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/productionos-help)<a href="https://agentmods.dev/commands/shaheerkhawaja/productionos/productionos-help"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/productionos-help/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/productionos-help"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/productionos-help.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 | $0.00026 | $0.01685 |
| Opus 5.5 | $0.00010 | $0.00674 |
| Sonnet 5.5 | $0.00005 | $0.00337 |
| Haiku 4.5 | $0.00003 | $0.00169 |
Grade A, and why
productionos-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 1mo 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProductionOS — Usage Guide
Getting Started
ProductionOS v1.0.0-beta.1 is your AI engineering team — 80 agents, 41 commands, 17 hooks, 6 CLI tools, and dual Claude/Codex targets. Here's how to use it effectively.
What's New in v1.0
- Always-present hooks — Security scan on auth/payment files, telemetry on every edit, review hints after 10+ changes, session handoff on exit
- CLI tools —
pos-init,pos-config,pos-analytics,pos-update-check - Auto-activating skills — Skills trigger based on file patterns (auth → security-scan, .tsx → frontend-audit)
- Continuous learning — Extracts patterns from sessions, builds instincts with confidence scoring
/frontend-upgrade— CEO vision + parallel swarm for frontend transformation
Step 0: Preamble
All ProductionOS commands run the shared preamble (templates/PREAMBLE.md) before execution. This includes environment check, prior work discovery, agent resolution, cost estimation, and prompt injection defense.
Quick Reference
COMMAND WHEN TO USE
/production-upgrade Audit and improve any codebase (start here)
/omni-plan Full 13-step pipeline for major work
/omni-plan-nth Recursive perfection — loops until 10/10
/auto-swarm "task" Throw agents at any task in parallel
/auto-swarm-nth "task" Recursive swarm until 100% coverage
/max-research "topic" 500-1000 agents — exhaustive research (nuclear)
/deep-research "topic" Research anything before building
/agentic-eval Evaluate quality with CLEAR framework
/security-audit 7-domain security deep-dive
/context-engineer Build token-optimized context packages
/logic-mode "idea" Validate a business idea
/learn-mode "topic" Interactive code tutor
/productionos-pause Save pipeline state for later
/productionos-resume Resume from checkpoint
/productionos-update Update to latest version
/frontend-upgrade CEO-enriched frontend transformation
/productionos-help This guide
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.
- 1mo ago First seen · 164 lines · 26 tokens per session scan A 7e52a449c9a7
productionos-help is a command published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 6mo ago), licensed MIT. It adds 26 tokens to every session and 1,685 once invoked, about $0.0001 per session on Opus 5.5. 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
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.
settings
View or edit fellowship configuration (/.claude/fellowship.json). Run /settings to see current settings, change values, or reset to defaults.
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.
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.
red-book
Use after receiving PR review feedback. Extracts conventions from reviewer comments and offers to add them to CLAUDE.md. Closes the convention learning loop.