Borrowing it
Nothing to install: this file belongs to nicholasxdavis/telelink. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nicholasxdavis/telelink/master/.skills/telelink/SKILL.mdgit clone --depth 1 https://github.com/nicholasxdavis/telelinkWrote 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/nicholasxdavis/telelink/telelink)<a href="https://agentmods.dev/skills/nicholasxdavis/telelink/telelink"><img src="https://agentmods.dev/badge/skills/nicholasxdavis/telelink/telelink/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/nicholasxdavis/telelink/telelink"><img src="https://agentmods.dev/badge/skills/nicholasxdavis/telelink/telelink.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.04606 |
| Opus 5.5 | $0.00024 | $0.01842 |
| Sonnet 5.5 | $0.00012 | $0.00921 |
| Haiku 4.5 | $0.00006 | $0.00461 |
Grade A, and why
telelink 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 — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TeleLink
Agent fast path (read this first — ~10 seconds)
Do not explore telelink/*.py before running a command.
.\telelink.ps1 agent context # JSON: tone, recent caught, analyze paths, exact commands
.\telelink.ps1 agent # same as AGENTS.md cheat sheet
| User task | Command |
|---|---|
| What did X send me? | received mom or received last 5 mom |
| Read SMS thread (both ways) | convo "Contact Name" --raw |
| Read notifications | caught --raw --limit 10 |
| Send SMS | send "Contact Name" message |
| Last attachment (vision) | data/.analyze/latest.json → latest.png |
Repo root AGENTS.md and .cursor/rules/telelink-agent.mdc give Cursor/Claude the same recipes automatically.
When to use this skill
Use when the user:
- Runs or debugs
python -m telelink/telelinkcommands - Edits
config.yaml,data/contacts.jsonl, or caught data - Sets up Phone Link, watcher, intake (LAN/global), outtake (GitHub)
- Wants to send SMS, browse notifications, review missed calls, or sync contacts
- Develops or extends the
telelink/Python package
Not a cloud service — everything is local on Windows. Requires Phone Link paired with iPhone.
Setup from scratch: guided install for agents is in SETUP.md (same folder as this skill).
What TeleLink does
iPhone → Phone Link (Windows) → watcher → data/caught.jsonl
↘ data/attachments/
↘ data/.analyze/ (AI snapshot, short TTL)
Phone → intake web form (LAN) ────────→ caught + attachments + .analyze
PC files → outtake (GitHub) → QR/SMS → phone downloads
| Layer | Role |
|---|---|
| Watcher | Separate console window; WinRT/PowerShell notifications + folder watch + harvest |
| Caught | JSONL log of notifications; browse with caught |
| Contacts | data/contacts.jsonl + match rules tag senders |
| Send | Opens Phone Link SMS compose (messaging.method: manual / auto / adb) |
| Calendar | Schedule SMS for later; optional Google Calendar two-way sync |
| Calls | Phone Link call toasts → data/calls.jsonl; calls / missed CLI |
| Intake | Separate HTTP server (intake command, port 8787); baby-blue web UI |
| Outtake | Upload file(s) to GitHub, print QR or SMS link |
What ships with it
3 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.
- 1mo ago First seen · 350 lines · 61 tokens per session scan A 8d154c23f1ea
telelink is a skill published in the GitHub repository nicholasxdavis/telelink (5 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 4,606 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
agent-browser
Browser automation via Chrome/Chromium CDP — open, snapshot, click, screenshot. For testing web apps, mobile layouts, and automated interactions without Playwright/Puppeteer.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp: publish the Windows head first, then point packaging at the resolved resizetizer manifest. Use for a MAUI MSIX or signed unpackaged build, MAUI packaging in CI, or 'manifest contains unresolved placeholders' errors from winapp package.
sweetpad
Build, run, and test Xcode and Swift Package apps from the terminal with the sweetpad CLI ("xcodebuild for humans"). Use when the user wants to compile an iOS/macOS/Swift app, run it on a simulator or device, read build errors, run tests, or inspect resolved build settings from the command line — with agent-safe…
baguette
Drive and inspect iOS simulators with the baguette CLI: taps, swipes, buttons, typing, screenshots, the accessibility tree, logs, and the conditions an app runs under (location, network, appearance, push, UserDefaults), without opening Xcode. Use when an agent must act on or verify a running simulator — a UI flow…
Swift Performance Optimization Skill
Use when investigating measured Swift or Apple-platform regressions in CPU, memory, launch, scrolling, animation hitches, image processing, energy, networking, or concurrency, or when designing performance tests and Instruments experiments. Do not use for speculative micro-optimization, ordinary refactoring, or a…
ios-rebuild-dev
A development workflow for rebuilding the TermioMobile iOS app and launching it on a connected iPhone or simulator. It connects the app to the companion server running on the Mac.