Borrowing it
Nothing to install: this file belongs to WayneJin0918/Omni-Rewriter. 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/WayneJin0918/Omni-Rewriter/main/.cursor/skills/omni-rewriter-model-contribution/SKILL.mdgit clone --depth 1 https://github.com/WayneJin0918/Omni-RewriterWrote 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/skills/waynejin0918/omni-rewriter/omni-rewriter-model-contribution)<a href="https://agentmods.dev/skills/waynejin0918/omni-rewriter/omni-rewriter-model-contribution"><img src="https://agentmods.dev/badge/skills/waynejin0918/omni-rewriter/omni-rewriter-model-contribution/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/skills/waynejin0918/omni-rewriter/omni-rewriter-model-contribution"><img src="https://agentmods.dev/badge/skills/waynejin0918/omni-rewriter/omni-rewriter-model-contribution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.00746 |
| Opus 5.5 | $0.00022 | $0.00298 |
| Sonnet 5.5 | $0.00011 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
omni-rewriter-model-contribution 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Omni-Rewriter model contribution
Start here
- Read
docs/architecture.md,docs/dialects/community-models.md, and the relevant profile guide. - Classify the contribution as exactly one of
video,image, orunified. - Copy the structure in CONTRIBUTION_TEMPLATE.md.
- Keep prompt expansion and media generation as separate deliverables.
Required implementation order
- Evidence — link the public upstream prompt/API/runtime contract. Do not infer private behavior or equate stock vLLM, custom vLLM forks, and vLLM-Omni.
- Routing — map public user intent to an existing task, or justify a new transport-neutral
task without breaking current
RewriteRequestusers. - Schema — add or reuse a strict typed output. Unknown fields must remain rejected.
- Validation — encode deterministic constraints before adding repair instructions.
- Renderer — serialize the validated output into the target public dialect.
- Repair — pass only the invalid candidate, errors, and required invariants; keep retries bounded.
- Fixtures and tests — cover valid, invalid, boundary, and RAW-vs-expanded cases.
- Adapter, optional — add generation only when a public contract exists. Pin the tested
runtime and label every untested path
unverified. - Docs — update the supported matrix only to the exact demonstrated level: PE, adapter, or live runtime.
Category checklist
Video
- Require
duration_seconds. - Define timeline, camera, motion, cut, continuity, dialogue, and audio behavior where applicable.
- Test timestamp bounds and task/media-role combinations.
- Optional dialect selector:
metadata.video_pe_profile(h3default,seedancefor Seedance PE,ltxfor LTX-2.5 PE). Seedance is PE-only. LTX has an optional official-CLI runner; live runtime is unverified until a local generate is recorded.
Image
- Omit
duration_seconds. - Define ratio/resolution, visible-text quoting, reference retention, and edit locality.
- Test T2I, I2I, and edit routes only when the model contract supports them.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 82 lines · 54 tokens per session scan A d8e15e38f9b7
omni-rewriter-model-contribution is a skill published in the GitHub repository WayneJin0918/Omni-Rewriter (89 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 746 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
omni-rewriter-model-contribution compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| omni-rewriter-model-contributionWayneJin0918/Omni-Rewriter | Skill | 89 | 2mo ago | Apache-2.0 | A | 54 | Cursor |
| model-aware-image-prompt-engineerEmily2040/nano-banana-image-skill | Skill | 36 | 5mo ago | Apache-2.0 | A | 210 | Codex |
| seedance-2-5-prompt-directorzhouwei713/seedance-2-5-prompt-director | Skill | 13 | 3mo ago | MIT | A | 159 | Codex |
| nano-banana-image-skillEmily2040/nano-banana-image-skill | Skill | 36 | 5mo ago | Apache-2.0 | A | 40 | Codex |
| seedance-prompt1370998960-del/https-github.com-Emily2040-seedance-2.0 | Skill | 247 | 4mo ago | MIT | A | 68 | Claude Code |
| ai-engineering-toolkitLiHongwei-cn/lihongwei-cn | Skill | 5 | 29d ago | MIT | A | 47 | Claude Code, Codex |
| mj-promptkhanhhuyenngo985-sys/character-scene-design-skills | Skill | 18 | 5mo ago | none | A | 53 | Claude Code, Codex |