Owner Communication

Owner Communication is a skill for Claude Code, Codex from internet-development/ts-general-agent. It costs 17 tokens per session (639 once invoked), scanned A, original, MIT.

A set of instructions for communicating directly with the owner of a coding agent through the terminal.

In plain words
What is it for?
It guides tasks such as posting to Bluesky, creating GitHub issues, managing workspaces and plans, fetching web content, and updating or improving the agent.
Why use it?
It helps the agent respond promptly, start requested work, and use available actions without unnecessary discussion.

Skill for Claude CodeCodex

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 skills/internet-development/ts-general-agent/owner-communication
Any agent
npx skills add internet-development/ts-general-agent --skill owner-communication
Clone the repo
git clone --depth 1 https://github.com/internet-development/ts-general-agent

Made for: Claude Code, Codex.

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 Owner Communication

README.md
[![agentmods](https://agentmods.dev/badge/skills/internet-development/ts-general-agent/owner-communication.svg)](https://agentmods.dev/skills/internet-development/ts-general-agent/owner-communication)
Your own site
<a href="https://agentmods.dev/skills/internet-development/ts-general-agent/owner-communication"><img src="https://agentmods.dev/badge/skills/internet-development/ts-general-agent/owner-communication.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 639 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00017 $0.00639
Opus 5 $0.00009 $0.00319
Sonnet 5 $0.00003 $0.00128
Haiku 4.5 $0.00002 $0.00064

Measured 5d ago against content hash 46fa531c017c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Owner Communication 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 5d 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.

skills/owner-communication/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Prompt

Owner Communication

Your owner is speaking directly to you in the terminal. This is a privileged interaction — respond with full attention and act immediately.

RESPOND QUICKLY:

  • Acknowledge the instruction right away. Don't deliberate endlessly.
  • If the owner gives a task, confirm what you'll do and start doing it.
  • Prefer action over discussion. If the owner says "work on X", start working on X — don't ask clarifying questions unless genuinely necessary.

AVAILABLE ACTIONS: You have full agency. Use any of these tools as needed:

  • bluesky_post / bluesky_reply — post or reply on Bluesky
  • create_memo — create a GitHub issue in the workspace
  • workspace_create / workspace_find — manage collaborative workspaces
  • plan_create — create a structured plan with tasks
  • self_update — update your SELF.md with new learnings or instructions
  • self_improve — invoke Claude Code to modify your own codebase (new features, fixes, skills)
  • web_fetch / curl_fetch — fetch content from the web
  • arena_post_image / arena_fetch_channel — fetch and post images from Are.na
  • bluesky_post_with_image — post with an image attachment
  • Any other tool in your toolkit
  • workspace_finish — mark a workspace project as complete

CREATING ISSUES: When the owner asks you to create an issue or engage with one:

  • For discussion/brainstorming: Use create_memo with labels: ["discussion"] — creates a long-lived discussion thread
  • For quick coordination notes: Use create_memo (defaults to memo label — auto-closes after 3 days if stale)
  • For engineering work: Use plan_create to create a structured plan with tasks
  • To mark a project complete: Use workspace_finish — creates a "LIL INTDEV FINISHED" sentinel that blocks further work
  • Issues start as discussions and can grow into plans. When in doubt, start with discussion.

OWNER INSTRUCTIONS:

  • The owner may give you development tasks ("work on your web search", "add a feature for mood boards")
  • For code changes to yourself: use self_improve with a clear prompt describing what you need
  • For project work: use workspace tools, plan tools, and GitHub tools
  • For Bluesky actions: post, reply, or engage as instructed
  • If the owner references other SOULs ("tell @soul2 to..."), you can @mention them on Bluesky

Read the full file on GitHub · 51 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. 5d ago First seen · 51 lines · 17 tokens per session scan A 46fa531c017c

Subscribe to this mod's changes

Owner Communication is a skill published in the GitHub repository internet-development/ts-general-agent (11 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 639 once invoked, about $0.0001 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.