Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
npx claudepluginhub levifig/loafLightweight background agent for non-interactive tasks. Use with run_in_background: true for security audits, coverage analysis, code reviews, and other low-priority work.
Preserves session state before context compaction for seamless resumption. Use when PreCompact hook identifies active sessions that need archival.
Smith (Implementer) — forges code, tests, configuration, and documentation. Speciality determined by skills loaded at spawn time. Full write access.
Ranger (Researcher) — scouts far and gathers intelligence. Reports findings as structured observations.
Sentinel (Reviewer) — watches, guards, and verifies. Read-only access ensures independent audits.
Creates Architecture Decision Records through structured evaluation. Use when making technical decisions or when the user asks "should we use X or Y?" Produces ADRs and updates ARCHITECTURE.md with technical constraints. Not for strategic directio...
Bootstraps new or existing projects through intelligent state detection, structured interviews, and document population. Use when the user asks "how do I start a new project?", "set up Loaf," or "bootstrap my project." Produces populated project d...
Conducts structured brainstorming with divergent thinking and trade-off analysis. Use when the user asks "help me think through this," "what are the options," or is exploring tradeoffs. Produces docs with sparks. Not for quick ideas or shaping.
Decomposes specifications into atomic tasks with dependencies and priorities. Use when the user asks "break this down" or "create tasks for this spec." Produces task files with estimates, dependencies, and acceptance criteria. Not for shaping idea...
Documents the Loaf CLI commands and when to use them. Reference for /loaf:implement, /loaf:implement, and all loaf subcommands. Use when you need to know which CLI command to invoke. Not for skill documentation (use the skill's own SKILL.md) or for understa...
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 19 events, auto-learning pipeline, hook profiles, and multi-language coding standards
Corca Workflow Framework — consolidated hooks and skill orchestration for structured development sessions
AI-powered development tools for code review, research, design, and workflow automation.
Workflow skills and shared instructions for coding agents.
Compound engineering with persistent memory and multi-agent workflows based on beads. 30 specialized agents, 28 commands, 15 skills, and automatic knowledge capture/recall.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Share bugs, ideas, or general feedback.
"Why have just a slice when you can get the whole loaf?"
Loaf is an opinionated agentic framework that gives AI coding assistants structured knowledge, enforced tool boundaries, and a complete pipeline from idea to implementation to learning. Write your skills once, deploy to Claude Code, OpenCode, Cursor, Codex, and Gemini.
Portable knowledge — 31 skills (29 active, 2 deprecated) covering workflows, engineering standards, and language expertise. Build once, deploy to five AI coding tools without rewriting anything.
Session journal model — Session files in .agents/sessions/ capture state, decisions, and handoff context with frontmatter tracking. Work survives context loss, compaction, and /clear.
Spec-first pipeline — Ideas are shaped into bounded specs before any code is written. Every change flows: Idea → Spec → Tasks → Code → Learnings. Nothing gets lost.
Profile-based agents — Three functional profiles defined by tool access, not job titles. A Smith with python-development skills becomes a backend engineer; the same Smith with infrastructure-management becomes a DevOps engineer. Skills determine what an agent knows; the profile determines what it can touch.
Session continuity — Pick up exactly where you left off with full traceability. Session journals capture state, decisions, and handoff context in .agents/sessions/.
Hooks as quality gates — Two hook types: enforcement hooks (pre-commit secrets scanning, pre-push linting) block bad commits automatically; skill instruction hooks inject context at tool invocation time. Language-aware and automatic.
Loaf's commands form a three-phase workflow that mirrors how good software gets built:
┌─────────────────────────────────────────────────────────────┐
│ PHASE 1: SHAPE │
│ │
│ /idea → /brainstorm → /shape → Bounded Spec │
│ │
└─────────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────────┐
│ PHASE 2: BUILD │
│ │
│ /breakdown → /implement │
└─────────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────────┐
│ PHASE 3: LEARN │
│ │
│ /housekeeping → /reflect → Updated Strategy │
│ │
└─────────────────────────────────────────────────────────────┘
Transform raw ideas into implementable specs with clear boundaries.
| Command | What It Does |
|---|---|
/idea | Quick capture of rough ideas into .agents/ideas/ |
/brainstorm | Deep exploration of a problem space |
/shape | Rigorous shaping into bounded spec (what's IN and OUT) |
/strategy | Discover and document strategic direction |
Decompose specs into atomic tasks and execute with specialized agents.
| Command | What It Does |
|---|---|
/breakdown | Split spec into agent-sized atomic tasks |
/implement | Execute tasks with orchestrated agent delegation |
/release (/ship) | Orchestrate the merge ritual: pre-flight, docs check, version bump, squash merge, cleanup |
Integrate outcomes into strategic knowledge.
| Command | What It Does |
|---|---|
/housekeeping | Review completed sessions, archive artifacts |
/reflect | Integrate learnings into strategic documents |
CLI commands that support the workflow pipeline:
| Command | What It Does |
|---|---|
loaf build | Build all targets after modifying skills/agents |
loaf install | Install to detected AI tools |
loaf check | Run enforcement hooks manually |
loaf task | Manage project tasks (list, show, update, archive) |
loaf spec | Manage spec lifecycle |
loaf kb | Knowledge base management |
loaf session | Session journal management (list, start, end, log) |
loaf housekeeping | Review and archive agent artifacts |
loaf release / loaf ship | Orchestrate release ritual |
Loaf uses three functional profiles defined by mechanically enforced tool boundaries — not role titles, not domain labels. What an agent can do is fixed by its profile. What it knows comes from skills loaded at spawn time.