conclave-launch

A deployment script for launching a Conclave workspace on Runpod, a service that provides cloud GPU computers. The workspace can include services such as Matrix, Planka, Ollama, a browser, and coding agents.

In plain words
What is it for?
Starting a new Runpod pod, choosing its GPU and storage size, supplying the container image, setting service credentials and hostnames, and optionally adding SSH keys.
Why use it?
It automates creating a configured GPU workspace instead of requiring each service and setting to be started manually.

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/ssube/conclave/conclave-launch
Any agent
npx skills add ssube/conclave --skill conclave-launch
Clone the repo
git clone --depth 1 https://github.com/ssube/conclave

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 541 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 $0.00046 $0.00541
Opus 5 $0.00023 $0.00270
Sonnet 5 $0.00009 $0.00108
Haiku 4.5 $0.00005 $0.00054

Measured 2d ago against content hash fcc72e1d5a21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conclave-launch 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.

pi/skills/conclave-launch/SKILL.md · 60 lines

What it actually says

Launch Conclave on Runpod

Deploy a Conclave workspace pod on Runpod using the GraphQL API.

Prerequisites

  • RUNPOD_API_KEY environment variable set
  • Conclave Docker image pushed to a registry

Usage

# Basic launch with defaults (A100 80GB, 500GB volume)
bash /opt/conclave/scripts/launch-runpod.sh \
  --env NGINX_PASSWORD=your-password \
  --env MATRIX_SERVER_NAME=conclave.local \
  --env EXTERNAL_HOSTNAME=pod-id-8888.proxy.runpod.net

# Custom GPU and image
bash /opt/conclave/scripts/launch-runpod.sh \
  --gpu a6000 \
  --image your-registry/conclave:latest \
  --volume-size 1000 \
  --env NGINX_PASSWORD=your-password \
  --env ANTHROPIC_API_KEY=sk-ant-...

# With SSH keys
bash /opt/conclave/scripts/launch-runpod.sh \
  --env NGINX_PASSWORD=your-password \
  --env SSH_AUTHORIZED_KEYS="ssh-ed25519 AAAA..."

Required Environment Variables

Pass via --env flags:

  • NGINX_PASSWORD (required) — basic auth password for dashboard/ollama/chromadb-admin
  • MATRIX_SERVER_NAME — Matrix server domain (default: conclave.local)
  • EXTERNAL_HOSTNAME — Pod external hostname for config templates

Optional Environment Variables

  • ANTHROPIC_API_KEY — for Claude Code and pi
  • OPENAI_API_KEY — for pi (OpenAI provider)
  • SSH_AUTHORIZED_KEYS — SSH public keys (newline-separated)
  • DEFAULT_OLLAMA_MODEL — model to pre-pull (default: qwen3-coder:30b-a3b-q8_0)

After Launch

  1. The script prints the dashboard URL and SSH connection string
  2. Access the dashboard at https://{pod-id}-8888.proxy.runpod.net/
  3. Follow the quick-start guide on the dashboard
  4. Always ask the user if they want you to launch the SSH tunnel for the Neko browser, this will help them out a lot if they want to use the interactive browser in the Conclave workspace
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 · 60 lines · 46 tokens per session scan A fcc72e1d5a21

Subscribe to this mod's changes

conclave-launch is a skill published in the GitHub repository ssube/conclave (2 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 541 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

agents-sdk

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks.

bobbyjohnstx/tinycode · 59 tokens

mempalace-task

Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.

MemPalace/mempalace · 67 tokens

tool-prompt-optimization

Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…

can1357/oh-my-pi · 0 tokens

semantic-compression

Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…

can1357/oh-my-pi · 77 tokens

hosted-agents

This skill should be used when designing hosted or background agent infrastructure: sandboxed execution, remote coding environments, warm pools, session persistence, multiplayer collaboration, self-spawning agents, or Modal-style sandboxes.

muratcankoylan/Agent-Skills-for-Context-Engineering · 46 tokens

kagent-dev

Development guide for kagent's v1alpha3 Harness and AgentTemplate CRDs, AgentInstance gRPC control plane, upstream A2A integration, Substrate runtime provisioning, tests, generation, and PR workflow. Use for any implementation, debugging, review, or CI task in the kagent repository.

kagent-dev/kagent · 65 tokens