# AGENTS.md — Build guide for Revid AI ## Project scope Turn a reviewed script and reusable style file into a small sequence of generated or user-supplied shots, add authorized narration/captions and render a vertical video. Catalogue verdict: yes. Revid does not own a model or a render farm. The shots come from Seedance 2.0 and Gemini Omni Flash, the voice comes from ElevenLabs, and the stitch is ffmpeg. All three are public APIs with public docs, so the honest replacement is an agent skill that reads those docs and calls them: a project folder per video, a style file holding the look, aspect ratio, pacing, captions, and voice, and a cache so a re-render does not repay for unchanged shots. This is why it lands on yes where the older video tools on this site land on kinda. Those wrap encoding and editing infrastructure you would have to rebuild. Revid wraps three endpoints. What you are really paying for is that someone already wired them together and pointed them at a publishing button. Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope. ## Working agreement - Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture. - Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled. - After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran. - Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply. - Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization. ## Prerequisites - Runtime and tools: Node, TypeScript and FFmpeg in a CLI/skill folder with JSON style and render-manifest files. - Before starting: FFmpeg, user-owned assets, an approved voice and currently documented generation-provider credentials; no web server is required. ## Stack and architecture - Node, TypeScript and FFmpeg in a CLI/skill folder with JSON style and render-manifest files - Data design: Store StyleVersion, Shot, ProviderJob, NarrationSegment and RenderManifest; each shot keeps its prompt/config/receipt and failed jobs can be resumed without repurchasing completed shots. - Setup: FFmpeg, user-owned assets, an approved voice and currently documented generation-provider credentials; no web server is required ## Security and data integrity - Keep source files immutable and store edit decisions separately. Run media tools with argument arrays, bounded file size/runtime and unique job directories; only rename a completed export into its final location. - Deliver a CLI/skill-folder workflow rather than a full editor. Verify current model availability and voice rights before integration; no invented model endpoints, automatic publishing or assumed generation costs. - Keep secrets outside client bundles and exported projects; document what leaves the device and make retention/deletion controls visible. ## Agent implementation rules - Project rule — domain: Store StyleVersion, Shot, ProviderJob, NarrationSegment and RenderManifest; each shot keeps its prompt/config/receipt and failed jobs can be resumed without repurchasing completed shots. - Project rule — scope and recovery: Deliver a CLI/skill-folder workflow rather than a full editor. Verify current model availability and voice rights before integration; no invented model endpoints, automatic publishing or assumed generation costs. - Project rule — acceptance: Make the second shot generation fail after the first completes; retain the first receipt, allow a local replacement and keep narration/captions aligned in the final render. - Project rule — delivery: document real setup commands and permissions; do not claim a build, accuracy level, performance result or security certification that has not been demonstrated. ## Optional agent skills and references - Recommended skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — review configuration and API defaults against the app-specific invariants and recovery boundaries above; this is not a security certification. Follow the maintainer's installation instructions and match its requirements to the chosen runtime. - Recommended skill: [copywriting](https://github.com/coreyhaines31/marketingskills/blob/main/skills/copywriting/SKILL.md) — write clear, evidence-grounded draft copy or notifications without invented claims; sending/publishing remains separately approved. Follow the maintainer's installation instructions and match its requirements to the chosen runtime. Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism. ## Distribution ideas These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone. - Demonstrate this working slice using synthetic or explicitly authorized non-sensitive examples: Turn a reviewed script and reusable style file into a small sequence of generated or user-supplied shots, add authorized narration/captions and render a vertical video. - Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Make the second shot generation fail after the first completes; retain the first receipt, allow a local replacement and keep narration/captions aligned in the final render. - State the limits before asking someone to replace their existing tool: Deliver a CLI/skill-folder workflow rather than a full editor. Verify current model availability and voice rights before integration; no invented model endpoints, automatic publishing or assumed generation costs. ## Engineering roadmap 1. Phase 1 — Pin the working slice and create its example input: Turn a reviewed script and reusable style file into a small sequence of generated or user-supplied shots, add authorized narration/captions and render a vertical video. Confirm setup: FFmpeg, user-owned assets, an approved voice and currently documented generation-provider credentials; no web server is required. 2. Phase 2 — Implement durable result files and command invariants before formatting terminal output: Store StyleVersion, Shot, ProviderJob, NarrationSegment and RenderManifest; each shot keeps its prompt/config/receipt and failed jobs can be resumed without repurchasing completed shots. 3. Phase 3 — Connect CLI commands to real saved state and explicit result/exit statuses. Keep source files immutable and store edit decisions separately. Run media tools with argument arrays, bounded file size/runtime and unique job directories; only rename a completed export into its final location. 4. Phase 4 — Expose the app-specific limits and recovery path in context: Deliver a CLI/skill-folder workflow rather than a full editor. Verify current model availability and voice rights before integration; no invented model endpoints, automatic publishing or assumed generation costs. 5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Make the second shot generation fail after the first completes; retain the first receipt, allow a local replacement and keep narration/captions aligned in the final render. Finish the README and backup/restore instructions; report unfinished capabilities explicitly. ## Paid-product capabilities outside this build - the 3M+ viral video library to remix, which is a licensing problem and not a coding one - one-click publishing to TikTok, Instagram, and YouTube - AI avatars, face swaps, and the 100+ prebuilt tools around the core generator - one predictable bill instead of three metered APIs you can overspend on in an afternoon - auto-mode workers grinding out videos while you are asleep ## Implementation prompt Build the following focused alternative to Revid AI. Implement the focused workflow below first; the verdict is not evidence of a completed or production-certified build. WORKING SLICE Turn a reviewed script and reusable style file into a small sequence of generated or user-supplied shots, add authorized narration/captions and render a vertical video. SETUP AND ARCHITECTURE Use Node, TypeScript and FFmpeg in a CLI/skill folder with JSON style and render-manifest files. Prerequisites: FFmpeg, user-owned assets, an approved voice and currently documented generation-provider credentials; no web server is required. Before integrating anything, record actual versions and permissions, plus model files or provider limits only where used, in the README; make unavailable dependencies visible rather than simulating success. DOMAIN MODEL AND INVARIANTS Store StyleVersion, Shot, ProviderJob, NarrationSegment and RenderManifest; each shot keeps its prompt/config/receipt and failed jobs can be resumed without repurchasing completed shots. IMPLEMENTATION CONTRACT Keep source files immutable and store edit decisions separately. Run media tools with argument arrays, bounded file size/runtime and unique job directories; only rename a completed export into its final location. Provide documented CLI inputs, progress/status output, reviewable result files and explicit exit codes; do not add a web application. Preserve the last saved state if a job or save fails. Include empty, loading, permission-denied, partial and retryable-error states. Log identifiers and error categories without secret values or unnecessary private content. APP-SPECIFIC BOUNDARY AND RECOVERY Deliver a CLI/skill-folder workflow rather than a full editor. Verify current model availability and voice rights before integration; no invented model endpoints, automatic publishing or assumed generation costs. ACCEPTANCE SCENARIO Make the second shot generation fail after the first completes; retain the first receipt, allow a local replacement and keep narration/captions aligned in the final render. Also resume the configured workflow after an interrupted operation, confirm the saved record/export remains inspectable, and document the recovery action. These are implementation acceptance requirements, not a claim that this guide has been tested. DELIVERY Deliver the CLI/skill folder with its dependency manifest, versioned configuration/result files, a non-sensitive example, setup instructions, exact acceptance commands and a recovery/export walkthrough. Implement the working slice before optional integrations; list any deferred paid-product capabilities honestly. Do not add capabilities outside the working slice just to resemble the original product. PROJECT RULES FOR AGENTS.md Keep the domain invariants above executable at the write boundary. Propose scope changes before adding providers or permissions. Never fabricate source evidence, publish results, identity matches or successful delivery. Preserve user originals and require an explicit confirmation for destructive changes or external publication. ## Completion evidence Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.