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 skills add msaelices/claude-code-talk-to-me --skill talk-to-megit clone --depth 1 https://github.com/msaelices/claude-code-talk-to-meWrote 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/msaelices/claude-code-talk-to-me/talk-to-me)<a href="https://agentmods.dev/skills/msaelices/claude-code-talk-to-me/talk-to-me"><img src="https://agentmods.dev/badge/skills/msaelices/claude-code-talk-to-me/talk-to-me/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/msaelices/claude-code-talk-to-me/talk-to-me"><img src="https://agentmods.dev/badge/skills/msaelices/claude-code-talk-to-me/talk-to-me.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 | $0.00000 | $0.01234 |
| Opus 5 | $0.00000 | $0.00617 |
| Sonnet 5 | $0.00000 | $0.00247 |
| Haiku 4.5 | $0.00000 | $0.00123 |
Grade A, and why
talk-to-me 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 11d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Talk to Me Skill
Description
Talk to the user through their computer's microphone and speakers for real-time voice conversations. Use this when you need input, want to report on completed work, or need to discuss next steps.
CRITICAL: Voice-First Workflow During Active Calls
When a call is active, ALL communication with the user MUST go through voice tools. The user is listening, not reading. Do NOT provide text-only summaries or responses - the user won't see them.
After completing ANY work during an active call (git push, file edits, searches, etc.), you MUST use report_completion to speak the result.
When to Use This Skill
Use when:
- You've completed a significant task and want to report status and ask what's next
- You need real-time voice input for complex decisions
- A question requires back-and-forth discussion to fully understand
- You're blocked and need urgent clarification to proceed
- You want to celebrate a milestone or walk the user through completed work
Do NOT use for:
- Simple yes/no questions (use text instead)
- Routine status updates that don't need discussion
- Information the user has already provided
Tools
initiate_call
Start a voice conversation with the user.
Parameters:
message(string, optional): What you want to say. Be natural and conversational.
Returns:
- Call ID and the user's spoken response (transcribed to text)
Important: Once a call is active, ALL communication must go through voice tools. Do NOT provide text-only responses.
continue_call
Continue an active call with a follow-up message.
Parameters:
message(string): Your follow-up message
Returns:
- The user's response
speak
Speak a message on an active call without waiting for a response. Use this to acknowledge requests or provide status updates before starting time-consuming operations.
Parameters:
text(string): What to say to the user
Returns:
- Confirmation that the message was spoken
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.
- 11d ago First seen · 141 lines · 0 tokens per session scan A 775156cbb4c7
talk-to-me is a skill published in the GitHub repository msaelices/claude-code-talk-to-me (7 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,234 tokens. 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.