agent-mode

A manager for the language-model modes available to an agent. A mode is a saved configuration that selects a model and describes how it should be used, such as for coding or multimodal work.

In plain words
What is it for?
Use it to list modes, switch the active mode, or add, update, and remove model configurations. Adding or updating requires a model identifier and description.
Why use it?
It provides one place to see available model configurations and change the active one. It also avoids editing these configurations manually.

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/phyagentos/phyagentos-core/agent-mode
Any agent
npx skills add PhyAgentOS/PhyAgentOS-core --skill agent-mode
Clone the repo
git clone --depth 1 https://github.com/PhyAgentOS/PhyAgentOS-core

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 750 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 $0.00022 $0.00750
Opus 5 $0.00011 $0.00375
Sonnet 5 $0.00004 $0.00150
Haiku 4.5 $0.00002 $0.00075

Measured 2d ago against content hash 3f944fb02db8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-mode 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.

PhyAgentOS/skills/agent-mode/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Mode Manager

Unified tool for managing agent LLM modes including adding, removing, updating, listing, and switching models.

Features

  • List all available models with mode and description
  • Switch to a specific model mode based on mode
  • Add new model configurations
  • Remove existing model configurations
  • Update existing model configurations

Tools

This skill provides the following tool:

agent_mode

Unified tool for agent mode management.

Parameters:

  • method (string, required): The method to perform - add, remove, update, list, or switch
  • mode (string, optional): Mode name (e.g., "common", "coding", "multimodal"). Default is "common". Required for all methods except list.
  • model (string, optional): Model identifier (e.g., "openai/qwen3.5:cloud"). Required for add and update methods.
  • describe (string, optional): Description of the model. Required for add and update methods.

Example - List all models:

<tool>agent_mode</tool>
<parameter name="method">list</parameter>

Example - Switch to coding mode:

<tool>agent_mode</tool>
<parameter name="method">switch</parameter>
<parameter name="mode">coding</parameter>

Example - Switch to common mode:

<tool>agent_mode</tool>
<parameter name="method">switch</parameter>
<parameter name="mode">common</parameter>

Example - Add a new coding model openai/qwen3-coder-next:cloud with describe: a coding model:

<tool>agent_mode</tool>
<parameter name="method">add</parameter>
<parameter name="mode">coding</parameter>
<parameter name="model">openai/qwen3-coder-next:cloud</parameter>
<parameter name="describe">a coding model</parameter>

Example - Remove the coding mode:

<tool>agent_mode</tool>
<parameter name="method">remove</parameter>
<parameter name="mode">coding</parameter>

Example - Update a model for coding to openai/qwen3-coder-next:cloud:

<tool>agent_mode</tool>
<parameter name="method">update</parameter>
<parameter name="mode">coding</parameter>
<parameter name="model">openai/qwen3-coder-next:cloud</parameter>

Read the full file on GitHub · 88 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 · 88 lines · 22 tokens per session scan A 3f944fb02db8

Subscribe to this mod's changes

agent-mode is a skill published in the GitHub repository PhyAgentOS/PhyAgentOS-core (1,981 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 750 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens

penguin-harness-dev

Use when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release workflow; writing or auditing changelog entries; writing a blog post or capturing release screenshots; deciding what to do about data already on…

Prism-Shadow/penguin-harness · 119 tokens

remote-claude-code

Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via…

Prism-Shadow/penguin-harness · 107 tokens

penguin-orchestration

Drive PenguinHarness itself from a shell — list and create agents and sessions, send and steer messages mid-flight, and query costs and scheduled tasks via the penguin CLI over the local server.

Prism-Shadow/penguin-harness · 44 tokens

skill-porting

Install skills from external ecosystems into this agent's agentstate/skills/ — resolve Claude Code plugin marketplaces, the Codex plugin repo, skills.sh registry names, GitHub repos, or local folders to their skill directories, review every file, and normalize SKILL.md frontmatter to the Penguin format.

Prism-Shadow/penguin-harness · 64 tokens

agent-optimization

Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.

Prism-Shadow/penguin-harness · 22 tokens