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.
git clone --depth 1 https://github.com/ShaheerKhawaja/ProductionOSWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/shaheerkhawaja/productionos/max-research)<a href="https://agentmods.dev/commands/shaheerkhawaja/productionos/max-research"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/max-research/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/shaheerkhawaja/productionos/max-research"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/max-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00048 | $0.06003 |
| Opus 5 | $0.00024 | $0.03002 |
| Sonnet 5 | $0.00010 | $0.01201 |
| Haiku 4.5 | $0.00005 | $0.00600 |
Grade A, and why
max-research 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 573 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Max-Research — Nuclear-Scale Simultaneous Research Deployment
You are the Max-Research orchestrator — the most powerful research command in ProductionOS. Unlike /auto-swarm (7 agents per wave) or /deep-research (1-7 agents), you deploy 500-1000 agents in ONE massive simultaneous wave for total topic saturation.
Architecture: ONE wave. ALL agents. Maximum parallelism.
This is not iterative. This is a simultaneous detonation of research intelligence across every facet of a topic at once.
Input
- Topic: $ARGUMENTS.topic
- Agents: $ARGUMENTS.agents (default: 500)
- Domains: $ARGUMENTS.domains (default: 10)
- Depth: $ARGUMENTS.depth (default: ultra)
- Sources: $ARGUMENTS.sources (default: all)
- Skip Warning: $ARGUMENTS.skip_warning (default: false)
PHASE 0: MANDATORY USAGE WARNING
Unless --skip-warning is passed, you MUST display this warning and WAIT for explicit user confirmation before proceeding.
Display this nuclear warhead ASCII art followed by the resource warning:
▄▄██▄▄
▄████████▄
███████████▌
████████████
████████████
▀███████████
▀████████▀
▀██████▀
██████
██████
██████
██████
████████
██████████
████████████
██████████████
████████████████
██░░░░░░░░░░░░░░██
██░░ M A X ░░██
██░░ RESEARCH v5.2 ░██
██░░░░░░░░░░░░░░░░░░░░██
██████████████████████████
████████████████████████████
██████████████████████████████
████████████████████████████████
██░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░██
██░░ {agents} AGENTS ARMED ░░██
██░░ SINGLE WAVE DEPLOYMENT ░░██
██░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░██
████████████████████████████████████████████
██████████████████████████████████████████████
████████████████████████████████████████████████
██████████████████████████████████████████████████
████████████████████████████████████████████████████
██░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░██
██░░ N U C L E A R R E S E A R C H E N G I N E ░██
██░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░██
████████████████████████████████████████████████████████
████████████▀▀▀▀ ▀▀▀▀████████████
████████▀ ▀████████
██████ ▄▄ ▄▄ ██████
████ ██████████ ████
██ ████████████ ██
████████████
██████████
██████
██
╔══════════════════════════════════════════════════════╗
║ MAX-RESEARCH: NUCLEAR OPTION ARMED ║
╠══════════════════════════════════════════════════════╣
║ ║
║ Agents: {agents} deployed in ONE wave ║
║ Domains: {domains} parallel research tracks ║
║ Per domain: {agents/domains} agents each ║
║ Depth: {depth} ║
║ ║
║ ESTIMATED RESOURCE CONSUMPTION: ║
║ ├── Token budget: ~10-15M tokens ║
║ ├── Concurrent calls: {agents} simultaneous agents ║
║ ├── Wall time: ~30-90 minutes ║
║ └── Output size: ~3-8MB of research ║
║ ║
║ ALTERNATIVES (less destructive): ║
║ ├── /deep-research → 1-7 agents, focused ║
║ ├── /auto-swarm → 7-77 agents, wave-based ║
║ └── /max-research → 500-1000, single wave ║
║ ║
║ THIS WILL CONSUME YOUR ENTIRE CONTEXT BUDGET. ║
║ ║
╚══════════════════════════════════════════════════════╝
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.
- 9d ago First seen · 573 lines · 48 tokens per session scan A fb07bdbc3eb9
max-research is a command published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 6,003 once invoked, about $0.0002 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.
Other commands, from other repositories
settings
View or edit fellowship configuration (/.claude/fellowship.json). Run /settings to see current settings, change values, or reset to defaults.
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.
rekindle
Recover a fellowship after a session crash. Scans worktrees and quest state, presents a recovery dashboard, and re-spawns Gandalf with recovered quest context. Use when returning to a crashed or expired fellowship session.
validate-docs
Validate that site and README documentation is current. Report-only — flags issues without modifying anything.
chronicle
One-time codebase onboarding — interactively extracts your team's conventions, identifies reference files, and generates CLAUDE.md sections so Claude codes the way your team does. Run once per project.
scribe
Create a reusable quest template for a specific type of task (e.g., "API endpoint", "migration"). Encodes project-specific rules and conventions into phase guidance that loads automatically during quests.