- --goal
- States the one outcome you want the next actions to move toward, in up to 4,096 characters. It is required for every run. A specific goal, such as a date or a measurable result, produces far more specific ideas than a broad one.
- --project
- Loads the stored memory of one project, created earlier with project create, as context for this run. That memory is the project's title, its scope, and every suggestion you accepted or rejected with the reasons, and it goes to the model through your own Codex or Claude Code with the rest of the request, never to Vidbyte. Leave it out and the run reads no project file at all.
- --context
- Adds a background fact that does not fit a more specific option. Repeat it once per fact. Each value is carried to the agents as task data, never as an instruction.
- --files
- Adds a text, Markdown, or JSON file whose contents inform the run, repeated once per file. Only the paths you name are read; nothing else on disk is scanned. Oversized files are truncated and reported in the manifest rather than dropped silently. What is read goes to the model provider through your own Codex or Claude Code, so name only files you are willing to share with it.
- --attach
- Attaches one local file directly to the model's input, repeated once per file in order. Text files are sent as snapshots and supported images stay native images, both through your own Codex or Claude Code. Missing, duplicate, empty, unsupported, or oversized files fail before anything is bought or any model is called.
- --completed
- Records an outcome that is already true, so the agent does not propose it again. Repeat it once per finished item. This is the single most effective way to stop a slate from repeating work you already did.
- --in-progress
- Records work that has started but is not finished. The agent treats it as underway, so it can suggest how to finish or unblock it rather than proposing it as new. Repeat it once per item.
- --decision
- Records a decision already made, so ideas build on it instead of reopening it. Repeat it once per decision. Use it for settled choices, such as a vendor, a deadline, or an architecture.
- --constraint
- Records a hard limit every idea must respect, such as a budget, a team size, or a freeze. Repeat it once per constraint. Every idea is expected to respect it, and the independent critic reviews each idea against it.
- --avoid
- Names a direction you do not want proposed at all. Repeat it once per direction. It is softer than a forbidden action: it steers the search away rather than declaring something off limits.
- --mistakes
- Records a mistake already made, so the agent can suggest how to recover and avoid proposing a repeat. Repeat it once per mistake. Use it for errors that shaped where the work is now.
- --forbidden
- Declares an action that must never appear in a suggestion, such as deleting data or contacting customers. Repeat it once per action. Use it for anything that would be unacceptable, not merely unwanted.
- --approaches
- Records an approach you already tried or are considering, so the agent can compare against it or build on it. Repeat it once per approach. It keeps the slate from rediscovering what you already know.
- --outcomes
- Records a result you have already observed, such as a metric after a change. Repeat it once per outcome. Real outcomes let the agent judge what is working instead of guessing.
- --blockers
- Names something currently stopping progress. Repeat it once per blocker. Naming it points the agent at ideas that remove it.
- --hypotheses
- Records a belief you have not yet tested. Repeat it once per hypothesis. The agent can propose the cheapest way to confirm or kill each one.
- --risks
- Names a risk you already see. Repeat it once per risk. The agent can propose ways to reduce it, and spends less of the slate re-discovering it.
- --trajectory
- Describes the direction the work has been moving over time, such as a trend or the last few milestones. Repeat it once per note. It helps the agent tell a next step apart from a course correction.
- --question
- States an open question you want the ideas to help answer. Repeat it once per question. The agent treats each one as something worth resolving, not just as background.
- --capability
- Names a skill, tool, person, access grant, or resource available to you. Repeat it once per capability. Ideas can then use what you have instead of assuming you have nothing.
- --success
- States what success looks like for the goal. Repeat it once per criterion. The critic uses it to judge whether an idea actually moves you toward the finish line.
- --count
- Sets the most ideas the final slate may hold, from 2 to 100, defaulting to 5. It is a ceiling, not a quota, so a weaker field returns fewer ideas with a shortfall note. It is also the number the Vidbyte charge is based on, one requested suggestion at a time, so a trimmed slate still costs the count you asked for.
- --category
- Limits the search to one kind of opportunity, such as quick_wins, big_bets, risk_prevention, or strategy, repeated once per category. There are 31 categories, and unknown names are rejected before any model is called. Leave it out to consider the whole registry.
- --all-categories
- Explicitly asks for every category to be considered. This matches the behavior when no category is given, but records the intent in the saved request. It does not force one idea from each category.
- --horizon
- Chooses when ideas should become useful: now, next, later, or any, which is the default. Now keeps every idea to something you can start today, while later favors directions that pay off over time. Each idea still records its own horizon in the result.
- --rounds
- Sets how many critique-and-revision cycles refine the pool, from 1 to 8, defaulting to 2. More rounds help difficult or ambitious goals, and every round adds a critic turn and a revision turn on your own model account, while the Vidbyte charge stays the same. The run ends early if a revision leaves no candidates.
- --max-messages
- Caps how many times a critic may stop its review early and message the generator directly about one urgent problem, from 0 to 8, defaulting to 2. Once the limit is spent, critics always return a full review. Zero turns the messages off.
- --provider
- Names the model provider behind the generator and critic. The only accepted value is openai, which runs the agent on Codex. It makes the source of a run's reasoning explicit in scripts.
- --model
- Names the model that drafts and revises the ideas, which every extra-compute generator uses too. Leave it out and your host's own default model answers. A Claude model runs the agent on Claude Code and an OpenAI model runs it on Codex, and that provider bills the model's usage to your own account.
- --critic-model
- Names the model for the independent critic only, leaving the generator on its own model. It must run on the same host as the generator, and leaving it out keeps the critic on the generator's model. Use it when you want review from a stronger, cheaper, or different model than the one drafting ideas.
- --extra-compute
- Runs one separate generator for each selected category, on the generator model, and combines their ideas before critique. It finds more genuinely distinct directions, but every category adds its own model turn on your own account, so it multiplies a run's model usage. With all 31 categories, that is 31 generator turns before the first critique, for the same Vidbyte charge.
- --max-output-tokens
- Sets a token budget for each individual model reply. The agents are asked to keep every reply within it, which keeps one turn from consuming the whole run. It is a target for each reply, not a hard cap the host enforces.
- --max-total-tokens
- Bounds the token usage of the whole run, from 1 to 20,000,000 tokens, which makes it the main control on the model usage your own account pays for. It is checked before every turn, so once the budget is reached no new turn starts and the run returns the last fully reviewed ideas. The result names the stop reason so a partial slate never looks complete.
- --timeout-seconds
- Sets a deadline for the whole run, from 1 second to 86,400 seconds. No new work starts after it passes, and the last fully reviewed ideas are returned. A request already in flight may finish slightly later.
- --dry-run
- Validates the whole request and prints its settings and its context manifest without calling a model. It needs no stored key or signed-in host, buys nothing, and uses none of your balance. Use it to confirm what a large request will read before you run it.