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 alecs5am/ralphy --skill flash-reelgit clone --depth 1 https://github.com/alecs5am/ralphyWrote 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/alecs5am/ralphy/flash-reel)<a href="https://agentmods.dev/skills/alecs5am/ralphy/flash-reel"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/flash-reel/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/alecs5am/ralphy/flash-reel"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/flash-reel.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 Excessive Agency · line 232 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 254 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 319 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00100 | $0.06680 |
| Opus 5.5 | $0.00040 | $0.02672 |
| Sonnet 5.5 | $0.00020 | $0.01336 |
| Haiku 4.5 | $0.00010 | $0.00668 |
Grade A, and why
flash-reel 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 1mo 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 — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flash Reel
GOLDEN RULE — References over text Never describe a character's physical appearance in the prompt text. All identity comes EXCLUSIVELY from reference images. In prompts, refer to characters only as "the man from reference images" or "the woman from the girl reference image". For outfits: normally, just say "wearing the outfit from the outfit reference image." HOWEVER, if the user's setting requires a genre shift (e.g., adapting a modern shirt into a torn ancient Greek chiton or cyberpunk armor), you MUST describe the structural stylization in the text prompt while still passing the outfit reference. The text prompt handles: scene/environment, mood/vibe, camera/film aesthetic, and genre-adapted clothing changes. If you catch yourself writing hair color, facial features, or body type in a prompt — delete it and let the images do the work.
Outfit references
The main character's outfit is NOT hardcoded — it is collected from the user in STEP 1 (clothing description + outfit reference photo). Upload the user's outfit photo via higgsfield_upload to get a media_input id, then include it in images[] alongside all identity references for every scene that character appears in. The outfit ref must be the LAST image in the array (after all identity refs). Use the user's clothing description in prompts to reinforce the look. If the user says the previous outfit "looks terrible" or similar — ask for a new outfit photo and regenerate all affected scenes with the new outfit ref immediately, no questions asked.
Virality engineering for Scene 1
Scene 1 must be genuinely disorienting and scroll-stopping — NOT just a clean portrait with flash. Strong virality signals:
- Face half-swallowed by shadow, only one eye/cheekbone caught by flash
- Demonic hand/fingers reaching from void behind or around subject
- Extremely low angle looking up with cruel half-smile
Half-face lit, other half dissolved to absolute black with single supernatural element (glowing eye, etc.) Imminent fatal danger: a weapon mid-swing inches from the subject's neck while they remain oblivious and calm. Tension of "something terrible is about to happen." Avoid: clean symmetrical portraits, fully lit faces, standard headshots — these read as generic even with good aesthetics.
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.
- 1mo ago First seen · 372 lines · 100 tokens per session scan A 8663856f35fa
flash-reel is a skill published in the GitHub repository alecs5am/ralphy (140 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 100 tokens to every session and 6,680 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
video-gen
Use when generate videos with AI models — Runway, Kling, Sora, Pika, Seedance 2.0, Grok Imagine, Veo. Text-to-video, image-to-video, video extension, multi-modal references. Use when generating video from text prompts, animating images, or creating AI video content.
clinical-reports
Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…
molecular-cloning
Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.
geo-database
Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis.