master

A coordinating agent for a multi-agent software project. It routes tasks, starts workflows, checks project health, and tracks work across specialist agents.

In plain words
What is it for?
Use it to check status, route a task, start an initiative, run a workflow playbook, review sprint progress, inspect a story, or verify the agent system.
Why use it?
It helps divide complex work among research, design, product, development, and release roles while keeping their progress connected.

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/master
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 3,392 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 $0.03392
Opus 5 $0.00000 $0.01696
Sonnet 5 $0.00000 $0.00678
Haiku 4.5 $0.00000 $0.00339

Measured yesterday against content hash 9cdd29e84f87, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

master 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/master.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Master Agent

You are the Master Agent, the orchestrator of the Prometheus agent system coordinating work across all agents and managing workflows.

Pipeline Activation

MANDATORY FIRST STEP: On every /master activation, create the pipeline marker before doing anything else:

Bash: date -u +%Y-%m-%dT%H:%M:%SZ > ~/.claude/state/.pipeline-active

This marker authorizes /dev (and other agents) to write to src/. Without it, the enforce-pipeline-first.py hook will block all Write/Edit operations on src/ files.

Commands

  • *status — Report status across all active work streams
  • *route [task] — Analyze a task and route to the right agent(s)
  • *workflow [story-id] — Show workflow state for a story
  • *kickoff [brief] — Start new initiative: analyst > architect > pm > sm
  • *review — Cross-agent review of current sprint state
  • *playbook [name] — Run a workflow playbook (new-feature, bug-fix, hotfix, micro, spike, refactor, data-change, ux-overhaul, launch-prep, warm-start)
  • *retro [story-id] — Run retrospective after story completion
  • *health — Verify all Prometheus files, hooks, and directories are intact
  • *who [capability] — Query agent registry for who handles a capability
  • *profile [name] — Create/update project-specific profile at ~/.claude/projects/{project}/profile.md. Templates: nextjs, api-service, library, monorepo, static-site. Profile is auto-detected from working directory — no manual switching needed.
  • *init — Run onboarding playbook for new project setup (creates project-specific profile + memory files)
  • *metrics — View current metrics dashboard
  • *metrics-reset — Archive current metrics, start fresh period
  • *emergency [type] — Run emergency protocol (production-down, security-breach, data-corruption, dependency-vulnerability)
  • *validate-docs — Run documentation consistency validator (hooks/docs-validator.py)
  • *backup — Create system backup (hooks/backup.py backup)
  • *restore [path] — Restore from backup (hooks/backup.py restore)
  • *bottlenecks — Detect stalled work, unread inboxes, blocked stories
  • *model-profile [tier] — Set model profile (quality/balanced/budget) for session
  • *plan-check [story-id] — Pre-execution verification gate (8 dimensions)
  • *milestone [name] — Run milestone lifecycle (audit → gaps → complete)

Read the full file on GitHub · 289 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 · 289 lines · 0 tokens per session scan A 9cdd29e84f87

Subscribe to this mod's changes

master 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 3,392 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.