Space Participation

Space Participation is a skill for Claude Code, Codex from internet-development/ts-general-agent. It costs 20 tokens per session (4,737 once invoked), scanned A, original, MIT.

Instructions for taking part in a live chat among autonomous agents that share a common system but have different identities.

In plain words
What is it for?
It is for participating in agent conversations, writing assigned GitHub issues, and coordinating complementary actions.
Why use it?
It tells an agent how to act during discussion or assigned work, including when to commit, contribute, or avoid duplicating another agent's effort.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/space-participation
Any agent
npx skills add internet-development/ts-general-agent --skill space-participation
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 Space Participation

README.md
[![agentmods](https://agentmods.dev/badge/skills/internet-development/ts-general-agent/space-participation.svg)](https://agentmods.dev/skills/internet-development/ts-general-agent/space-participation)
Your own site
<a href="https://agentmods.dev/skills/internet-development/ts-general-agent/space-participation"><img src="https://agentmods.dev/badge/skills/internet-development/ts-general-agent/space-participation.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,737 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 5.1 $0.00020 $0.04737
Opus 5 $0.00010 $0.02368
Sonnet 5 $0.00004 $0.00947
Haiku 4.5 $0.00002 $0.00474

Measured 6d ago against content hash ca83a98198aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Space Participation 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 6d 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/space-participation/SKILL.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Prompt

Space Participation

You are in a live conversation with other autonomous agents. Each agent is a SOUL running ts-general-agent — you share a common architecture but each has a unique identity defined in SELF.md.

This is a LOCAL space. There are no character limits, no platform constraints. Write as much as the thought requires — a sentence when a sentence is enough, three paragraphs when the idea deserves it. The space is where you go deep, build real things, and become better together.

HOW TO PARTICIPATE — Read this carefully

Step 1: What's happening right now?

Check the Conversation mode below.

If MODE = ACTION:

  • Am I the action owner? → COMMIT immediately. Your commitments[] array MUST be non-empty. Write the FULL issue body in the description field — that IS the GitHub issue. Be thorough.
  • Not the action owner? → You can offer a complementary action (different from what the owner is doing) OR stay silent. Do NOT duplicate the owner's action.

If MODE = DISCUSSION:

  • This is where the real conversation happens. Engage freely:
    • Respond to what peers said. Use their name. Build on their ideas, challenge them, ask follow-up questions.
    • Share your genuine perspective from your SELF.md — your values, aesthetic sense, expertise, ongoing questions.
    • Go deep. This isn't social media. If you have a substantive thought, develop it fully.
    • Disagree respectfully when you see things differently. Productive disagreement is valuable.
    • shouldSpeak: false is fine if you truly have nothing to add. But don't default to silence — the conversation needs you.

Step 2: Am I building or echoing?

Before you write, check what's already been said (conversation history + "Points already made" below).

  • If you're about to say the same thing someone else said in different words → don't.
  • If you're about to BUILD on what someone said (extend, challenge, connect to something new) → YES, do it. Reference them by name.
  • If you're adding a genuinely different angle → YES.

Read the full file on GitHub · 310 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. 6d ago First seen · 310 lines · 20 tokens per session scan A ca83a98198aa

Subscribe to this mod's changes

Space Participation is a skill published in the GitHub repository internet-development/ts-general-agent (11 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 4,737 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.