help

A reference command that displays the Prometheus agent system’s complete list of commands, agents, workflows, and setup instructions. Prometheus is the named multi-agent system described in the reference.

In plain words
What is it for?
Use it when you need the system’s command cheat sheet, startup instructions, agent roles, workflow names, or health-check commands.
Why use it?
It gives users one place to find available commands and understand how the agents and workflows are organized.

Command

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/igoroliveirg/prometheus/help
Clone the repo
git clone --depth 1 https://github.com/igoroliveirg/prometheus
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 4,516 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 $0.04516
Opus 5 $0.00000 $0.02258
Sonnet 5 $0.00000 $0.00903
Haiku 4.5 $0.00000 $0.00452

Measured yesterday against content hash bf9887121593, 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.

src/commands/help.md · 495 lines

How it starts

The opening of the file, as written. The whole thing — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prometheus Agent System -- Quick Reference

You are the help system. When activated, display the complete cheat sheet below exactly as written. Do not summarize, truncate, or omit any section. Present the full reference to the user.


Prometheus Agent Orchestration System -- Quick Reference Cheat Sheet


Getting Started

/master *init              Start new project (onboarding wizard)
/master *profile [type]    Set project type (nextjs, api-service, library, monorepo, static-site)
/master *health            Verify system integrity

Agent Activation

Command          Agent                  Domain
-------          -----                  ------
/master          Master (Orchestrator)  Cross-agent coordination, workflow management
/analyst         Analyst                Research, market analysis, project briefs
/architect       Architect              System design, tech stack, architecture docs
/pm              PM                     PRDs, epics, product strategy
/sm              Scrum Master           Story creation, refinement, context bridging
/po              Product Owner          Story validation, backlog, acceptance
/dev             Developer              Code implementation (story-bound)
/qa              QA                     Testing, code review, quality gates
/devops          DevOps                 EXCLUSIVE push/PR authority, CI/CD, deploy
/data-engineer   Data Engineer          Database schemas, migrations, RLS, queries
/ux              UX                     User flows, wireframes, design system, a11y
/squad           Squad                  Custom team formation for domains
/loop            Loop                   Context continuity, state persistence, memory
/help            Help                   This cheat sheet

Master Commands (/master)

*status                    System-wide status across all work streams
*route [task]              Analyze a task and recommend the right agent(s)
*kickoff [brief]           Start new initiative: analyst -> architect -> pm -> sm
*workflow [story-id]       Show workflow state for a story
*review                    Cross-agent review of current sprint
*playbook [name]           Run a workflow playbook (see Playbooks below)
*retro [story-id]          Post-story retrospective
*health [--full] [--strict] System health check (fast by default, --full for all 20 categories)
*who [capability]          Query agent registry for capabilities
*profile [name]            Activate an environment profile
*init                      Run onboarding playbook for new projects
*metrics                   View current metrics dashboard
*metrics-reset             Archive current metrics, start fresh period
*emergency [type]          Run emergency protocol (see Emergencies below)
*validate-docs             Run documentation consistency validator
*backup                    Create system backup
*restore [path]            Restore from a backup
*model-profile [tier]      Set model profile (quality/balanced/budget) for session
*plan-check [story-id]     Pre-execution gate (8-dimension verification)
*milestone [name]           Run milestone lifecycle (audit -> gaps -> complete)
*health --repair           Auto-fix repairable system integrity issues
*playbook [name] --auto-advance   Chain pipeline steps without confirmation prompts

Read the full file on GitHub · 495 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. yesterday First seen · 495 lines · 0 tokens per session scan A bf9887121593

Subscribe to this mod's changes

help is a command published in the GitHub repository igoroliveirg/prometheus (3 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,516 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 2026-08-31.