Borrowing it
Nothing to install: this file belongs to jordanurbs/venice-video-harness. 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/jordanurbs/venice-video-harness/main/.agents/commands/fix-panel.mdgit clone --depth 1 https://github.com/jordanurbs/venice-video-harnessWrote 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/jordanurbs/venice-video-harness/fix-panel)<a href="https://agentmods.dev/commands/jordanurbs/venice-video-harness/fix-panel"><img src="https://agentmods.dev/badge/commands/jordanurbs/venice-video-harness/fix-panel/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/jordanurbs/venice-video-harness/fix-panel"><img src="https://agentmods.dev/badge/commands/jordanurbs/venice-video-harness/fix-panel.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 | $0.00000 | $0.00458 |
| Opus 5.5 | $0.00000 | $0.00183 |
| Sonnet 5.5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
fix-panel 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 2mo 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.
What it actually says
Fix character appearance in a storyboard panel using Venice multi-edit with character references.
Use this after QA flags panels with character consistency issues. Multi-edit takes the panel + character reference images and corrects character appearance without regenerating the entire composition.
Single character fix:
npx tsx src/mini-drama/cli.ts fix-panel -p output/<series> -e <episode> -s <shot> -c "SERA"
Two character fix:
npx tsx src/mini-drama/cli.ts fix-panel -p output/<series> -e <episode> -s <shot> -c "MARCUS,SERA"
Custom edit prompt (for specific issues):
npx tsx src/mini-drama/cli.ts fix-panel -p output/<series> -e <episode> -s <shot> -c "SERA" --prompt "Change the woman's dress to a deep plunging V-neckline black cocktail dress. Make her extremely busty with generous cleavage. Keep the background unchanged."
Available edit models:
nano-banana-pro-edit(default) -- same family as generation modelgpt-image-1-5-edit-- strong at reference matchinggrok-imagine-edit-- alternative optionqwen-edit-- good for precise editsflux-2-max-edit-- high quality edits
How it works:
- Loads the panel PNG as the base image
- Loads character front.png references as edit layers (up to 2)
- Constructs an edit prompt from the character's full description + wardrobe
- Calls Venice multi-edit API: panel + references -> corrected panel
- Archives the original as
shot-NNN-pre-fix.png - Saves the corrected panel as
shot-NNN.png
Two-pass storyboard (alternative):
Instead of fixing after QA, generate with refinement built in:
npx tsx src/mini-drama/cli.ts storyboard-episode -p output/<series> -e <episode> --refine
This generates panels normally, then runs multi-edit on every panel that has characters.
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.
- 2mo ago First seen · 41 lines · 0 tokens per session scan A 388be1a80052
fix-panel is a command published in the GitHub repository jordanurbs/venice-video-harness (33 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 458 tokens. 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 2026-08-30.
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.
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.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.