Agents

This documentation was generated with the assistance of AI. Please report any inaccuracies.

An agent is a sub-instance of Claude Code, run via the Agent tool, with its own separate context window — spawned either to search the codebase without derailing the current conversation, or to isolate a sub-task (a verbose report, an entire multi-step skill run, a batch of independent summarization work) so only a distilled result lands back in the calling skill’s own context.

This repository defines three custom agents under .claude/agents/, each with its own detail page — Gate Runner, Isolated Skill Executor, and Change Summarizer — for shapes that recurred often enough across this catalog’s skills to be worth centralizing. This page instead documents the two built-in agent types this catalog still relies on for everything that doesn’t fit one of those three shapes.

Explore

A fast, read-only search agent for locating code — finding files by pattern, grepping for a symbol, or answering "where is X defined". It cannot edit files.

Used by

  • Explore — Step 4, codebase search of modules, abstractions and control flow.

  • Setup Antora — Step 7 uses it to locate the top-level source layout and main public entry points before writing `index.adoc’s repository overview, instead of reading the whole source tree directly.

  • Setup Readme — Step 7, locate main source entry points before reading them.

  • Update Java Spring Boot Documentation — Step 0, broad structural sweeps over modules, use cases, entities, metrics.

  • TypeScript Generate All Tests — Step 2 uses it to build a structural map of every candidate source file and the existing test-file convention across the project, instead of reading each file inline.

  • Android Generate All Tests — Step 2 uses it the same way, to map every candidate class and the existing test-file convention across the module.

  • Swift Generate All Tests — Step 2 uses it the same way, to map every candidate type and the existing test-file convention across the target.

  • .NET Generate All Tests — Step 2, to build the class/test-file inventory across the whole codebase without reading every source file directly.

  • Java Generate All Tests — Step 2, to build the class/test-file inventory across the whole codebase without reading every source file directly.

  • Java Spring Boot Performance Tests — the alternative to the iru-explore skill for Step 1’s survey.

Why this one specifically

Each of these is read-only research over a codebase whose size and shape aren’t known in advance — iru-explore’s whole job, and a narrower, bounded version of the same need in `iru-setup-antora/iru-setup-readme’s own Step 7. The `Explore agent is purpose-built for exactly that: broad, targeted search that stays out of the main conversation’s context window, without the ability to accidentally make an edit during what’s meant to be a non-destructive pass.

general-purpose

Claude Code’s default agent type — used whenever a skill spawns a sub-agent via the Agent tool without naming a specific type. It has the same tool access as the main conversation.

Used by

  • Generate Skill Docs — Step 3 spawns one per skill and per documented agent found, each reading only its own file and returning a compact structured summary (purpose, inputs, outputs, steps, invokes/spawns edges) instead of this skill’s own conversation reading every SKILL.md in the catalog directly; separately, it also spawns one (as does Update Docs) only when no Antora documentation module exists yet, to run the iru-setup-antora skill (briefed with the context of what’s about to follow) before continuing with the rest of their own work.

  • PR Description — Step 2, reads the full diff and drafts the description text.

  • Update Java Spring Boot Documentation — Step 1, runs iru-setup-antora mid-run.

  • KMP Generate All Tests — Step 5 spawns one sub-agent per class needing tests, each reading only its own source file (and any existing test file) to write or extend that class’s tests.

  • TypeScript Generate All Tests — Step 5 spawns one sub-agent per file needing tests, dispatched concurrently in batches, each reading only its own source file (and any existing test file) to write or extend that file’s tests.

  • Android Generate All Tests — Step 5 spawns one sub-agent per class needing tests, the same way.

  • Swift Generate All Tests — Step 5 spawns one sub-agent per type needing tests, the same way.

  • .NET Generate All Tests — Step 5, one per class needing new/extended tests, dispatched concurrently since each only touches its own test file.

  • Java Generate All Tests — Step 5, one per class needing new/extended tests, dispatched concurrently since each only touches its own test file.

Why this one specifically

Bootstrapping a documentation module mid-run, extracting one skill’s metadata, and drafting a description from a diff are each one-off, occasional delegations — not a shape common enough across the catalog to justify a dedicated custom agent definition the way Gate Runner, Isolated Skill Executor, and Change Summarizer were. The plain default is the right choice here: nothing about the delegation needs restricted tool access or a specialized system prompt.

Adding a custom agent to this catalog

If a future need doesn’t fit either built-in type above or one of this catalog’s three custom agents, define it under .claude/agents/<name>.md following the same frontmatter convention Claude Code uses for agent definitions, then re-run the iru-generate-skill-docs skill so this page and AI Catalog's dependency graph pick it up.