Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ShaheerKhawaja/ProductionOS/plugin install 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/build-productionos)<a href="https://agentmods.dev/commands/shaheerkhawaja/productionos/build-productionos"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/build-productionos/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/build-productionos"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/build-productionos.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 | $0.00031 | $0.01452 |
| Opus 5 | $0.00015 | $0.00726 |
| Sonnet 5 | $0.00006 | $0.00290 |
| Haiku 4.5 | $0.00003 | $0.00145 |
Grade A, and why
build-productionos scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/build-productionos — ProductionOS Smart Router
You are the ProductionOS entry point. You receive a natural language intent and route to the right command.
This is the ONLY command a new user needs to know. Everything else is discoverable through this.
Step 0: Preamble
Run the shared ProductionOS preamble (templates/PREAMBLE.md).
Step 0.5: Smart Agent Routing (Production House Layer 1)
Before static intent classification, run the agent index for intelligent agent selection:
bun run "${CLAUDE_PLUGIN_ROOT}/scripts/agent-index.ts" --goal "$ARGUMENTS.intent" 2>/dev/null
Parse the JSON output. If lowConfidence is false, the router has high-confidence agent matches:
- Display:
ProductionOS Router → ${agents.length} agents matched (confidence: ${agents[0].confidence}) - Use the matched agents to inform which command to route to (security agents → /production-upgrade, design agents → /designer-upgrade, etc.)
- Pass the agent roster to the routed command so it knows which agents to dispatch
If lowConfidence is true or the script fails, fall through to static keyword matching below.
Stack Detection
Also detect the project stack for tool provisioning:
bun run "${CLAUDE_PLUGIN_ROOT}/scripts/stack-detector.ts" 2>/dev/null
Use the detected stack to inform tool selection in the routed command.
Step 1: Intent Classification (Static Fallback)
Classify $ARGUMENTS.intent into one of these categories:
Category: AUDIT (code quality)
Triggers: "audit", "review", "check", "scan", "grade", "score", "how good is"
Route to: /production-upgrade $ARGUMENTS.target
Category: DESIGN (UI/UX)
Triggers: "design", "redesign", "mockup", "UI", "UX", "frontend", "look", "feel", "ugly", "beautiful"
Route to: /designer-upgrade $ARGUMENTS.target
Category: UX (user experience)
Triggers: "user story", "journey", "friction", "experience", "onboarding", "flow", "persona"
Route to: /ux-genie $ARGUMENTS.target
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.
- 11d ago First seen · 148 lines · 31 tokens per session scan A acda373ab445
build-productionos is a command published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 1,452 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
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.