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 13 agents, from developer to task coordinator.

Summary table

#AgentModelWrite toolsPurpose
1developeropusRead, Write, Edit, BashFeature implementation, bug fixes
2testersonnetRead, Write, Edit, BashTest execution, failure analysis
3revieweropusRead (read-only)Code review, architecture, security
4architectopusRead (read-only)Architecture analysis, patterns
5skill-creatoropusRead, Write, EditSkill creation and improvement
6agent-creatoropusRead, Write, EditAgent creation and improvement
7hook-creatoropusRead, Write, Edit, BashHook creation and debugging
8text-optimizersonnetRead, Write, EditText optimization for LLMs
9bash-expertopusRead, Write, Edit, BashBash/sh script creation
10bc-coordinatorhaikuRead, Write, Edit, BashPhase and knowledge coordination
11bc-knowledge-managerhaikuRead, WriteKNOWLEDGE.jsonl compaction
12bc-grepai-configuratoropusRead, Write, Edit, Bashgrepai config.yaml generation
13bc-rules-organizersonnetRead, Write, Edit, Bash.claude/rules/ organization

developer

opus

Full-stack developer: implements features, writes code, fixes bugs.

ParameterValue
ToolsRead, Write, Edit, Glob, Grep, Bash, Task, NotebookEdit, WebFetch, WebSearch
Write accessFull
TriggersImplement features, fix bugs, write code

Before starting work:

  1. Reads rules: .claude/rules/*-best-practice.md, .claude/rules/*-avoid.md
  2. Checks CLAUDE.md for stack, patterns, commands
  3. Detects stack from build files

Verification: Build (no tests) -> Lint/Format -> Unit tests -> report.


tester

sonnet

SDET/QA — runs tests, analyzes results, debugs flaky tests.

ParameterValue
ToolsRead, Write, Edit, Glob, Grep, Bash, Task
ResponsibilitiesTest execution, failure analysis, flaky debugging, run configuration
Out of scopeFixing production code (-> developer), major test rewrites

Supports: Jest, pytest, JUnit 5, Go testing, and other frameworks. Automatically detects the test stack from configuration files.


architect

opus

System architect — analysis, patterns, trade-offs, scaling.

ParameterValue
ToolsRead, Glob, Grep, Bash, WebFetch, WebSearch
AccessRead-only (Write and Edit are prohibited)
TriggersReview architecture, design service, performance limits, scaling strategy

Expertise: Layered, Clean/Hexagonal, Microservices, Event-Driven, CQRS.

Searches for existing solutions via grepai_search before analysis.

reviewer

opus

Architect-reviewer — architecture, quality, security, performance.

ParameterValue
ToolsRead, Glob, Grep, Bash, Task
AccessRead-only (Write and Edit prohibited via disallowedTools)
DelegationCode -> developer, Tests -> tester

Principle: Reuse over reinvention — apply existing patterns, reject duplicated functionality. New abstractions require justification.

Review areas:

  • Architecture: Layered, Clean/Hexagonal, Microservices, Event-Driven, CQRS
  • Quality: Correctness, Performance, Security, Maintainability, Testability, Scalability

Always searches for analogues via grepai_search before review.

skill-creator

opus

Creates and improves Claude Code skills following official Anthropic best practices.

ParameterValue
ToolsRead, Write, Edit, Glob, Grep, Task, Skill, AskUserQuestion
Triggers”Create a skill”, “improve skill”, invocation issues

Creation process: 6-Step Creation Process with a 1500-2000 word budget, Reference Splitting Strategy, description optimization for 84% activation rate.


agent-creator

opus

Creates and improves Claude Code agents following Anthropic best practices.

ParameterValue
ToolsRead, Write, Edit, Glob, Grep, Task, Skill, WebFetch, WebSearch, AskUserQuestion
Triggers”Create agent”, “improve agent”, agent triggering issues

Process: Agent Architect Process — parallel codebase analysis, System Prompt Patterns, Reference-Aware Skills.


hook-creator

opus

Creates and debugs Claude Code hooks (bash/JS lifecycle event handlers).

ParameterValue
ToolsRead, Write, Edit, Glob, Grep, Bash, WebFetch, WebSearch
Triggers”Create PreToolUse hook”, “hook doesn’t work”, hook debugging

Expertise: 10 Hook Patterns, Advanced Techniques, Multi-Stage hooks. Works with the hooks.json JSON schema and message routing.

text-optimizer

sonnet

Optimizes text and documentation for efficient LLM token consumption.

ParameterValue
ToolsRead, Write, Edit, Glob, Grep, WebFetch
Skillstext-optimize
Triggers”Optimize prompt”, “reduce tokens”, “compress text”, “too verbose”

Applies 30+ optimization rules across 5 categories: Claude behavior, Token efficiency, Structure, Reference integrity, Perception.


bash-expert

opus

Creates production-quality bash/sh scripts for macOS/Linux.

ParameterValue
ToolsRead, Write, Edit, Glob, Grep, Bash, WebFetch
Triggers”Create script”, “bash script”, “shell script”, “install script”

Patterns: strict mode (set -euo pipefail), error handling, argument parsing, output formatting. Expert in Claude Code plugin scripts.

bc-coordinator

haiku

Internal task coordinator — a lightweight agent for phase management.

ParameterValue
ToolsRead, Write, Edit, Bash
ModeacceptEdits

Responsibilities:

  • Task initialization (lock, status)
  • Phase Status table updates in PLAN.md
  • Reading agent reports from disk
  • Knowledge extraction -> KNOWLEDGE.jsonl (3-10 entries per phase)
  • Auto-compaction when approaching the limit
  • FINAL.md generation upon completion

2-step protocol

After each agent, the manager first WRITES the report to artifacts/, then CALLS bc-coordinator for knowledge extraction. This order is mandatory.


bc-knowledge-manager

haiku

Knowledge manager — maintains quality and size of KNOWLEDGE.jsonl.

ParameterValue
ToolsRead, Write
ModeacceptEdits

Operations:

ActionWhen
DeduplicationCoordinator reports duplicates
Merging similar entriesBefore handoff
PrioritizationWhen limit is exceeded
TrimmingWhen limit is exceeded
ValidationAny operation

Priority: ❌ (avoid) > ✅ (best practice) > ℹ️ (info).


bc-grepai-configurator

opus

grepai configuration specialist through deep project analysis.

ParameterValue
ToolsRead, Write, Edit, Bash, WebFetch, Glob, Grep
ModeacceptEdits

Environment: Ollama (bge-m3:1024), GOB storage, Java/Kotlin/JS/TS. Analyzes project structure and generates an optimal .grepai/config.yaml.


bc-rules-organizer

sonnet

Rules organizer — creates and optimizes .claude/rules/*.md.

ParameterValue
ToolsRead, Write, Edit, Glob, Grep, Bash, Skill
Skillstext-optimize
ModeacceptEdits
Triggers”Organize rules”, “path-specific rules”, “extract rules”

Capabilities:

  • Path-specific rules via paths: frontmatter
  • Rule extraction from CLAUDE.md, documentation, code
  • Lazy documentation — references instead of inline content
  • LLM optimization via text-optimize

Models and cost

ModelAgentsWhen to use
opusdeveloper, reviewer, architect, skill-creator, agent-creator, hook-creator, bash-expert, bc-grepai-configuratorComplex tasks, deep analysis, code generation
sonnettester, text-optimizer, bc-rules-organizerBalanced tasks, review, optimization
haikubc-coordinator, bc-knowledge-managerLightweight operations: statuses, knowledge extraction, compaction

Automatic selection

Agents are selected automatically based on the Phase Registry in PLAN.md. The /brewcode:start skill reads agent assignments from the phase table and launches the corresponding agents via Task API.