agent-toolkit: Skill for Codex

.agents/skills/agent-bringup/SKILL.md

agent-bringup is a skill for Codex from sageox/agent-toolkit. It costs 74 tokens per session (2,124 once invoked), scanned A, original, Apache-2.0.

A setup tool for creating and configuring a hosted software agent, including its identity, chat surfaces, memory, tools, and repository context. It can validate an existing setup and optionally publish the agent.

In plain words
What is it for?
Use it to create, initialize, configure, diagnose, validate, or deploy an agent with the agent-toolkit command line tool.
Why use it?
It provides a repeatable way to bring an agent from an incomplete or new configuration to a checked setup.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md; $skill-name invocation.

This is sageox/agent-toolkit's own configuration. It tells Codex how to work on agent-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-toolkit configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./bin/sageox-agent doctor --agent <agent-name>.

Reuse

Borrowing it

Nothing to install: this file belongs to sageox/agent-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sageox/agent-toolkit/main/.agents/skills/agent-bringup/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sageox/agent-toolkit

Made for: 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 agent-bringup

README.md
[![agentmods](https://agentmods.dev/badge/skills/sageox/agent-toolkit/agent-bringup/github.svg)](https://agentmods.dev/skills/sageox/agent-toolkit/agent-bringup)
Your own site
<a href="https://agentmods.dev/skills/sageox/agent-toolkit/agent-bringup"><img src="https://agentmods.dev/badge/skills/sageox/agent-toolkit/agent-bringup/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.

agentmods 80×15 button for agent-bringup

Your own site · 80×15
<a href="https://agentmods.dev/skills/sageox/agent-toolkit/agent-bringup"><img src="https://agentmods.dev/badge/skills/sageox/agent-toolkit/agent-bringup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,124 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00074 $0.02124
Opus 5 $0.00037 $0.01062
Sonnet 5 $0.00015 $0.00425
Haiku 4.5 $0.00007 $0.00212

Measured yesterday against content hash a57a4ab349ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-bringup 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 yesterday.

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/skills/agent-bringup/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bring up an agent

Use the toolkit CLI as the implementation. Do not recreate its identity, credential, surface, or deployment logic in the skill. Keep the agent directory declarative and make each step safe to repeat.

Choose the path

Inspect the target before changing it:

ls "${AGENT_TOOLKIT_HOME:-${XDG_CONFIG_HOME:-$HOME/.config}/agent-toolkit/agents}"
./bin/sageox-agent doctor --agent <agent-name>

Each agent is one self-contained directory under that home. There is no list subcommand; running the CLI with no arguments prints the usage and the home path it resolved.

  • For a new human-guided agent, ./bin/sageox-agent create is the user's to run in their own terminal. The interview covers mission inputs, definition of done, approval boundaries, voice, visual metaphor, palette, expression, and a role-specific joke, and avatar generation offers three candidates. A tool shell has no TTY, so the same command run by you asks nothing, takes every default, and skips preflight.
  • To scaffold it yourself, supply the corresponding flags and either --starter-avatar or --generate-avatar --avatar-candidates 1 --non-interactive.
  • For an existing agent, preserve its directory and use only the focused command for the missing capability. Never recreate an identity to repair registration.

Read identity-design.md before drafting or substantially changing AGENTS.md, profile.json, or the agent's operating contract.

Create locally

Hand the guided flow to the user when they can answer at a terminal:

./bin/sageox-agent create --name <agent-name>

To scaffold it yourself, make every choice explicit — nothing is asked for:

./bin/sageox-agent create \
  --name <agent-name> \
  --display-name "<display name>" \
  --about "<one-line purpose>" \
  --inputs "<trusted inputs and sources>" \
  --success "<observable definition of done>" \
  --boundary "<actions requiring approval>" \
  --voice "<chat voice>" \
  --visual "<signature silhouette or prop>" \
  --metaphor "<visual role metaphor>" \
  --palette "<wardrobe and palette intent>" \
  --expression "<expression and posture>" \
  --joke "<role-specific visual joke>" \
  --starter-avatar --non-interactive

Read the full file on GitHub · 191 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 191 lines · 74 tokens per session scan A a57a4ab349ef

Subscribe to this mod's changes

agent-bringup is a skill published in the GitHub repository sageox/agent-toolkit (10 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 2,124 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 2026-09-10.