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/aryaminus/socials-assistant/script-reviewnpx skills add aryaminus/socials-assistant --skill script-reviewgit clone --depth 1 https://github.com/aryaminus/socials-assistantWrote 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/aryaminus/socials-assistant/script-review)<a href="https://agentmods.dev/skills/aryaminus/socials-assistant/script-review"><img src="https://agentmods.dev/badge/skills/aryaminus/socials-assistant/script-review.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 | $0.00065 | $0.01335 |
| Opus 5 | $0.00032 | $0.00668 |
| Sonnet 5 | $0.00013 | $0.00267 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
script-review 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 4d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
script-review — vault-evidence script scoring
Score scripts against what has actually worked for THIS creator, not generic advice. Every claim in the review cites vault data or the creator profile.
Before scoring
socials-mcp:profile_get— niche, tone, keywords. If empty, build it first (4 questions + auto-fill).socials-mcp:top_content(limit: 10,metric: "views"and once withmetric: "engagement_rate") — the proven patterns.- If TikTok retention data exists (
vault_query:SELECT title, retention_json, traffic_json FROM video_metrics vm JOIN videos v ON v.id = vm.video_id WHERE retention_json IS NOT NULL ORDER BY captured_at DESC LIMIT 5), read the curves of the top performers. - Research search demand — web-search the specific topic, place, product, or person named in the script. Report High / Medium / Low demand and what it implies:
- High demand (well-known subject): can be a "big swing" piece — expect it to carry reach
- Low demand (obscure, hyper-local): fine to shoot, often converts viewers into followers well, but raw view count will likely stay modest regardless of quality
Score (0–10 each, weighted total /50)
| Dimension | Evidence source | What earns marks |
|---|---|---|
| Hook (×2) | Titles + retention of top_content | First line contains a concrete, searchable noun (a place/object/person) + tension or number — mirrors top titles; not generic ("check this out"); lands in first 2–3 seconds as a pattern-interrupt |
| Search demand (×1) | Web research (Step 4) | Topic has pre-existing name recognition or search interest; if low-demand, score honestly and adjust reach expectations |
| Structure / retention (×1.5) | Retention curves | Beats arranged so a new visual or verbal change lands every 5–8s (matches where past videos held viewers); specific re-hook around the 8–10s mark before natural drop-off; no dead middle |
| SEO (×1.5) | Profile keywords + traffic_json search share | Primary keyword spoken aloud, shown as on-screen text, AND leading the caption — all three, not just one (triple-mention measurably outperforms single); long-tail variant included |
| Fit (×1) | Profile niche/tone + audience_overview | On-niche for the audience (country/language/age), tone matches tone_notes; balances the account's ratio of discovery/story vs. educational/promotional content (roughly 2–3 discovery per 1 straight-explainer is a reasonable default) |
| Deliverable safety (×1) | brief in pipeline item (if sponsored) | Meets brand brief requirements; claims verifiable; disclosure (#ad) planned; nothing that conflicts with the creator's past collaborations |
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.
- 4d ago First seen · 81 lines · 65 tokens per session scan A b7e380dcd4ca
script-review is a skill published in the GitHub repository aryaminus/socials-assistant (0 stars, last pushed 6d ago), licensed MIT. It adds 65 tokens to every session and 1,335 once invoked, about $0.0003 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
dcf-model
Build discounted cash flow valuation workbooks in Excel.
hermes-agent-skill-authoring
Author in-repo SKILL.md files: frontmatter and structure.
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
flash-attention
Speed up long-sequence transformer training and inference.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
grounded-citations
Ground answers and documents in cited, verifiable sources.