Borrowing it
Nothing to install: this file belongs to oh-my-engine/oh-my-engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/oh-my-engine/oh-my-engine/main/.claude/commands/ome-plan.mdgit clone --depth 1 https://github.com/oh-my-engine/oh-my-engineWrote 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/oh-my-engine/oh-my-engine/ome-plan)<a href="https://agentmods.dev/commands/oh-my-engine/oh-my-engine/ome-plan"><img src="https://agentmods.dev/badge/commands/oh-my-engine/oh-my-engine/ome-plan.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00758 |
| Opus 5 | $0.00006 | $0.00379 |
| Sonnet 5 | $0.00003 | $0.00152 |
| Haiku 4.5 | $0.00001 | $0.00076 |
Grade A, and why
ome-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 6d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ome-plan
Workflow Session Start (MANDATORY)
Before reading source files, planning, editing, or running verification for this workflow, you MUST start the OME workflow session by running:
ome plan $ARGUMENTS
This creates .ome/.session so the final ome finish command can record the execution into .ome/memory/executions/.
If a Windows PowerShell policy blocks the ome shim, run the same step through the cross-shell fallback: cmd.exe /c ome.cmd plan $ARGUMENTS. Do not hardcode this fallback on non-Windows platforms.
Claude Code fast path (other agents: ignore the leading ! and run the bare command via your shell tool):
!ome plan $ARGUMENTS
Purpose
Turn a clarified task into an implementation plan with interfaces, edge cases, and test strategy.
When to Use
- Use when the goal is known but the implementation still needs design decisions.
- Use when you need a precise sequence of edits before writing code.
- Do not use when the task is already a tiny, obvious change.
Inputs
- The clarified goal and scope.
- Relevant project rules, source files, and existing patterns.
- Known edge cases, compatibility constraints, and verification expectations.
Process
- Summarize the goal and any constraints that matter.
- Identify the narrowest implementation path that preserves existing behavior.
- List interfaces, files, or modules that may change.
- Call out edge cases and failure modes before coding.
- Define the test strategy and acceptance criteria.
- Produce a plan that another engineer could implement without guessing.
- Avoid writing code in the planning step.
Red Flags
- The plan makes undocumented assumptions about public interfaces.
- The approach requires broad refactors without a clear need.
- Tests or edge cases are missing from the proposal.
- The result is really implementation disguised as planning.
Common Rationalizations
- "The obvious fix is good enough without a closer read of the rules."
- "I can skip verification because the change is small."
- "I should broaden the patch while I am here."
- "A vague summary is enough for handoff."
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.
- 6d ago First seen · 97 lines · 13 tokens per session scan A 4365d5d5e171
ome-plan is a command published in the GitHub repository oh-my-engine/oh-my-engine (5 stars, last pushed 4d ago), licensed MIT. It adds 13 tokens to every session and 758 once invoked, about $0.0001 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
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.