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/internet-development/ts-general-agent/owner-communicationnpx skills add internet-development/ts-general-agent --skill owner-communicationgit clone --depth 1 https://github.com/internet-development/ts-general-agentWrote 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/internet-development/ts-general-agent/owner-communication)<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>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 | $0.00017 | $0.00639 |
| Opus 5 | $0.00009 | $0.00319 |
| Sonnet 5 | $0.00003 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
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.
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 Blueskycreate_memo— create a GitHub issue in the workspaceworkspace_create/workspace_find— manage collaborative workspacesplan_create— create a structured plan with tasksself_update— update your SELF.md with new learnings or instructionsself_improve— invoke Claude Code to modify your own codebase (new features, fixes, skills)web_fetch/curl_fetch— fetch content from the webarena_post_image/arena_fetch_channel— fetch and post images from Are.nabluesky_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_memowithlabels: ["discussion"]— creates a long-lived discussion thread - For quick coordination notes: Use
create_memo(defaults tomemolabel — auto-closes after 3 days if stale) - For engineering work: Use
plan_createto 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_improvewith 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
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.
- 5d ago First seen · 51 lines · 17 tokens per session scan A 46fa531c017c
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.
Other skills, from other repositories
Code Execution
Run Python, Node.js, AND arbitrary shell commands in a secure E2B cloud sandbox that PERSISTS across calls within a conversation. Clone repos, install packages, run CLI tools (git, psql, ffmpeg, duckdb), and build up state turn over turn.
Parallel Web Research
Deep web research powered by Parallel.ai — fast search with excerpts, URL→markdown extraction, long-running Task Runs, structured find-all datasets, and persistent web monitors.
CSV / Spreadsheet Operations
List sheets, read rows, read a single line, and write back to spreadsheets. Supports .csv / .tsv / xlsx / Google Sheets. Canonical partner for agentbatch when iterating row-by-row.
Platos RAG
Ingest documents into the agent's long-term memory, then retrieve chunks semantically at turn-time. Five tools — ingest, retrieve, list, reindex, delete. Chunks are stored on the user's PlatosMemory rows with kind="rag" in metadata, so scope + user isolation comes for free.
Email Send
Send transactional emails through Resend. Supports HTML / plain-text bodies, reply-to, cc, bcc, and tags.
File Operations
Read and write files in the agent's per-conversation MinIO workspace.