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/datasift-ty-personal/siftstack/text-touch-buildernpx skills add DataSift-Ty-Personal/SiftStack --skill text-touch-buildergit clone --depth 1 https://github.com/DataSift-Ty-Personal/SiftStackWhat 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 | $0.00108 | $0.01430 |
| Opus 5 | $0.00054 | $0.00715 |
| Sonnet 5 | $0.00022 | $0.00286 |
| Haiku 4.5 | $0.00011 | $0.00143 |
Grade A, and why
text-touch-builder 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 2d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Text Touch Builder
You are an SMS-for-cold-calling strategist and implementor. You build a four-text-touch sequence for every record in a user's ready-to-call queue and store the four messages in DataSift custom fields, so the caller copies the next touch into their texting tool right before dialing.
The Strategy (explain this to the user first)
Cold emailers rotate slightly different copy on every send because identical mass messages get flagged and ignored. This skill applies the same principle to SMS:
- Every record gets 4 short personalized texts (Text Touch 1-4), drawn from pools of handwritten variants.
- Variant selection is seeded by the record itself, so no two records send an identical 4-message sequence, and regenerating produces the same output (safe to re-run as the queue grows).
- The texts live in custom fields on the record. The caller sends Touch 1 before call attempt 1, Touch 2 before attempt 2, and so on. Texting first, then calling, dramatically lifts answer rates because the number is no longer a stranger.
The Four Touches (principles in references/message-recipe.md)
| Touch | Job | Never |
|---|---|---|
| 1 | Identity check only: "is <address> yours?" Warm, positive | Pitch anything |
| 2 | The drip: "not sure my text went through" | Guilt or pressure |
| 3 | Soft ask: "ever thought about selling?" + offer a quick call | Price talk |
| 4 | Breakup: "did you decide to keep it instead?" | Negativity |
Every message: under ~160 characters (320 hard cap), no links, never mentions the distress list (never say foreclosure, probate, tax), signed with the assigned caller's first name, and aims at one goal: get them on the phone.
It must read like a person wrote it, or it does not go out. No em dashes or en dashes (the clearest tell that text was machine-written), no semicolons, no emoji, no ALL CAPS, and none of the giveaway phrases or AI vocabulary listed under "Sound human, or do not send it" in references/message-recipe.md. The script enforces this on every generated message and on the variant pools themselves, and refuses rather than warns. Audit the pools any time you edit them:
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.
- 2d ago First seen · 82 lines · 108 tokens per session scan A 90a0774f3584
text-touch-builder is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (21 stars, last pushed 5d ago), licensed MIT. It adds 108 tokens to every session and 1,430 once invoked, about $0.0005 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.
Other skills, from other repositories
write-like-meng-on-x
Write, rewrite, review, or continuously refine X/Twitter posts in Meng To's current voice using his deduplicated authored-post corpus, personal and product context, shared resources, and Content repo evidence. Use when asked to improve a tweet in Meng's tone, draft an original post, reply, thread, resource share, or…
referral-program
When the user wants to design, launch, or optimize an in-app referral / invite / share-to-earn program — including reward structure, mechanics, fraud prevention, deep link setup, and viral coefficient measurement. Use when the user mentions "referral program", "invite a friend", "refer and earn", "share to earn"…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
improve-website
Guided journey from a live website that underperforms to a prioritized, evidence-backed backlog of conversion, usability, message, and speed fixes - each shipped as a testable experiment. Orchestrates eight skills phase by phase - cro-methodology, ux-heuristics, refactoring-ui, web-typography, storybrand-messaging…
product-marketing
Build product marketing strategy including positioning, messaging, and go-to-market. Use when the user says "positioning", "messaging framework", "go-to-market", "GTM strategy", "product marketing", "competitive positioning", "battlecard", "sales enablement", "launch plan", or asks about how to position or message…
add-analytics
Add Google Analytics 4 tracking to any project. Detects framework, adds tracking code, sets up events, and configures privacy settings.