alex2481kobe/claude-mods/tree/main/plugins/agent-models

A Claude Code mod that labels each subagent row in the native agent list with the model and effort it runs on, using an agent.spawn hook.
alex2481kobe/claude-mods/tree/main/plugins/agent-models

agent-models is a Claude Code plugin for the mods API that annotates every subagent entry in the agent list with the model and reasoning effort it will use, e.g. "Review auth · Opus 5.5 (high)". It works via an agent.spawn hook that appends the model label to the task description before the subagent starts, resolving the model from the Agent tool's model option, the agent file's model:/effort: frontmatter (read from .claude/agents/ and ~/.claude/agents/), or the parent's model for inheriting agents. Built-ins such as Explore and Plan, and plugin-provided agents, are intentionally left unlabelled, and rows are never guessed when the model is unknown. Tested on Claude Code 2.1.287. Install with /plugin marketplace add alex2481kobe/claude-mods and /plugin install agent-models@claude-mods.
Check the author's README for the marketplace and plugin name first. Commands may change as the repository evolves.
claude plugin marketplace add alex2481kobe/claude-mods claude plugin install agent-models@claude-mods
Each Claude subagent's model and effort in Claude Code's agent list.

Claude Code's agent list shows a subagent's task but not what it runs on. With this mod each row carries it, the way the codex mod's rows do:
Review auth · Opus 5.5 (high)
Check label.ts · Sonnet 5.5 (medium)
Say ok · Haiku
| The agent | Its label |
| --------------------------------------------------- | ------------------------------------------------- |
| general-purpose, a fork, an agent file's inherit | the parent's model and effort |
| an agent file with model: (and effort:) | that model, and that effort |
| the Agent tool's model option | that model; the parent's effort only if the same model |
| Explore, Plan and other built-ins | none: their model is the engine's to choose |
| a plugin's agent (codex:read) | none: the plugin labels its own |
Where the model cannot be known before the agent starts, the row is left as it was rather than guessed.
/plugin marketplace add alex2481kobe/claude-mods
/plugin install agent-models@claude-mods
agent.spawn hook, which runs before the subagent starts, appends
· <model> (<effort>) to the task's description; the agent list shows that
description.model option, else the agent file's, else the
parent's for the agents that inherit it. Agent files are read from the
project's .claude/agents/ and your own (~/.claude/agents/, or
$CLAUDE_CONFIG_DIR/agents/), matched by their name.effort, else the effort of the parent's
latest request, and that only when the agent runs on the parent's own model:
another model may take no effort at all (Haiku takes none).claude-opus-5-5 is Opus 5.5.agents/, or one defined in settings, a
flag or policy, is not read, so its agent goes unlabelled.model: line is left unlabelled.haiku is Haiku.effort is shown even when the Agent tool's model option
overrides its model.claude -p).claude plugin validate plugins/agent-models
claude plugin test plugins/agent-models
claude --plugin-dir plugins/agent-models
Is this your project? Add this badge to your README or website. It links back to this page.