What is update-agent?

A tool for creating, changing, and removing agent templates—saved instructions that define specialised AI helpers, including their tools and permissions.

Use it to find agent templates, write new ones, update their instructions or access, and delete agents you no longer need.

It keeps agent definitions organised and lets you decide whether to create a new helper or adjust an existing one. It also accounts for differences between Claude, Copilot, and Codex, while noting that Cursor does not support agents.

update-agent — Skill for Claude Code and Codex by fabis94

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.

Any agent

npx skills add fabis94/universal-ai-config --skill update-agent

Clone the repo

git clone --depth 1 https://github.com/fabis94/universal-ai-config

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fabis94/universal-ai-config/update-agent/github.svg)](https://agentmods.dev/skills/fabis94/universal-ai-config/update-agent)

Your own site

<a href="https://agentmods.dev/skills/fabis94/universal-ai-config/update-agent"><img src="https://agentmods.dev/badge/skills/fabis94/universal-ai-config/update-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fabis94/universal-ai-config/update-agent"><img src="https://agentmods.dev/badge/skills/fabis94/universal-ai-config/update-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 748 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00032	$0.00748
Opus 5.5	$0.00013	$0.00299
Sonnet 5.5	$0.00006	$0.00150
Haiku 4.5	$0.00003	$0.00075

Measured yesterday against content hash d0cf8cd25a4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

update-agent 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.

.universal-ai-config/skills/update-agent/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manage Agent Templates

Agents are specialized AI personas with scoped tools and permissions that run in isolated contexts.

Every target supports agents. Cursor agents (.cursor/agents/<name>.md) take only name, description, model, readonly and background. Codex emits each agent as a standalone .codex/agents/<name>.toml file (body becomes developer_instructions) and skips an agent with no description or an empty body; see <%= docPath('uac/codex') %>.

Finding Existing Agents

List files in <%= agentTemplatePath() %>/ to discover existing agent templates. Read their frontmatter to understand each agent's purpose and capabilities.

Deciding What to Do

Create new: when you need a new specialized persona with distinct capabilities
Update existing: when an agent needs adjusted tools, permissions, or system prompt
Delete: when an agent is no longer needed; then run uac generate --clean so its output goes too

Creating a New Agent

Create a .md file in <%= agentTemplatePath() %>/ with a descriptive name (e.g. code-reviewer.md)
Add YAML frontmatter with at minimum name and description
Write the agent's system prompt as the body

Frontmatter Fields

Key fields: name, description, model, effort, tools, permissionMode, skills, hooks, plus Cursor's readonly, Copilot's modelPolicy, and the Codex-only codex block. Every field with its per-target support: <%= docPath('uac/frontmatter') %>. Per-target override syntax: <%= docPath('uac/templates') %>.

Cross-target gotchas for agents

model, permissionMode, and tools don't carry over between targets. Set model per target. Codex agents inherit the session's sandbox, approvals and MCP servers, so permissionMode, tools, skills and mcpServers are dropped for Codex (set sandboxing in .codex/config.toml; restrict tools per MCP server with enabledTools). Copilot's default harness rejects handoffs, subAgents and argumentHint, so uac drops them. Details: <%= docPath('uac/codex') %>. Model IDs per target: <%= docPath('uac/models') %>. Tool names per target: <%= docPath('uac/tools') %>.

Read the full file on GitHub · 59 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.

yesterday Changed · +5 lines d0cf8cd25a4c
2d ago Changed · -4 lines 42760755c9cb
2mo ago First seen · 58 lines · 32 tokens per session scan A 9538eb975e03

Subscribe to this mod's changes

update-agent is a skill published in the GitHub repository fabis94/universal-ai-config (14 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 748 once invoked, about $0.0001 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 2026-08-30.

Building agents

update-agent next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
update-agentfabis94/universal-ai-config	Skill	14	2d ago	MIT	A	32	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex