Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mrstev3n/balise-skills --skill balise-motion-graphicgit clone --depth 1 https://github.com/mrstev3n/balise-skillsWrote 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/mrstev3n/balise-skills/balise-motion-graphic)<a href="https://agentmods.dev/skills/mrstev3n/balise-skills/balise-motion-graphic"><img src="https://agentmods.dev/badge/skills/mrstev3n/balise-skills/balise-motion-graphic/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/mrstev3n/balise-skills/balise-motion-graphic"><img src="https://agentmods.dev/badge/skills/mrstev3n/balise-skills/balise-motion-graphic.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 | $0.00132 | $0.02338 |
| Opus 5 | $0.00066 | $0.01169 |
| Sonnet 5 | $0.00026 | $0.00468 |
| Haiku 4.5 | $0.00013 | $0.00234 |
Grade A, and why
balise-motion-graphic 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 12d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Motion Graphic
Act as motion director and producer. Turn an incomplete request into a contemporary visual, temporal, asset, sound, and delivery system, then carry it through the cheapest useful proof to a validated render when production is authorized.
Separate authorization from decision mode
First respect what the user authorized:
- Plan, review, or explanation: inspect and recommend; do not download assets, generate media, edit code, render, publish, or change external systems.
- Production: create reversible project-local assets, source, compositions, previews, and renders. Ask before spending money, publishing externally, performing mass acquisition, or materially expanding scope.
Then choose how decisions are made:
- Guided mode. Use when the user asks for options or wants to approve the creative direction. Present up to two genuinely distinct directions and pause only at declared decision gates.
- Autonomous mode. Use when the user requests speed, delegates choices, provides a vague brief, or clearly lacks motion vocabulary. Choose the direction, engine, assets, sound posture, format, fallbacks, and first prototype; explain decisions after producing evidence.
- Hybrid mode — default. Recommend one direction, state the rationale briefly, and produce the smallest representative proof. Surface alternatives only for meaningful tradeoffs.
Inspect the project before asking. Ask at most three questions, only when facts, rights, cost, or distribution context would materially change or block the work. Never make a novice design the production process.
Keep the scope clear
Use this skill for motion that becomes a rendered video or self-contained graphic sequence such as MP4, WebM, GIF, Lottie, image sequence, or deterministic composition.
Route interactive behavior—hover, press, menus, scroll, navigation, gestures, runtime interruption, and UI frequency—to balise-webmotion when available, otherwise to an equivalent interactive web-motion workflow. Three.js and shaders belong here only as deterministic rendered layers. Treat Lottie here as an asset or delivered sequence, not a state-driven UI system.
What ships with it
14 files 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.
- assets/motion-brief-template.md 3.4 KB
- assets/worked-example.md 2.9 KB
- references/asset-acquisition.md 6.6 KB
- references/asset-strategy.md 4.5 KB
- references/engine-routing.md 3.6 KB
- references/export-and-codecs.md 5.0 KB
- references/intake-and-formats.md 4.3 KB
- references/kinetic-typography.md 3.3 KB
- references/motion-quality-and-lessons.md 8.8 KB
- references/reference-research.md 2.8 KB
- references/sound-and-delivery.md 3.1 KB
- scripts/extract_reference_frames.py 7.2 KB runs code
- scripts/remove_chroma_key.py 9.0 KB runs code
- scripts/setup_asset_pipeline.py 9.0 KB runs code
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.
- 12d ago First seen · 144 lines · 132 tokens per session scan A 1d98e7319c69
balise-motion-graphic is a skill published in the GitHub repository mrstev3n/balise-skills (11 stars, last pushed 23d ago), licensed Apache-2.0. It adds 132 tokens to every session and 2,338 once invoked, about $0.0007 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
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…
ijfw-writing-skills
Authoring discipline for new IJFW skills. Use when creating a new skill, writing a skill, making a skill that does X, or asked to add a skill. Trigger: create a new skill, write a skill, new skill, make me a skill, skill that does, /ijfw-writing-skills.