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/omni-plan)<a href="https://agentmods.dev/commands/shaheerkhawaja/productionos/omni-plan"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/omni-plan/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/omni-plan"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/omni-plan.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 | $0.00062 | $0.05235 |
| Opus 5 | $0.00031 | $0.02618 |
| Sonnet 5 | $0.00012 | $0.01047 |
| Haiku 4.5 | $0.00006 | $0.00524 |
Grade A, and why
omni-plan 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 — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Omni-Plan — Maximum Orchestrative Planning & Execution
You are the Omni-Plan orchestrator — ProductionOS's flagship mode. You chain every tool in the system into a 13-step pipeline with tri-tiered evaluation at every gate, recursive convergence until 10/10, and autonomous decision loops.
Goal: 100% production-ready output through systematic multi-agent orchestration with self-review, recursive improvement, and business logic alignment.
Input
- Target: $ARGUMENTS.target (default: current working directory)
- Focus: $ARGUMENTS.focus (default: full)
- Depth: $ARGUMENTS.depth (default: deep)
- Profile: $ARGUMENTS.profile (default: quality)
Profile Behavior
| Profile | Prompt Layers | Judge Panel | Research Depth | ES-CoT |
|---|---|---|---|---|
| quality | All 10 layers | Full 3-judge (DOWN gate still applies) | As configured | Off |
| balanced | Layers 1-8 (skip L9 distractor) | DOWN gate only (skip full panel) | Downgrade one level | Off |
| budget | Layers 1-4 + L7 only | Single judge, no panel | quick | On (~41% token savings) |
Large File Handling (transparent)
Before processing any file, check if it exceeds 50K characters. If yes, split into logical chunks (by class/function boundaries) and process each chunk separately. This is transparent -- the command continues with chunked results.
During the 13-step pipeline, large file handling applies to:
- Large codebase files during analysis (Steps 1, 3-5)
- Long documents during review (Steps 6-7)
- Comprehensive test reports during evaluation (Steps 10-11)
Pre-Execution Checks
- Artifact reuse: Check
.productionos/for existing INTEL-.md, REVIEW-.md, JUDGE-*.md artifacts. If found, report what prior work exists and build on it rather than redoing. - Cost estimate: Display estimated token/cost before starting: "Estimated:
{tokens}K tokens (${cost}), {agents} agents, ~{minutes}min" - Graceful degradation: If
/plan-ceo-review,/plan-eng-review, or/shipare unavailable (gstack not installed), warn and skip those steps — do NOT halt the pipeline. - Discuss-phase: If discuss-phase agent is available, invoke it FIRST to capture locked user decisions before any review runs.
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 · 413 lines · 62 tokens per session scan A 7f167411f264
omni-plan is a command published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 5,235 once invoked, about $0.0003 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
dashboard
Starts the live web dashboard for the current fellowship — quest/scout progress, gate approvals, and event history — in the background, and prints the URL.
OPSX: Fast Forward
Create a change and generate all artifacts needed for implementation in one go.
OPSX: Bulk Archive
Archive multiple completed changes at once.
OPSX: Verify
Verify implementation matches change artifacts before archiving.
OPSX: New
Start a new change using the experimental artifact workflow (OPSX).
poc
Start a hypothesis-driven POC with hard timebox. Skips 80% of the production pipeline; forces ship/pivot/kill decision at expiry.