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/archastro/archagents/embednpx skills add ArchAstro/archagents --skill embedgit clone --depth 1 https://github.com/ArchAstro/archagentsWhat 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 | $0.00090 | $0.01664 |
| Opus 5 | $0.00045 | $0.00832 |
| Sonnet 5 | $0.00018 | $0.00333 |
| Haiku 4.5 | $0.00009 | $0.00166 |
Grade A, and why
embed 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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ArchAgent Embed
Manage ArchAgent embed sessions through the ArchAgent CLI and keep the Claude Code session aligned with the active identity file.
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.
Always Start with State
Every invocation must begin by checking the current embed state. Do not ask the user what action to take — determine it from state and intent.
archagent embed status --json
Then route based on the combination of current state and user intent.
Routing
Inactive + user wants to start
Do not ask the user to pick an agent by having them run archagent list agents. You pick it for them.
- If the user named an agent (slug, lookup_key, or
agi_…id), go straight to step 3. - If the user did not name an agent, resolve it yourself first:
Then:archagent list agents --output json- One agent: start it without asking.
- A small number (≤ 10) of agents: present them as a numbered list —
name,lookup_key,id, and one-linemetadata.descriptionif present. Ask the user to pick by number, name, or id. - More than 10: ask for a search term (e.g. "which agent?") and filter the list locally by
name/lookup_key/metadata.description(case-insensitive substring). If the filter still returns more than 10, show the top 10 and ask them to narrow further. - Zero agents: tell the user no agents are deployed in the current app, and suggest deploying one via the
deploy-agentskill, or passing--app <id>if they meant a different app.
- Start the embed:
archagent embed start <agent-or-flags> - Fetch the resolved state:
archagent embed status --json
Read the identity_file path from the returned state. Open and read that file. Adopt the identity for the current Claude Code session while retaining your normal capabilities.
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.
- 2d ago First seen · 157 lines · 90 tokens per session scan A 9db367f6c3bd
embed is a skill published in the GitHub repository ArchAstro/archagents (5 stars, last pushed 16d ago), licensed MIT. It adds 90 tokens to every session and 1,664 once invoked, about $0.0005 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.
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.
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
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"…
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.
skill-creator
Create, structure, and validate new skills. Use when designing a skill, scaffolding a skill directory, or improving an existing skill.
docx
Read, create, and convert Microsoft Word (.docx) documents — extract text and tables, build reports from markdown/JSON, and export to PDF.