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.
npx agentmods add commands/igoroliveirg/prometheus/helpgit clone --depth 1 https://github.com/igoroliveirg/prometheusWhat 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 | $0.00000 | $0.04516 |
| Opus 5 | $0.00000 | $0.02258 |
| Sonnet 5 | $0.00000 | $0.00903 |
| Haiku 4.5 | $0.00000 | $0.00452 |
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.
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
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 · 495 lines · 0 tokens per session scan A bf9887121593
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.