archagent-embed

A skill for embedding an ArchAgent agent into Codex, so Codex can work with that agent’s identity and linked skills. ArchAgent is an external agent system whose command-line tool must already be installed and authenticated.

In plain words
What is it for?
Use it to start, check, refresh, or stop an embedded agent session and inspect the skills linked to that agent.
Why use it?
It keeps the Codex session aligned with the selected embedded agent and makes the current embed state visible before actions are taken.

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

Made for: Claude Code, Codex.

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,215 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 $0.00093 $0.01215
Opus 5 $0.00046 $0.00607
Sonnet 5 $0.00019 $0.00243
Haiku 4.5 $0.00009 $0.00121

Measured 2d ago against content hash c27911f14250, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

archagent-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.

agents/archastro-onboarding/skills/archagent-embed/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 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 Codex session aligned with the active identity file.

This skill assumes the ArchAgent CLI is already installed and authenticated. Install or upgrade archagent if missing, and run archagent auth login <email> if not authenticated.

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

archagent embed start <agent-or-flags>

Then:

archagent embed status --json

Read the identity_file path from the returned state. Open and read that file. Adopt the identity for the current Codex session while retaining your normal capabilities.

After adoption, check state.skills. If the agent has linked skills, tell the user what's available and offer to install them:

archagent embed list skills --json

Active + user asks about status (or no specific intent)

Summarize the current state from the JSON already fetched:

  • Agent name and ID
  • App ID
  • Tool count and skill count
  • Loaded (installed) skills and their invocations
  • Timestamps

If the identity file has not been read in this session yet, read it and adopt the identity.

Active + user wants to sync/refresh

archagent embed sync

Then:

archagent embed status --json

Re-read the identity_file and re-adopt the refreshed identity. Report what changed (new/removed tools or skills).

Active + user wants to stop

archagent embed stop

Drop the embedded identity from the current session. Confirm that local state was removed.

Active + user asks about tools

List the embedded agent's tools:

archagent embed list tools --json

To execute a tool directly:

archagent embed run tool <tool-name> --input '<json>' --json

Read the full file on GitHub · 151 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 · 151 lines · 93 tokens per session scan A c27911f14250

Subscribe to this mod's changes

archagent-embed is a skill published in the GitHub repository ArchAstro/archagents (5 stars, last pushed 17d ago), licensed MIT. It adds 93 tokens to every session and 1,215 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.

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