index

A directory and guide for FlowDeck's 12-agent coding team, where an orchestrator assigns work to specialist agents. An orchestrator coordinates the work rather than implementing tasks itself.

In plain words
What is it for?
Use it to understand available agents, their modes, responsibilities, and how the orchestrator delegates planning, research, architecture, and implementation work.
Why use it?
It makes the agent roles and selection process clear, so each task can be routed to the appropriate specialist.

Agent

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 agents/dvnghiem/flowdeck/index
Clone the repo
git clone --depth 1 https://github.com/DVNghiem/FlowDeck
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 566 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 $0.00000 $0.00566
Opus 5 $0.00000 $0.00283
Sonnet 5 $0.00000 $0.00113
Haiku 4.5 $0.00000 $0.00057

Measured 2d ago against content hash cf4219cf1be2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

index 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.

docs/agents/index.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents

FlowDeck runs a 12-agent system coordinated by an orchestrator. All agent configurations live in src/agents/. Agent definitions use YAML frontmatter (description, mode, model, temperature). The orchestrator selects specialists based on context and delegates work through the OpenCode SDK delegate tool.

Agent Modes

  • primary — visible and selectable from the user interface
  • subagent — internal only, invoked programmatically by other agents

The orchestrator is the only primary agent. All others are subagents.

Agent Roster

@orchestrator (primary)

AI coding orchestrator that coordinates specialist agents. Routes all work to appropriate agents and workflows. Does not execute tasks directly.

@planner

Creates detailed, step-by-step implementation plans. Use PROACTIVELY for any feature that spans multiple files, requires architectural decisions, or needs phased delivery.

@architect

Designs system architecture, creates ADRs, and defines API contracts. Use PROACTIVELY when planning new modules, API changes, database schema changes, or cross-cutting concerns.

@researcher

Researches documentation, APIs, and best practices. Searches Context7, vendor docs, and package registries. Use when implementation requires understanding an unfamiliar API or library.

@mapper

Maps existing code. Explores unfamiliar areas read-only (structure, call paths, conventions) and documents the codebase into ~/.fd-plan/<slug>/.codebase/ files. Produces factual analysis only — no speculation.

@backend-coder

Implements backend features and fixes based on confirmed plans. Follows existing code patterns and project conventions.

@frontend-coder

Implements frontend features and fixes based on confirmed plans. Follows existing code patterns and project conventions.

@devops

Implements DevOps and infrastructure changes based on confirmed plans. Follows existing repo conventions and operational safety practices.

@tester

Writes and runs tests following TDD principles. Use when implementing new features, fixing bugs, or when test coverage is needed.

Read the full file on GitHub · 61 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 · 61 lines · 0 tokens per session scan A cf4219cf1be2

Subscribe to this mod's changes

index is an agent published in the GitHub repository DVNghiem/FlowDeck (24 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 566 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

build-agent-empty-input-diagnosis

Status: Resolved for interview injections. Date: 2026-08-10 Related PR: #818 (fix/preset-tui-slash-command) — same root class as the original /preset fix. Suspected sibling bug reported by user: During superpowers / brainstorm skill conversations, when the orchestrator asks for confirmation or work is interrupted…

alvinunreal/oh-my-opencode-slim · 0 tokens

codemap

Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…

alvinunreal/oh-my-opencode-slim · 0 tokens

issue-tracker

Issues and PRs for this repo live as GitHub issues. Use the gh CLI for all operations. The project repo is alvinunreal/oh-my-opencode-slim.

alvinunreal/oh-my-opencode-slim · 0 tokens

triage-labels

Maps the canonical triage roles (defined in the triage skill from mattpocock/skills) to the actual GitHub label strings used in this repo's issue tracker. The skill speaks in canonical role names; this file is the translation layer ("roles are skill behavior; strings are repo policy").

alvinunreal/oh-my-opencode-slim · 0 tokens

domain

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

alvinunreal/oh-my-opencode-slim · 0 tokens

lead-eng

Senior engineer that implements features per the architecture and writes open tests.

DUBSOpenHub/dark-factory · 16 tokens