard-claude-pluginWrote 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/alona-iaig/overboard-claude-plugin/setup)<a href="https://agentmods.dev/commands/alona-iaig/overboard-claude-plugin/setup"><img src="https://agentmods.dev/badge/commands/alona-iaig/overboard-claude-plugin/setup.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 5.1 | $0.00014 | $0.00509 |
| Opus 5 | $0.00007 | $0.00254 |
| Sonnet 5 | $0.00003 | $0.00102 |
| Haiku 4.5 | $0.00001 | $0.00051 |
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 7d 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
Overboard Studio MCP Setup
Help the user connect their Overboard Studio account to Claude Code via MCP.
Step 1: Check if MCP is already configured
Read the user's MCP config file. On macOS/Linux check ~/.claude/claude_mcp_config.json. Look for an "overboard" entry.
If already configured, tell the user:
Overboard MCP is already configured! Try
/overboard brainstormto create your first board.
Step 2: If not configured, set it up
The Overboard MCP server runs in two modes:
Option A: Remote (Recommended — no setup needed)
Add to ~/.claude/claude_mcp_config.json:
{
"mcpServers": {
"overboard": {
"type": "url",
"url": "https://api.overboard.studio/mcp"
}
}
}
This uses OAuth — the user will be prompted to log in when first using an Overboard command.
Option B: Local (for development)
Requires SUPABASE_URL and SUPABASE_SERVICE_ROLE_KEY:
{
"mcpServers": {
"overboard": {
"command": "node",
"args": ["/path/to/packages/mcp-server/dist/index.js"],
"env": {
"SUPABASE_URL": "https://your-project.supabase.co",
"SUPABASE_SERVICE_ROLE_KEY": "your-service-role-key"
}
}
}
}
Step 3: Merge with existing config
Read the existing config file. If it exists, merge the "overboard" entry into the existing "mcpServers" object. Don't overwrite other MCP servers.
If the file doesn't exist, create it with just the overboard entry.
Step 4: Verify
Tell the user:
MCP configured! Restart Claude Code, then try:
/overboard brainstorm Ideas for Q3 roadmap/overboard plan Mobile app launch/overboard diagram User authentication flowYour boards will appear at https://overboard.studio/boards Sign up free at https://overboard.studio/register if you don't have an account yet.
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.
- 7d ago First seen · 68 lines · 14 tokens per session scan A 56387b0aec04
setup is a command published in the GitHub repository alona-iaig/overboard-claude-plugin (1 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 509 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
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
api-contract-review
Review an API contract (endpoints, request/response shapes, error codes, auth model) BEFORE implementation for naming consistency, versioning, pagination, idempotency, and alignment with existing endpoints. Distinct from review-hard (post-implementation risk) and repo-consistency-sweep (pattern matching on written…
standup
Deprecated alias for /turnstile:pickup -- will be removed in the next release.
silver-migrate
Silver Bullet silver-migrate workflow.
import-dependabot.zh-CN
A security-workflow command that imports a Dependabot alert and creates a task to address it. Dependabot is a tool that reports known security problems in project dependencies.