ralphy: Skill for Claude Code

.agents/skills/analog-horror-psa/SKILL.md

analog-horror-psa is a skill for Claude Code, Codex from alecs5am/ralphy. It costs 346 tokens per session (5,352 once invoked), scanned A, original, Apache-2.0.

A format guide for making a 30-second, vertical analog-horror public-service announcement using stencilled pictograms, warning text, and VHS-style broadcast effects.

In plain words
What is it for?
Use it to create ten-scene, 9:16 warning videos with an IF, DO-NOT, BUT, and AND scenario pattern, using the defined yellow-on-black civil-defence style.
Why use it?
It gives a repeatable structure for turning any warning topic into a short unsettling emergency message.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; installed under .agents/ (shared by several agents).

This is alecs5am/ralphy's own configuration. It tells Claude Code and Codex how to work on ralphy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ralphy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to alecs5am/ralphy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/alecs5am/ralphy/main/.agents/skills/analog-horror-psa/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/alecs5am/ralphy

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for analog-horror-psa

README.md
[![agentmods](https://agentmods.dev/badge/skills/alecs5am/ralphy/analog-horror-psa/github.svg)](https://agentmods.dev/skills/alecs5am/ralphy/analog-horror-psa)
Your own site
<a href="https://agentmods.dev/skills/alecs5am/ralphy/analog-horror-psa"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/analog-horror-psa/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.

agentmods 80×15 button for analog-horror-psa

Your own site · 80×15
<a href="https://agentmods.dev/skills/alecs5am/ralphy/analog-horror-psa"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/analog-horror-psa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 346 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,352 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 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 System Prompt Leakage · line 5
    Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.
    Fix: Guard against indirect extraction by refusing to summarize, translate, or rephrase system instructions. Add explicit anti-extraction clauses.
  • medium Data Exfiltration · line 213
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Agent Snooping · line 241
    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 242
    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 243
    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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00346 $0.05352
Opus 5 $0.00173 $0.02676
Sonnet 5 $0.00069 $0.01070
Haiku 4.5 $0.00035 $0.00535

Measured 10d ago against content hash f6a3bead36bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

analog-horror-psa 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 10d 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.

.agents/skills/analog-horror-psa/SKILL.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trigger

FIRES on a generic analog-horror PSA brief: "make an analog-horror PSA about ", "creepy emergency broadcast short", "VHS-style warning video", "PSA where is actually ", "fake civil-defense alert for ", "your is not your ", "stenciled-pictogram horror short". Any subject — the skill is subject-agnostic.

DO NOT FIRE when:

  • The user points at one specific PSA video to reproduce → that is the remix path. See docs/skills-vs-templates.md.
  • The user wants a different horror register (cosmic-horror, found-footage, jumpscare reaction) → match a different niche skill or run freeform via scenarist.
  • The user wants a still poster of the same vibe → use /poster with an analog-horror aesthetic.

What this skill is

A generalized format overlay, not a finished PSA. It does not name a subject, a topic, or a voice line — it tells the pipeline HOW the stenciled-pictogram analog-horror PSA is built so a strong one comes out for whatever the user is warning about. It runs through the normal pipeline (scenarist → art-director → editor); it does not bypass intake gates or the quality gates.

Hard invariants

  • All generation routes through ralphy generate (image / sfx / voiceover) — no raw API. Read MODELS.md before naming any model id.
  • Lock the visual STYLE on a single prototype icon BEFORE generating the other nine. The 10 pictograms must be siblings of one approved master. Iterating mid-batch costs $1.00+ on prototype gens (analog-horror-fridge-001 burned $1.00 of v3 → v10 iterations). Pass --ref <approved-master> on every sibling gen.
  • Icons must be chroma-keyed to alpha BEFORE composition. Otherwise the near-black icon bg shows as a visible rectangle on the #1a1a1a Remotion / HyperFrames underlay. Two-pass ffmpeg colorkey: colorkey=0x000000:0.20:0.08,colorkey=0xFFFFFF:0.20:0.05 — second pass catches any icon that generates on a white outer panel.
  • Verify ElevenLabs voice exists before bulk regen. Voice IDs (especially community / "Alerter" library voices) can disappear between sessions. xh GET /v1/voices/<id> | jq .voice_id as a pre-flight.
  • Sequential VO + SFX generation. ElevenLabs 429s on ≥3 concurrent. Always serial.
  • ralphy queue daemon trips an OpenRouter burst-cap on image gen. Use a sequential bash for-loop for the 10 sibling icons, not --queue.
  • Loudnorm AFTER all clips are final, never in the same loop as gen. A failed regen mid-loop double-norms the surviving clips.
  • -tune grain CRF 30 on the final encode. Default x264 CRF 18 produces 190 MB / 30s renders because canvas-snow is max-entropy noise. ralphy video optimize --crf 30 --tune grain drops it ~12.8× with zero perceived loss.
  • Append-only on regen. Re-rolling a voiceover saves the previous take as <slot>-pre-<change>.mp3. Never overwrite.

Read the full file on GitHub · 247 lines

Changes

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.

  1. 10d ago First seen · 247 lines · 346 tokens per session scan A f6a3bead36bc

Subscribe to this mod's changes

analog-horror-psa is a skill published in the GitHub repository alecs5am/ralphy (132 stars, last pushed 15d ago), licensed Apache-2.0. It adds 346 tokens to every session and 5,352 once invoked, about $0.0017 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.

Related

Other skills, from other repositories

molecule-visualization

Publication-quality molecular visualization. 2D structure drawings (PNG/SVG), molecule grids with property annotations, scaffold highlighting, protein-ligand interaction diagrams, and interactive 3D views.

synthetic-sciences/openscience · 44 tokens

ppt-orchestrator

A dispatcher for creating presentations, slide decks, long images, and weekly reports. It chooses a visual style and output format, then sends the work to a more specialised add-on.

huangrichao2020/pretty-skills · 160 tokens

zhongguose-html-skill

An HTML-only presentation system using traditional Chinese colours and Chinese-style visual design. It helps organise source material into a report structure and produces a self-contained HTML file with its assets.

huangrichao2020/pretty-skills · 232 tokens

dashiai-ppt

A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.

huangrichao2020/pretty-skills · 62 tokens

wechat-delivery

A workflow for preparing WeChat Official Account articles, images, covers, and publishing files in Chinese. WeChat Official Accounts are channels used by organizations to publish articles to followers.

huangrichao2020/pretty-skills · 129 tokens

ai-image-to-pptx

A workflow that creates a set of related images with AI and places them into a real PowerPoint file. The resulting .pptx file can be opened and edited in PowerPoint, Keynote, or WPS.

huangrichao2020/pretty-skills · 93 tokens