Brewcode Overview
Brewcode is a plugin for Claude Code that turns single sessions into an infinite task pipeline with automatic context handoff between sessions. The name is a nod to brewing: skills (recipes) define what to brew, agents (brewers) do the work, and hooks (processes) manage the lifecycle.
Key Features
Infinite context
Automatic knowledge transfer between sessions via KNOWLEDGE.jsonl and the handoff mechanism. Tasks continue after compaction without losing progress.
15 skills (recipes)
Full cycle: from project analysis (/brewcode:setup) to task execution (/brewcode:start) and code review (/brewcode:standards-review).
13 agents (brewers)
Specialized agents: developer, tester, reviewer, architect, skill-creator, agent-creator, and coordinators.
8 hooks (processes)
Lifecycle hooks for context management: knowledge injection, grepai integration, exit blocking when a task is still active.
Semantic search
Integration with grepai — AI-powered code search via Ollama + bge-m3. Auto-start, reminders, configurator.
Code quality
Standards-review, convention analysis, secrets-scan, text-optimize. Rules are automatically synced to .claude/rules/.
Architecture
Brewcode works as a layer on top of Claude Code through the hook system. The plugin has no external runtime — all context is managed through built-in Claude Code events.
Brewcode Plugin
┌──────────────────────────────────────────────────────────┐
│ │
│ Skills (recipes) Agents (brewers) │
│ ┌──────────────┐ ┌──────────────────┐ │
│ │ setup, spec │ │ developer, tester │ │
│ │ plan, start │ ──────> │ reviewer, architect│ │
│ │ convention,. │ │ coordinator, ... │ │
│ └──────────────┘ └──────────────────┘ │
│ │ │ │
│ v v │
│ Hooks (processes) Templates + Knowledge │
│ ┌──────────────┐ ┌──────────────────┐ │
│ │ session-start│ │ PLAN.md.template │ │
│ │ pre-task │ <──────> │ KNOWLEDGE.jsonl │ │
│ │ pre-compact │ │ SPEC.md.template │ │
│ │ stop │ │ artifacts/ │ │
│ └──────────────┘ └──────────────────┘ │
│ │
└──────────────────────────────────────────────────────────┘
Task execution flow
PLAN.md --> phases (phases/) --> agents execute --> hooks manage
│ │ │
│ Phase Registry │ Task API │ SessionStart
│ (phase table) │ (create/update) │ PreToolUse
│ │ │ PostToolUse
v v │ PreCompact
artifacts/{P}-{N}{T}/ KNOWLEDGE.jsonl │ Stop
{AGENT}_output.md (knowledge accumulation) v
handoff (auto)
Plugin structure
brewcode/
├── .claude-plugin/
│ └── plugin.json # Plugin manifest
├── hooks/
│ ├── hooks.json # Binding 8 hooks to events
│ ├── session-start.mjs # Session initialization
│ ├── grepai-session.mjs # Auto-start grepai watch
│ ├── pre-task.mjs # Knowledge injection into agents
│ ├── grepai-reminder.mjs # grepai reminder
│ ├── post-task.mjs # Session binding, 2-step protocol
│ ├── pre-compact.mjs # Knowledge compaction, handoff
│ ├── stop.mjs # Exit blocking
│ ├── forced-eval.mjs # Skill activation (84%)
│ └── lib/
│ ├── utils.mjs # I/O, lock files, configuration
│ └── knowledge.mjs # KNOWLEDGE.jsonl operations
├── agents/ # 13 agents
│ ├── developer.md # Feature implementation (opus)
│ ├── tester.md # Testing (sonnet)
│ ├── reviewer.md # Code review (opus)
│ ├── architect.md # Architecture (opus)
│ ├── skill-creator.md # Skill creation (opus)
│ ├── agent-creator.md # Agent creation (opus)
│ ├── hook-creator.md # Hook creation (opus)
│ ├── text-optimizer.md # Text optimization (sonnet)
│ ├── bash-expert.md # Bash scripts (opus)
│ ├── bc-coordinator.md # Task coordinator (haiku)
│ ├── bc-knowledge-manager.md # Knowledge manager (haiku)
│ ├── bc-grepai-configurator.md # grepai configurator (opus)
│ └── bc-rules-organizer.md # Rules organizer (sonnet)
├── skills/ # 15 skills
│ ├── setup/ # Project analysis, templates
│ ├── spec/ # Specification creation
│ ├── plan/ # Plan creation
│ ├── start/ # Task execution
│ ├── convention/ # Convention analysis
│ ├── rules/ # Rule extraction
│ ├── grepai/ # Semantic search
│ ├── install/ # Dependency installation
│ ├── teardown/ # Cleanup
│ ├── text-optimize/ # Text optimization
│ ├── text-human/ # Code humanization
│ ├── standards-review/ # Standards review
│ ├── skills/ # Skill management
│ ├── agents/ # Agent management
│ └── secrets-scan/ # Secrets scanning
└── templates/ # Rule templates
Target project structure
After running /brewcode:setup and /brewcode:start, the following appears in your project:
{PROJECT}/
└── .claude/
└── tasks/
├── cfg/
│ ├── brewcode.config.json # Plugin configuration
│ └── brewcode.state.json # Execution state
├── templates/ # Adapted templates
│ ├── PLAN.md.template
│ ├── SPEC.md.template
│ └── phase*.template
├── logs/
│ └── brewcode.log # Hook log
├── sessions/
│ └── {session_id}.info # Session information
└── {TS}_{NAME}_task/ # Task directory
├── PLAN.md # Execution plan
├── SPEC.md # Specification
├── KNOWLEDGE.jsonl # Accumulated knowledge
├── phases/ # Phase files
│ ├── 1-create-entity.md
│ ├── 1V-verify-entity.md
│ └── FR-final-review.md
├── artifacts/ # Agent reports
│ ├── FINAL.md
│ └── {P}-{N}{T}/
├── backup/ # Backups
└── .lock # Session lock file
Components in detail
15 skills (recipes) cover the full task lifecycle. See the Skills section for details.
| Group | Skills | Purpose |
|---|---|---|
| Core cycle | setup, spec, plan, start | Task creation and execution |
| Quality | standards-review, convention, rules, secrets-scan | Code analysis and review |
| Utilities | grepai, install, teardown, text-optimize, text-human, skills, agents | Tools and configuration |
13 agents (brewers) with different models and specializations. See the Agents section for details.
| Role | Agents | Model |
|---|---|---|
| Implementation | developer, tester, architect | opus/sonnet |
| Review | reviewer | opus |
| Creation | skill-creator, agent-creator, hook-creator | opus |
| Optimization | text-optimizer, bash-expert | sonnet/opus |
| Coordination | bc-coordinator, bc-knowledge-manager, bc-grepai-configurator, bc-rules-organizer | haiku/sonnet/opus |
8 hooks (processes) manage the lifecycle through Claude Code events. See the Hooks section for details.
| Event | Hooks | Purpose |
|---|---|---|
| UserPromptSubmit | forced-eval | Skill activation |
| SessionStart | session-start, grepai-session | Initialization |
| PreToolUse | pre-task, grepai-reminder | Context injection |
| PostToolUse | post-task | Session binding |
| PreCompact | pre-compact | Knowledge handoff |
| Stop | stop | Exit blocking |
Recommended launch order
- Installation/brewcode:install
Install dependencies: brew, coreutils, jq, optionally grepai.
- Project setup/brewcode:setup
Analyze the project and generate adapted templates.
- Specification/brewcode:spec
Parallel codebase research, SPEC.md creation.
- Plan/brewcode:plan
Phase generation, quorum review, requirements tracing.
- Execution/brewcode:start
Launch the task with infinite context and automatic handoff.