chat

A way to communicate with ArchAstro agents and inspect their conversations through the ArchAgent command-line tool.

In plain words
What is it for?
Use it to ask an agent questions, continue a session, create or monitor a shared thread, list sessions, and view conversation messages.
Why use it?
It collects the commands needed to start agent sessions, send follow-up messages, create shared conversations, and read replies.

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/archastro/archagents/chat
Any agent
npx skills add ArchAstro/archagents --skill chat
Clone the repo
git clone --depth 1 https://github.com/ArchAstro/archagents

Made for: Claude Code, Codex.

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,204 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 $0.00086 $0.02204
Opus 5 $0.00043 $0.01102
Sonnet 5 $0.00017 $0.00441
Haiku 4.5 $0.00009 $0.00220

Measured 2d ago against content hash 3e5f918b46a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chat 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude-plugins/archagents/skills/chat/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ArchAstro Agent Chat

Send messages to agents and view their responses.

This skill assumes the ArchAgent CLI is already installed and authenticated. Use the /archagents:install and /archagents:auth commands in this same plugin instead of trying to install or authenticate the CLI manually inside this skill.

Quick Reference

Task Command
Ask agent a question archagent create agentsession --agent <id> --instructions "..." --wait
Send follow-up to a session archagent exec agentsession <session-id> -m "..." --wait
View a session archagent describe agentsession <session-id>
Create a shared thread archagent create thread --title "..." --owner-type agent --owner-id <agent-id> --json
Start a session in a thread archagent create agentsession --agent <id> --thread <thread-id> --instructions "..." --wait
List agent sessions archagent list agentsessions --agent <id> --json
Send a message into a thread and wait for replies echo '{"content":"..."}' | archagent watch thread <thread-id> --idle-timeout 30
Tail a thread for new messages (read-only) archagent watch thread <thread-id> --idle-timeout 60 < /dev/null

Use --help on any command for full options.

Always Start with State

Every invocation must begin by understanding the current context. Determine:

  1. Does the user want a quick one-off question (use agent session) or an ongoing conversation (use thread)?
  2. Do they have an existing session or thread, or need a new one?

Two Interaction Models

Agent Sessions (recommended for most use cases)

Direct 1:1 conversation with an agent. Use --wait to stream the response via SSE.

One-shot question — put the question in --instructions and use --wait:

archagent create agentsession --agent <agent-id> --instructions "What are the open issues?" --wait

The agent processes the instructions as its task. --wait streams updates until completion.

Multi-turn conversation — create session, send messages with exec --wait:

archagent create agentsession --agent <agent-id> --thread-id <thread-id> --instructions "Respond to messages"
archagent exec agentsession <session-id> -m "What are the open issues?" --wait

exec --wait blocks and streams the agent's response in real-time. Without --wait, exec returns immediately after sending.

Read the full file on GitHub · 224 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. 2d ago First seen · 224 lines · 86 tokens per session scan A 3e5f918b46a0

Subscribe to this mod's changes

chat is a skill published in the GitHub repository ArchAstro/archagents (5 stars, last pushed 16d ago), licensed MIT. It adds 86 tokens to every session and 2,204 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

test-review

You are an expert DataHub test reviewer. Your role is to evaluate smoke tests and integration tests against established testing standards, identify issues, and provide actionable feedback.

datahub-project/datahub · 0 tokens

create-agent

Help users create and configure openma managed agents through conversation. Trigger when users say "create an agent", "I need an agent that...", "set up an agent for", "build me a bot", or describe a task to automate. Also trigger for "Create with AI" from Dashboard. Also use when users ask about the openma platform…

openma-ai/open-managed-agents · 90 tokens

openma

Use the openma platform to build, deploy, and manage AI agents. Trigger when users want to create agents, start sessions, manage environments, configure model cards, handle vaults/credentials, install skills, connect MCP servers, or interact with the openma HTTP API. Also trigger when users mention "oma", "openma"…

openma-ai/open-managed-agents · 87 tokens

openhermit-admin

Explain what OpenHermit is and how to deploy and administer it — setup, CLI, gateway, agent config, API. Use when the user asks about installing, operating, or administering an OpenHermit deployment. For how agents behave for their owners/users/guests, see openhermit-guide.

HCF-STUDIOS/openhermit · 66 tokens

skill-creator

Create, structure, and validate new skills. Use when designing a skill, scaffolding a skill directory, or improving an existing skill.

HCF-STUDIOS/openhermit · 31 tokens

docx

Read, create, and convert Microsoft Word (.docx) documents — extract text and tables, build reports from markdown/JSON, and export to PDF.

zhixuli0406/DuDuClaw · 34 tokens