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-promo-pipeline/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-promo-pipeline)<a href="https://agentmods.dev/skills/waynejin0918/omni-rewriter/omni-rewriter-promo-pipeline"><img src="https://agentmods.dev/badge/skills/waynejin0918/omni-rewriter/omni-rewriter-promo-pipeline/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-promo-pipeline"><img src="https://agentmods.dev/badge/skills/waynejin0918/omni-rewriter/omni-rewriter-promo-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 69 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 122 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 123 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00066 | $0.01617 |
| Opus 5 | $0.00033 | $0.00809 |
| Sonnet 5 | $0.00013 | $0.00323 |
| Haiku 4.5 | $0.00007 | $0.00162 |
Grade A, and why
omni-rewriter-promo-pipeline 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 13d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Omni-Rewriter promo pipeline
Mission
Reproduce the maintainer promo workflow: expand (PE) → generate (H3) → proof cards →
designed finale → assemble. Expand is not generate. Do not commit full .mp4 files.
Hard rules
- Video tasks require
duration_seconds; validate withBaseRewritebefore submit. - Promo model matrix excludes Seedance (
docs/promo/model_matrix.yaml). - Include roadmap models (
wanted/unverified/adapter) honestly—never claim PE for them. - No chapter bumpers (
01/02/03). Soft crossfades only. - Never burn VO/dialogue as corner subtitles; quote on-screen product text exactly.
- Proof audio comes from the PE arm only.
- Models act = short designed finale (
build_models_finale.py): bridge → brand hero → staggered T2V|T2I lanes, one continuous audio bed. No H3 hanging-board B-roll; no slat-glued names. Target full film about 30–35s. Keep still-plate motion tiny (no sway). - After H3 intro, run
fix_intro_pe_card.pyso the PE close-up uses a clean designed card (H3 often garbles PE body text). - Prefer intro freeze as atmosphere; keep both T2V and T2I named in the lanes beat.
- Assemble regenerates each outgoing tail as a designed hold from the last frame
(blur/vignette/accent — not raw
tpadclone) so dialogue survivesacrossfadeand the gap still looks intentional. - Outro CTA voice: prefer H3 15s take with the same warm narrator (S1) + pluck BGM as the
intro (
omni_promo_outro_vo.json), then clip the usable window (e.g. 0.35–~10s) intobuild_outro_audio.py --vo-audio … --bgm-vol 0→outro_full.mp4→ assemble--no-endcard. Edge-TTS is fallback only when H3 is unavailable.
Layout
| Path | Role |
|---|---|
docs/promo/*.json |
PE envelopes (request + output) |
docs/promo/model_matrix.yaml |
Canonical T2V/T2I names + status |
scripts/promo/submit_h3_chunk.py |
Submit one envelope to H3 |
scripts/promo/submit_h3_batch.py |
Multi-seed H3 regen on the 8-GPU node |
scripts/promo/build_proof_cards.py |
RAW|PE cards + PE audio |
scripts/promo/fix_intro_pe_card.py |
Replace garbled H3 PE close-up with clean card |
scripts/promo/build_models_finale.py |
Designed models finale (bridge/brand/lanes) |
scripts/promo/assemble_promo.py |
Soft-xfade final film |
scripts/promo/build_models_brand_card.py |
Legacy brand card (not default cut) |
scripts/promo/burn_names_on_slats.py |
Legacy slat name burn (not default cut) |
docs/promo/out/ |
Local outputs (gitignored *.mp4) |
docs/day2-h3-pe/ |
Site: promo entry → home.html |
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.
- 13d ago First seen · 124 lines · 66 tokens per session scan A f7b1249b228d
omni-rewriter-promo-pipeline is a skill published in the GitHub repository WayneJin0918/Omni-Rewriter (85 stars, last pushed 23d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,617 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
fal
Use when calling a fal.ai endpoint by id to generate image, audio, or video from JS/Python/curl: subscribe vs submit, queue states, ED25519 webhook signature verification, per-call cost, or migrating off @fal-ai/serverless-client. NOT which model or art direction (that is ai-media); NOT the same models on another…
minimax-h3-reference-video-prompt
Default downstream MiniMax H3 specialist for every image-based request unless the user explicitly declares boundary-only first/last frames with no reusable reference role. Use the official six-section full-reference format for character/person/object consistency, scene/style/action/camera/storyboard/voice/audio…
minimax-h3-keyframe-video-prompt
Narrow downstream MiniMax H3 specialist for pure I2VA, FL2VA, and L2VA boundary-frame prompts. Use only after minimax-h3-creative-director verifies that the user explicitly declared the images as literal first/last frames and that they have no character, identity, person, object, costume, scene, style, voice, action…
minimax-h3-multishot-planner
Non-skippable planning-only MiniMax H3 subskill used by minimax-h3-creative-director before final prompt formatting. Invoke when the user explicitly requests multiple shots, scenes, cuts, montage, or shot-by-shot design, or when a video of at least 10 seconds has no declared single-shot/multishot preference and the…
minimax-h3-text-video-prompt
Downstream MiniMax H3 specialist for professional text-to-video (T2VA) prompts using the official three-field format. Use after minimax-h3-creative-director routes a request with no image, video, or audio reference asset, or when this skill is explicitly invoked for a text-only idea, script, or storyboard requiring an…
minimax-h3-creative-director
Primary mandatory entrypoint for every MiniMax H3 video-generation request. Use before any other H3 skill for creation, animation, extension, editing, restyling, reference, or prompt review. It reads the official h3-prompt-writing specification, defaults image-based work to full-reference consistency, permits pure…