conclave-build

conclave-build is a skill for Claude Code, Codex from ssube/conclave. It costs 45 tokens per session (2,148 once invoked), scanned B, original, MIT.

A build and testing procedure for the Conclave container, which packages Conclave services and tools into a runnable environment. It covers building the container image, starting it, checking it with browser tests, viewing logs, and managing its credentials.

In plain words
What is it for?
Use it after changing Conclave code or configuration to build the image, run the container, execute tests, inspect logs, print credentials, or clean up the local container workspace.
Why use it?
It provides a repeatable way to verify changes to Conclave services, configuration, scripts, skills, or extensions. It also includes commands for stopping, cleaning, and inspecting the local environment.

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

Made for: Claude Code, Codex.

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 conclave-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/ssube/conclave/conclave-build.svg)](https://agentmods.dev/skills/ssube/conclave/conclave-build)
Your own site
<a href="https://agentmods.dev/skills/ssube/conclave/conclave-build"><img src="https://agentmods.dev/badge/skills/ssube/conclave/conclave-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,148 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00045 $0.02148
Opus 5 $0.00023 $0.01074
Sonnet 5 $0.00009 $0.00430
Haiku 4.5 $0.00005 $0.00215

Measured 3d ago against content hash 95f0b1cc880f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

conclave-build scanned grade B with 1 finding 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

6. Verify specific changes: `sudo nerdctl exec conclave-dev <command>`
pi/skills/conclave-build/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conclave Build

Build and test the Conclave all-in-one container locally using scripts/dev.sh.

Quick Reference

# Full cycle: build image + start container + run tests
bash scripts/dev.sh

# Individual steps
bash scripts/dev.sh build        # build the image only
bash scripts/dev.sh run          # start container (runs tests automatically)
bash scripts/dev.sh test         # run browser tests against running container
bash scripts/dev.sh stop         # stop and remove container
bash scripts/dev.sh clean        # stop container AND delete the workspace volume
bash scripts/dev.sh logs         # tail container logs
bash scripts/dev.sh creds        # print admin and agent passwords

Build Process

The Dockerfile builds in this order:

  1. Base image: nvidia/cuda:12.4.1-runtime-ubuntu22.04
  2. Copy into image: ansible/, configs/, dashboard/, pi/
  3. Run Ansible playbook: installs all services (postgres, nginx, synapse, chromadb, ollama, planka, neko, ttyd, chromium, coding agents)
  4. Copy scripts: scripts/ copied to /opt/conclave/scripts/
  5. Entrypoint: scripts/startup.sh

Container Runtime

All services run under supervisord (configs/supervisord.conf). Key programs:

Priority Service Port
10 postgres, nginx, sshd, cron 5432, 8888, 22, —
14-17 dbus, xvfb, pulseaudio, openbox, chromium 9222 (internal)
30 synapse, chromadb, ollama, ttyd, pushgateway 8008, 8000, 11434, 7681, 9091
40 planka 1337
50 neko 8080, 8081 (TCPMUX)
99 tmux-session, ollama-pull, create-users oneshot

First Boot Flow

startup.sh runs on every container start:

  1. Generate secrets (passwords, tokens) if first boot
  2. Render config templates (nginx, element-web, planka, chromadb, neko)
  3. Write agent-env.sh with credentials for coding agents
  4. Sync pi skills/extensions to /workspace/data/coding/.pi/agent/
  5. Copy default pi-settings.json and cron.tab
  6. Launch supervisord

Read the full file on GitHub · 201 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 · 201 lines · 45 tokens per session scan B 95f0b1cc880f

Subscribe to this mod's changes

conclave-build is a skill published in the GitHub repository ssube/conclave (2 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 2,148 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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

deployment-patterns

Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.

mturac/everything-openai-codex · 41 tokens

docker-patterns

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration. Use when setting up containerized development environments or reviewing Docker configurations.

mturac/everything-openai-codex · 40 tokens

docker

Docker containerization, multi-stage builds, non-root security, layer caching optimization, and docker-compose standards.

kok-o/koko-contextos-agents · 23 tokens

docker-patterns

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

deepelementlab/jupyter-studio · 27 tokens

k8s-security-policies

Comprehensive guide for implementing NetworkPolicy, PodSecurityPolicy, RBAC, and Pod Security Standards in Kubernetes.

Threat-Vector-Security/guardian-agent · 0 tokens

kubernetes-expert

Expert Kubernetes: workloads, services, config, probes, resources, and troubleshooting. Trigger keywords: Kubernetes, k8s, Deployment, StatefulSet, Service, Pod, ConfigMap, Secret, Ingress, liveness, readiness, probe, requests, limits, HPA, kubectl, Helm, CrashLoopBackOff, ImagePullBackOff, OOMKilled. Use for writing…

Miaoge-Ge/coding-agent-skills · 93 tokens