telelink AGENTS.md

telelink AGENTS.md is an instructions file for Codex, OpenCode from nicholasxdavis/telelink. It costs 978 tokens per session, scanned A, original, MIT.

Repository instructions and command shortcuts for TeleLink, a Windows tool that reads and sends phone text messages through a paired Phone Link device.

In plain words
What is it for?
Use it to read recent messages, inspect full SMS conversations and phone notifications, view the latest attachment, or send a text message.
Why use it?
It removes the need to search the codebase or remember the exact commands for common message tasks.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/nicholasxdavis/telelink/agents-md
Clone the repo
git clone --depth 1 https://github.com/nicholasxdavis/telelink

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for telelink AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nicholasxdavis/telelink/agents-md.svg)](https://agentmods.dev/instructions/nicholasxdavis/telelink/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/nicholasxdavis/telelink/agents-md"><img src="https://agentmods.dev/badge/instructions/nicholasxdavis/telelink/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 978 This file is loaded in full into every session.
When invoked 978 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00978 $0.00978
Opus 5 $0.00489 $0.00489
Sonnet 5 $0.00196 $0.00196
Haiku 4.5 $0.00098 $0.00098

Measured 3d ago against content hash 778cf29f9fbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

telelink AGENTS.md 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 3d 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.

AGENTS.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Do not explore the codebase first. Run commands from this repo root.

.\telelink.ps1 agent context    # JSON: tone, recent messages, analyze paths, exact commands
.\telelink.ps1 agent            # this cheat sheet as text

Full skill (setup, config, dev): .cursor/skills/telelink/SKILL.md


Run commands

Shell Command
Shortcut .\telelink.ps1 <cmd>
Direct .\.venv\Scripts\python.exe -m telelink <cmd>

Windows only. Phone Link must be paired. Watcher optional for convo / received; required for live caught.


Task → command (copy-paste)

User wants Run this
What did [name] send me? .\telelink.ps1 received mom
Last N messages from someone .\telelink.ps1 received last 5 mom
Read full SMS thread (both directions) .\telelink.ps1 convo mom --raw
List recent SMS threads .\telelink.ps1 convo threads
Read phone notifications .\telelink.ps1 caught --raw --limit 10
See last attachment (vision) Read data/.analyze/latest.json then data/.analyze/latest.png
Send SMS now .\telelink.ps1 send "Contact Name" Your message here
Schedule SMS later .\telelink.ps1 send in%2hour% "Contact" Your message
List contacts .\telelink.ps1 contacts
Missed calls .\telelink.ps1 missed
Share file to phone .\telelink.ps1 outtake C:\path\to\file.pdf
Auto-reply session with someone .\telelink.ps1 ars start {session} {who} then ars next {session} --raw — see .skills/telelink/ARS.md

“What did my mom send me?”

Use received, not convo alone:

.\telelink.ps1 received mom
  • Resolves mom, Mom?, Mom🩵, etc. via contacts + match rules
  • Returns one JSON object with full message bodies (not truncated tables)
  • Only incoming messages (what they sent you)

--raw on convo is JSONL for the whole thread; flags work after the contact: convo mom --raw, convo last 10 mom --raw.

Read the full file on GitHub · 98 lines

Changes

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.

  1. 3d ago First seen · 98 lines · 978 tokens per session scan A 778cf29f9fbd

Subscribe to this mod's changes

telelink AGENTS.md is an instructions file published in the GitHub repository nicholasxdavis/telelink (5 stars, last pushed 3mo ago), licensed MIT. It adds 978 tokens to every session, about $0.0049 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.