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 ArchAstro/archagents --skill chatgit clone --depth 1 https://github.com/ArchAstro/archagentsWrote 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/archastro/archagents/chat)<a href="https://agentmods.dev/skills/archastro/archagents/chat"><img src="https://agentmods.dev/badge/skills/archastro/archagents/chat/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/archastro/archagents/chat"><img src="https://agentmods.dev/badge/skills/archastro/archagents/chat.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 | $0.00086 | $0.02204 |
| Opus 5.5 | $0.00034 | $0.00882 |
| Sonnet 5.5 | $0.00017 | $0.00441 |
| Haiku 4.5 | $0.00009 | $0.00220 |
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 2mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- archagent-chat — 98% identical, 6 lines differ
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:
- Does the user want a quick one-off question (use agent session) or an ongoing conversation (use thread)?
- 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.
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.
- 2mo ago First seen · 224 lines · 86 tokens per session scan A 3e5f918b46a0
chat is a skill published in the GitHub repository ArchAstro/archagents (7 stars, last pushed 29d ago), licensed MIT. It adds 86 tokens to every session and 2,204 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
test-review
You are an expert DataHub test reviewer. Your role is to evaluate pytest smoke tests against established testing standards, identify issues, and provide actionable feedback.
sre-agent
Deploy or update the SRE Agent on Omnara, a production investigator that diagnoses issues across AWS and source code and reports the likely cause with evidence. Use when the user asks to deploy, set up, update, or remove the SRE agent.
browser-agent
Build and deploy a Browser Agent on Omnara, a long-running agent that signs in to web apps with stored credentials and works in a real browser, overnight if needed. Interviews the user about the job, sign-ins, schedule, and Slack or Discord first. Use when the user asks to build, deploy, set up, update, or remove a…
email-agent
Deploy or update the Email Agent on Omnara, an agent with its own email address that people can email, Cc, or @mention, built on Primitive's hosted email functions and MCP server. Use when the user asks to deploy, set up, update, customize, or remove the email agent.
linkedin-signal-agent
Deploy or update the LinkedIn Signal Agent on Omnara, an agent that scrapes LinkedIn posts (keyword search plus tracked company and profile feeds) and delivers a daily digest. Use when the user asks to deploy, set up, update, or remove the LinkedIn signal agent.
posthog-analytics-agent
Deploy or update the PostHog Analytics Agent on Omnara, an agent that queries a PostHog project through PostHog's MCP server and delivers a daily usage report. Use when the user asks to deploy, set up, update, or remove the PostHog analytics agent.