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 agentmods add skills/alecs5am/ralphy/fb-creativesnpx skills add alecs5am/ralphy --skill fb-creativesgit 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/fb-creatives)<a href="https://agentmods.dev/skills/alecs5am/ralphy/fb-creatives"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/fb-creatives.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 | $0.00315 | $0.04547 |
| Opus 5 | $0.00158 | $0.02273 |
| Sonnet 5 | $0.00063 | $0.00909 |
| Haiku 4.5 | $0.00032 | $0.00455 |
Grade A, and why
fb-creatives scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
How to make an N-creative FB / Meta / IG static ad pack for a real brand — generalized niche know-how, not one specific ad. A domain overlay on the standard pipeline: supplies the 5-set creative matrix (A real-people · B How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
FIRES on a generic N-creative ad-pack brief: "make 32 FB creatives for ", "ad pack for ", "set of Meta ads", "creative matrix", "8-10 static ads for IG feed", "performance creatives for our cold-traffic campaign". Any brand, any vertical — the skill is brand-agnostic.
DO NOT FIRE when:
- The brief is for ONE still (poster, drop graphic, hero image) → use
/posterinstead. - The brief is for a moving video (UGC / unboxing / talking-head) → match the matching
/ralphy-ugc-*skill. - The user points at one specific ad to reproduce (
@template:<slug>, "remix this exact ad") → that is the remix path. Seedocs/skills-vs-templates.md. - The user pasted
@guideline:<slug>for a register the pack sits in (photoreal humans, anti-AI-slop) → runralphy guideline show <slug>first and fold its rules into the A-set portrait prompts.
What this skill is
A generalized matrix overlay, not a finished ad pack. It does not name a brand, a hero, a price, or a number — it tells the art-director HOW a multi-register static ad pack is built so a strong one comes out for whatever the user is promoting. It runs through ralphy generate image; it does not bypass the reference-required gate or the site-grounding invariant.
Hard invariants
- All generation routes through
ralphy generate image(no raw API). ReadMODELS.mdbefore naming any model id — the stack below is a default, not a hardcode. - Real-brand pre-flight: site-grounding before ANY prompt. When the brief names a real brand URL, dispatch a Playwright sub-agent to crawl home +
/docs+/pricing+/features+/examplesBEFORE drafting brand-DNA. Readartifacts/refs/research.md(the sub-agent's digest), not a singleWebFetchof the home page. Every palette hex in a prompt must trace toartifacts/refs/tokens.json; every named API symbol in code-creative slots must trace to "Documented API surfaces" inresearch.md. Skipping this costsotaocr-fb-001$1.20 (wrong-palette v1 burn) + 5/32 hallucinated-Python-SDK creatives. Full discipline:.agents/skills/researcher/references/site-grounding.md. --ref artifacts/refs/hero.pngon EVERY gen. Once captured, pass the live-site hero screenshot as--refon all N creatives. Brand-palette + type drift across the pack drops to near zero. Without it, each prompt re-interprets "blue CTA" slightly differently — at 32 concepts the drift compounds.- Verify SDK / API surface before any code-creative. If the C / E sets render code on screen, the named API symbol (
import foo,foo.parse()) must exist on the brand's docs. If the landing only documents curl, the ad shows curl — not an invented Python wrapper. Curl is the strictly-safe fallback for HTTP APIs. - Append-only on regen. Re-rolling a slot writes
.v2.png, never overwrites. Failed / dark-bg v1 generations stay on disk as A/B reference. - The reference-required gate still fires for named real persons / IPs in the A or D set — refuse without a ref or logged
--no-ref-consent. - The quality gate refuses, not warns — two failed
scoreImagein a row → stop and report options.
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.
- 5d ago First seen · 208 lines · 315 tokens per session scan A c00ab4d43559
fb-creatives is a skill published in the GitHub repository alecs5am/ralphy (129 stars, last pushed 10d ago), licensed Apache-2.0. It adds 315 tokens to every session and 4,547 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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-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…
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…
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.
bioimage-analysis
Microscopy image analysis for cell biology. Cell segmentation (Cellpose, watershed), object tracking (trackpy), morphology quantification, colony counting, colocalization analysis, and cytoskeleton characterization. For pathology WSI use pathml; for flow cytometry use flow-cytometry-analysis.
flow-cytometry-analysis
Complete flow cytometry analysis pipeline. FCS file handling, compensation, manual/automated gating, immunophenotyping, CFSE proliferation analysis, cell cycle analysis (Dean-Jett-Fox), and apoptosis assays. Extends flowio with analytical workflows. For raw FCS parsing only use flowio.