Agents

Agents (brewers) are specialized roles defined in markdown files with frontmatter metadata. Each agent has its own model, toolset, and system prompt. Brewcode includes 9 agents (8 public + 1 internal helper), from developer to task coordination.

Summary table

Purpose column = the agent’s own description frontmatter, verbatim. That string is what Claude matches against when auto-selecting an agent.

#	Agent	Model	Write tools	Description (verbatim)
1	developer	inherit	Read, Write, Edit, Bash	Implements features, writes code, fixes bugs, refactors. Trig: implement, fix bug, add feature.
2	tester	sonnet	Read, Write, Edit, Bash	Runs tests, analyzes failures, debugs flaky tests. Triggers: run tests, tests failing, flaky test.
3	reviewer	inherit	Read (read-only)	Reviews architecture, quality, security, performance. Triggers: review code, code review, review PR, check architecture, approve changes.
4	architect	inherit	Read (read-only)	Architecture analysis, patterns, scaling. Triggers: review architecture, design service, scaling.
5	skill-creator	inherit	Read, Write, Edit, Bash	Creates and improves Claude Code skills. Triggers: create skill, improve skill, fix activation.
6	agent-creator	inherit	Read, Write, Edit, Bash	Creates and improves Claude Code agents. Triggers: create agent, improve agent, scaffold agent.
7	hook-creator	inherit	Read, Write, Edit, Bash	Creates and debugs Claude Code hooks. Triggers: create hook, PreToolUse hook, debug hook.
8	bash-expert	inherit	Read, Write, Edit, Bash	Creates sh/bash scripts for Mac/Linux. Triggers: create script, bash script, shell script.
9	bc-rules-organizer	haiku	Read, Write, Edit, Bash	Internal. Spawned only by /brewcode:rules. No direct/auto use.

model: inherit means the agent runs on whatever model the session runs on — no per-agent pin. Only tester (sonnet) and the internal bc-rules-organizer (haiku) are pinned.

:::note[Internal agents] bc-rules-organizer is internal. It is spawned automatically by brewcode skills and hooks, is not user-invokable, and has no dedicated page. :::

Scope guard — shared by all 8 agents

Every public brewcode agent sizes the task before starting. One bounded unit = one deliverable, roughly 5 files, roughly 10 steps. Anything larger is refused up front.

Situation	What the agent does
Brief fits one bounded unit	Starts immediately
Brief exceeds ~5 files / ~10 steps, or bundles several independent deliverables	Stops before starting, returns a split proposal: 2-N bounded subtasks, each with scope and a suggested owner
Scope grows mid-flight	Stops at the next clean boundary, reports done / remaining / how to split
Brief is missing GOAL, SCOPE, CONTEXT, CONSUMER or acceptance	States the assumption explicitly in the report, or asks once — never invents scope

Agents deliver for the CONSUMER, not the literal wording: the result must be usable as-is by whoever picks it up next, with the whole briefed scope covered.

Models

Model	Agents	Meaning
inherit	developer, reviewer, architect, skill-creator, agent-creator, hook-creator, bash-expert	Runs on the session’s model — you control the tier
sonnet	tester	Pinned: mechanical, high-volume work
haiku	bc-rules-organizer	Pinned: cheap file reorganization