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 Rishi4792/compass --skill cinematic-herogit clone --depth 1 https://github.com/Rishi4792/compassWrote 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/rishi4792/compass/cinematic-hero)<a href="https://agentmods.dev/skills/rishi4792/compass/cinematic-hero"><img src="https://agentmods.dev/badge/skills/rishi4792/compass/cinematic-hero.svg" alt="Measured on agentmods" 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 | $0.00203 | $0.01771 |
| Opus 5 | $0.00102 | $0.00886 |
| Sonnet 5 | $0.00041 | $0.00354 |
| Haiku 4.5 | $0.00020 | $0.00177 |
Grade A, and why
cinematic-hero 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 8d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cinematic-Hero — the motion + cinematic-visual house style
North stars: buzz.xyz (kinetic energy, spray-paint wordmarks) · SpaceX.com (restraint, cold cinematic grade, mission-HUD) · Christopher Nolan (gravitas — weight, atmosphere, decisive moments). The output should make a viewer believe the product is world-class — the asset itself is proof of quality.
Golden rule that took the most iterations to learn: motion is PHYSICS, never linear. Things have mass — they overshoot, oscillate, and lock decisively. A plain spin/fade reads as "AI slop." Weight over speed.
Companion files (in this skill dir)
template.html ← the cinematic canvas + physics-motion library. START HERE — copy it, then write beats.
render.sh ← per-frame renderer → GIF + MP4, or a single still. Has the hard-won pipeline lessons baked in.
The DNA (what "cinematic" means here — keep all of it)
- Environment: deep cold indigo→black grade · volumetric god-rays from a top light · atmospheric haze + drifting dust · film grain (feTurbulence overlay) · deep vignette · a mission-control HUD (letterbox bars, mono tracked labels, timecode, a
GATES ARMED-style status). Light emerges from darkness; nothing is flat. - Motion (physics): damped-harmonic settle (
damp()— overshoot → oscillate → converge) · velocity-based motion blur (mblur()) · decisive locks (lock()→ a flash + an expanding shockwave ring + the target element ignites; and text flips state — "seeking…"→"LOCKED", fail→pass — AT the lock, not gradually) · slow, weighty timing. - Type: SpaceX condensed uppercase, wide-tracked labels/HUD · buzz spray-paint hero wordmarks (
#sprayfeTurbulence displacement + a blurred glow copy + light-sweep) · mono for terminals/HUD. - Content — show REAL depth, never abstraction: a lit terminal with actual work ticking in (CI 94/94, eslint 0, secret-scan clean, adversarial review…) beats any "4 cute cards." Give roles a persona (e.g. The Adversary — "assume it's wrong, try to break it"). Prove things.
- Accent: the ONLY brand color (default indigo
--accent:#7C74FF); green = pass, red = fail. Everything else is the cinematic grade. Swap--accentfor the brand; keep the grade.
What ships with it
2 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.
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.
- 8d ago First seen · 45 lines · 203 tokens per session scan A c9ff6d870e70
cinematic-hero is a skill published in the GitHub repository Rishi4792/compass (2 stars, last pushed 2d ago), licensed MIT. It adds 203 tokens to every session and 1,771 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
github-pr-review
Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
a11y-audit
Dedicated WCAG 2.2 AA/AAA accessibility audit across 10 dimensions (A1-A10) covering semantic HTML, keyboard navigation, ARIA patterns, color contrast, forms, images/media, responsive/zoom, motion/animation, reading/content, and legal compliance. Goes far beyond surface-level design-review checks with deep…
init
Opt-in onboarding for the mARC agent team. Scaffolds a per-repo team binding so the team graduates from ephemeral session-memory to persistent, versioned config — without ever writing a file silently. Discovers the repo's org/repo/ project at runtime via gh, prefills {{ agentsdir }}/team.toml, and (optionally) a lean…
review
Run a full code review on current changes or specified files. Runs ruff lint, review-code agent, and security scan in sequence.
media-gen
Photoreal image + video generation and upscaling via fal.ai (pay-per-use, one API key, always-current models: Kling, Seedance, FLUX, nano-banana Pro, Topaz). Use for image-to-video ("animate this image", "turn this photo into a video"), photoreal video clips for websites/demos, hero video loops, upscaling…