A quick reference for the OMT development workflow, where several agents coordinate planning, design, coding, and review. It lists the available commands and when to use each one.

Use /omt to run a task through the full lifecycle, /init-agents to create the agent workspace, and /git-commit for a direct conventional Git commit.

It gives developers one place to see how to start a task, set up the agent workspace, or intervene manually. It also explains where human approval fits into the workflow.

help — Command by musingfox

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 commands/musingfox/cc-plugins/help

Clone the repo

git clone --depth 1 https://github.com/musingfox/cc-plugins

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,183 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.

Model	Per session	Once invoked
Fable 5	$0.00025	$0.01183
Opus 5	$0.00013	$0.00592
Sonnet 5	$0.00005	$0.00237
Haiku 4.5	$0.00003	$0.00118

Measured yesterday against content hash 257fa625db42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

help 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 yesterday.

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.

omt/commands/help.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OMT (One Man Team) — Quick Reference

Overview

The Agent-First Workflow uses Contract-First design and autonomous execution:

Humans provide a goal and approve consensus
/omt orchestrates the full lifecycle — dispatches all agents, presents consensus, runs execution loop
Contracts validate input/output at every stage

Workflow: /omt → Full Orchestration

/omt "Build feature X"
  → /omt captures goal and validates workspace
  → /omt dispatches @pm (autonomous requirements)
  → /omt dispatches @arch (autonomous architecture)
  → /omt dispatches @hive (consensus analysis)
  → /omt presents consensus summary to human
  → Human approves (single interaction)
  → /omt executes @dev → @reviewer loop per stage
  → Done (or /omt escalates after 3 failures)

Commands (4)

`/omt <goal>`

When: Start a new feature or task Does: Full orchestration — dispatches @pm, @arch, @hive, presents consensus, executes @dev/@reviewer loop

`/init-agents`

When: New project setup Does: Creates .agents/ workspace with .state/ infrastructure

`/git-commit`

When: Emergency manual intervention Does: Direct git commit with conventional commit format

`/help`

When: Need a quick reference Does: Shows this guide

Agents (5)

@hive (Sonnet)

Role: Consensus builder and analysis Trigger: Dispatched by /omt after @pm and @arch complete Does: Reads pm.md and arch.md, verifies contract artifacts, extracts decision points, builds consensus summary and stage execution plan Output: .agents/outputs/hive-consensus.md — consensus analysis Contract: contracts/hive.json

@pm (Haiku)

Role: Requirements management Trigger: Dispatched by /omt (autonomous mode) or manually by user Does: Analyzes project status, defines user stories and acceptance criteria Output: .agents/outputs/pm.md — requirements document Contract: contracts/pm.json

@arch (Sonnet)

Role: Technical architecture design Trigger: Dispatched by /omt (autonomous mode) or manually by user Does: API-First methodology — defines interfaces, types, pseudocode, and architecture Output: .agents/outputs/arch.md — architecture document Contract: contracts/arch.json

Read the full file on GitHub · 134 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.

yesterday First seen · 134 lines · 25 tokens per session scan A 257fa625db42

Subscribe to this mod's changes

help is a command published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 1,183 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.

Code review Git and workflow Planning

help