By formantio
Operate Formant organizations and robot fleets from Claude Cowork using the formant CLI with safe admin workflows.
This skill should be used when users ask to administer Formant organizations and fleets using natural language — operational queries, diagnostics, fleet management, user/team/role admin, telemetry and analytics, command dispatch, event and signal inspection, and general CLI tasks. Route persona chat sessions to formant-persona-chat, config mutations to formant-config-lifecycle, historical telemetry view design to formant-view-configuration, teleop view design to formant-teleop-view-configuration, event automation design to formant-event-automation, realtime connection design to formant-realtime-connection-design, task summary analytics to formant-task-summary-analytics, and stream tuning to formant-stream-tuning.
This skill should be used when users ask to change Formant configurations (device config, config templates, views, teleop views, or module configurations). Provides snapshot/edit/apply workflows with rollback-safe artifact capture, schema-aware editing, and deterministic lifecycle management.
This skill should be used when users ask to design, assess, or tune Formant event automation (event triggers and event trigger groups), including trigger semantics, scope filters, severity/message policy, notification/command/workflow actions, and alert-noise reduction. Use formant-administrator to execute CLI operations.
This skill should be used when users want to chat with a specific Formant persona via Theopolis, including persona selection, thread start/reuse, synchronous or asynchronous message turns, polling, history review, and multi-turn continuity on the same thread. Use formant-administrator for non-chat operations.
This skill should be used when users ask to design, assess, or tune Formant real-time connection behavior for teleoperation and live streams, including telemetry-vs-realtime stream roles, stream wiring, media settings, low-bandwidth behavior, and runtime validation.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Skills and commands for managing Formant robot fleets from AI coding agents.
If you are an AI coding agent, follow exactly one install path based on runtime.
# Add the plugin marketplace
/plugin marketplace add FormantIO/formant-agent-plugins
# Install the formant-admin plugin
/plugin install formant-admin@formantio-formant-agent-plugins
Policy:
set -euo pipefail
REPO="$HOME/src/formant-admin/formant-agent-plugins"
DEST="$HOME/.codex/skills"
if [ ! -d "$REPO/.git" ]; then
git clone https://github.com/FormantIO/formant-agent-plugins.git "$REPO"
fi
git -C "$REPO" pull --ff-only
if [ -d "$REPO/plugins/formant-admin/skills" ]; then
SRC="$REPO/plugins/formant-admin/skills"
else
SRC="$REPO/.agents/skills"
fi
mkdir -p "$DEST"
for skill in "$SRC"/formant-*; do
name="$(basename "$skill")"
rm -rf "$DEST/$name"
ln -s "$skill" "$DEST/$name"
done
Validation (required):
git -C "$REPO" status -sb
ls -ld "$HOME/.codex/skills"/formant-*
Policy:
formant-* skills into agent skill directories.git pull --ff-only before relinking.Install the Formant CLI and authenticate:
npm install -g @formant/formant-cli
formant auth login --user "<service-account-email>" --password "<password>"
| Skill | Description |
|---|---|
formant-administrator | Full-coverage CLI administration for operations, diagnostics, and fleet management |
formant-persona-chat | Persona-first Theopolis chat workflows with thread continuity, sync/async turns, polling, and history |
formant-config-lifecycle | Rollback-safe configuration mutations with schema-aware editing |
formant-view-configuration | Historical telemetry view (coherence style) design defaults and audit heuristics; suggestions only, not hard rules |
formant-teleop-view-configuration | Teleop view design defaults for camera/control composition and action wiring; suggestions only, not hard rules |
formant-event-automation | Event trigger and trigger-group design defaults for condition semantics, action routing, and alert-noise reduction |
formant-realtime-connection-design | Realtime stream architecture defaults for teleop/observe wiring, media tuning, and live validation |
formant-task-summary-analytics | Task-summary KPI and SQL defaults for reporting quality checks and analysis workflows |
formant-stream-tuning | Telemetry and video stream tuning defaults for rate, bandwidth, and usability tradeoffs |
| Command | Description |
|---|---|
/check | Validate CLI availability, authentication, and org access |
MIT — see LICENSE.
npx claudepluginhub formantio/formant-agent-plugins --plugin formant-adminGenesis (Forerunner) - AI-Powered Executive Director Automation Platform. Analyze organizational responsibilities, score automation potential with 6-factor algorithm, generate LangGraph workflows, and deploy 11 specialized agents for trade associations and nonprofits.
Production ADK orchestrator for A2A protocol and multi-agent coordination on Vertex AI
Agent dashboard TUI — tracks AI agent state via hooks for the fleet CLI
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).