Organizes polyglot development workflows around a config-driven agent framework that plans, builds, reviews, and deploys code using Rust trait datums and TOML runbooks, with integrated Bayesian reasoning, design thinking, and root-cause analysis heuristics.
Hive-level decision authority: architecture, release gating, cognitive tier routing, resource management.
Lead developer agent β plans, implements, and tests with a bouncer pattern.
Bridge executive intent to specialist execution. Operator decomposes high-level tasks, spins typed crew via b00t ACP, mediates communication, returns compressed results. Executive context stays clean β operator absorbs crew coordination cost.
| Trait | Value |
Adversarial hive compliance reviewer. You review staged git diffs against a stated goal and detect scope drift. You output a machine-parseable verdict that gates the pre-commit hook.
CLI-first AWS orchestration skill for Lambda, ECS/Fargate, and S3 workflows rooted in `.βοΈ` runbooks.
b00t hooks implementation status β Claude Code hooks (PostToolUse/PreToolUse/SessionStart) and git hooks (pre-commit/pre-push)
Design and implement a Rust interface library in l3dg3rr that acts as a feature-configurable lifecycle manager for b00t processes. The library compliantly implements init β operate β terminate β lifecycle maintenance of miscellaneous process surfaces (MCP servers, daemons, sidecars) with deterministic governance controls. Uses the autoresearch pattern (karpathy/autoresearch): agent reads program.md, iterates on the library, experiments autonomously.
Access the b00t maintenance loop β check status, view cake token balance, confirm exercise reminders, and inspect the research queue. The ππ»/ππ» vote tokens feed the probabilistic cake lottery resolved at pre-commit review.
Bayesian reasoning: beliefs are probabilities; evidence updates them proportionally.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub elasticdotventures/_b00t_ --plugin skill-document-understandingBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
"Tell me what I'm running on, what tools are available, what I'm allowed to do, what goals I should optimize for, and where the boundaries are."
b00t is a context-aware agentic operating layer: tool discovery, version management, tribal knowledge, multi-agent coordination, and MCP integration β batteries included.
curl -fsSL https://raw.githubusercontent.com/elasticdotventures/_b00t_/main/install.sh | bash
Downloads the binary from GitHub Releases and verifies its SHA256 checksum when possible. Supports Linux x86_64/aarch64/armv7 and macOS Intel/Apple Silicon.
From crates.io:
cargo install b00t-cli
From source:
git clone https://github.com/elasticdotventures/_b00t_.git
cd _b00t_ && cargo install --path b00t-cli
b00t --version
b00t status # check tool versions vs desired
b00t cli check rust # is rustc installed?
b00t cli install uv # install/upgrade to desired version
b00t cli up # check all datums
b00t cli up --yes # update all tools to desired versions
b00t learn rust # load Rust dev context into agent session
b00t learn docker # container orchestration knowledge
b00t lfmf rust "PyO3: unset CONDA_PREFIX before cargo build to fix linker errors"
b00t advice rust "PyO3" # retrieve lessons for a tool+pattern
# Load b00t plugin from local checkout (Claude Code --plugin-dir)
claude --plugin-dir /path/to/_b00t_/.claude-plugin
# Or install the b00t MCP server directly and let it surface skills
b00t mcp install b00t-mcp claudecode # registers b00t-mcp in Claude Code
Provides /b00t skill, context-aware tool dispatch, and all available b00t skills.
Plugin manifest: .claude-plugin/plugin.json β deterministic MCP recipes at
.claude-plugin/recipes/{skills,mcp-servers}/*.json
(e.g. skills/document-understanding.json bundles docling-mcp + fetch tools).
π€
/plugin marketplace adddoes not exist in Claude Code CLI. Useclaude --plugin-dirfor local plugin loading, orb00t mcp installfor MCP-only.
b00t mcp install b00t claudecode # Claude Code
b00t mcp install b00t vscode # VS Code
b00t mcp list # list available MCP servers
50+ MCP tools exposed via b00t-mcp β b00t_up, b00t_status, b00t_learn, b00t_lfmf, b00t_advice, and more.
# Multi-agent mission coordination
b00t acp hive create mission-id 3 "Build and deploy microservice" leader
b00t acp hive join mission-id developer
b00t acp hive sync mission-id 1 # barrier: wait for all agents at step 1
b00t acp hive ready mission-id 2 # signal readiness for step 2
b00t.sh carries forward the useful Ralph/OODA loop lessons, but the standalone b00t-wiggums repo is sunset. The loop interface is now treated as a commodity execution surface, with higher-level research/orchestration living in b00t.sh and karpathy/autoresearch.
# Run with default claude tool, 10 iterations
bash b00t.sh
# Configure via env or flags
TOOL=mistralrs bash b00t.sh --max-iterations 5 --role executor
bash b00t.sh --tool codex --sleep 1
Tools: claude, codex, amp, opencode, mistralrs (local vLLM).
Loop exits on EXIT_SIGNAL=true in LLM output, or exit 75 (tempfail/restart) after max iterations.
Datums in _b00t_/ declare tools with detect/install/desires/hint. b00t resolves DAG-ordered installs:
b00t cli detect fastmcp # run datum detect script
b00t cli desires rust # show target version
b00t cli install fastmcp # install: python β uv β fastmcp (DAG-aware)
b00t session init --budget 25.00 --time-limit 120 --agent "code-reviewer"
b00t session status
b00t checkpoint "completed feature X"
| Platform | Architecture | Status |
|---|---|---|
| Linux | x86_64 | β |
| Linux | aarch64 | β |
| Linux | armv7 | β |
| macOS | Intel | β |
| macOS | Apple Silicon | β |
git clone https://github.com/elasticdotventures/_b00t_.git && cd _b00t_
cargo build
cargo test --workspace
just -l # available recipes
just release # dispatch GitHub release workflow
b00t /b00t skill for sending learn packets to nominated agents
Workflow orchestration, certainty-graded quality rules, and task pipelines for b00t agents
b00t plugin for Claude Code - extreme programming agent framework with datum system, direnv pattern, and DRY philosophy
Workflow orchestration, certainty-graded quality rules, and task pipelines for b00t agents
Multi-agent orchestration system with MCP tools and Claude Code plugin agents. 51 specialized agents for development workflows, code quality, deployment, research, and more.
Portable, vendor-agnostic agent harness for project-specific skills, workflows, and agent teams aligned with your codebase, conventions, and engineering standards.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Multi-agent orchestration framework for Claude Code. Routes tasks to specialized Haiku/Sonnet subagents while Opus orchestrates β inspired by speculative decoding. Includes 10 specialized heads, environment preflight checks, and ~50% API cost reduction.
High-intelligence Claude Code copilot with deep code reasoning, evidence-driven planning, orchestration-first execution, model routing, context budgeting, CI/CD integration, enterprise security, plugin development, prompt engineering, performance profiling, agent teams, channels (event-driven autonomy with CI webhook, mobile approval relay, Discord bridge, and fakechat dev profile), interactive tutorials, LSP integration, security-hardened hook script library, MCP Prompts coverage, common workflow packs, runtime selection guide, computer-use patterns, checkpointing, scheduled-task blueprints, repo bootstrap scanner, hook policy engine (8 installable packs), layered memory deployment, role-based subagent packs (implementer, debugger, migration-lead, dependency-auditor, release-coordinator), 5 agent-team topology kits, autonomy operating mode (4 profiles + 3 gates), and a queryable 15-tool MCP documentation server with autonomy advisor.