babysitter-codex

Orchestrate complex, multi-step AI workflows with quality convergence loops, event-sourced state, and human-in-the-loop approval gates. Use when the user wants to babysit a task, orchestrate a workflow, run quality-gated development, resume a previous orchestration run, diagnose run health, plan without executing, set up a project or user profile for babysitter, or assimilate an external methodology. Also use when the user mentions "babysitter", "orchestrate", "babysit", "quality loop", or "convergence loop".

Help and documentation for babysitter commands, processes, skills, agents, and methodologies.

Plan a babysitter workflow without executing it. Focus on creating the best process possible.

Install or refresh a team-pinned babysitter runtime/content setup from lockfile.

Start a babysitter orchestration run. Use this command to start babysitting a complex workflow.

Analyze a completed or in-flight run and propose process improvements for future runs.

Drive feature development using Outside-In TDD with Hexagonal Architecture. Design emerges through inline code, in-memory fakes, interface extraction, and deferred I/O. Use when building features, writing tests, or structuring backend services. Triggers on: TDD, outside-in, hexagonal, ports and adapters, emergent design, acceptance test, component test, walking skeleton, in-memory fakes, component, contract test, adapter, fast tests, sub-second feedback. Language-agnostic (Go, Rust, Python, TypeScript, Java, C#).

Formal verification using Certora Prover with CVL specification language. Supports invariant rules, parametric verification, ghost variables, and counterexample analysis for mathematical proof of contract correctness.

On-chain analysis and transaction forensics for blockchain security investigations. Provides capabilities for tracing fund flows, identifying suspicious patterns, MEV analysis, and generating forensic reports for incident response.

Cross-chain bridge and multi-chain development expertise. Supports LayerZero, Chainlink CCIP, Wormhole, and Axelar for omnichain messaging, token bridging, and cross-chain state verification.

Implementation and secure usage of cryptographic primitives including ECDSA, BLS, Schnorr signatures, key derivation, secret sharing, and constant-time operations. Provides guidance for secure cryptographic implementations in blockchain applications.

Integration expertise for major DeFi protocols including Uniswap, Aave, Compound, Chainlink, Curve, and Balancer. Supports swaps, liquidity provision, lending, borrowing, oracles, and flash loans.

Property-based testing and fuzzing using Echidna for smart contracts. Includes invariant definition, corpus management, coverage analysis, and CI/CD integration for comprehensive security testing.

Deep EVM bytecode analysis and decompilation capabilities for smart contract security, gas optimization, and reverse engineering. Provides tools for analyzing opcodes, storage layouts, proxy patterns, and bytecode verification.

Expert usage of Foundry (Forge, Cast, Anvil, Chisel) for smart contract development, testing, and deployment. Includes fuzzing, gas reporting, local development, and deployment scripting capabilities.

Advanced gas optimization techniques for EVM smart contracts. Covers storage packing, memory vs calldata optimization, assembly/Yul, efficient data structures, batch operations, and benchmark-driven optimization strategies.

Expert usage of Hardhat for smart contract development, testing, and deployment. Includes TypeChain generation, plugin ecosystem, network forking, and deployment management.

Symbolic execution analysis using Mythril for deep vulnerability detection in smart contracts. Supports configurable transaction depth, timeout settings, and proof-of-concept exploit generation.

Expert usage of OpenZeppelin Contracts library for secure smart contract development. Covers access control, token standards, governance, upgrades, and security utilities.

Expert integration with Slither static analyzer for smart contract vulnerability detection, code quality analysis, and security reporting. Supports all Slither detectors and custom analysis configurations.

Deep expertise in Solidity language features, patterns, and best practices for secure smart contract development. Covers ERC standards, gas optimization, upgradeable contracts, and security patterns.

Subgraph development for The Graph protocol. Includes manifest configuration, GraphQL schema design, AssemblyScript handlers, entity relationships, and deployment to hosted and decentralized networks.

Token economics simulation and analysis. Supports supply modeling, staking mechanisms, liquidity mining, governance dynamics, agent-based simulations, and cadCAD integration.

Wallet connection and transaction management for dApps using wagmi and viem. Supports multiple connectors, chain switching, EIP-712 signing, and hardware wallet integration.

Zero-knowledge circuit development using Circom and Noir languages. Supports constraint optimization, ZK-friendly cryptographic primitives, proof generation (Groth16, PLONK), and Merkle tree implementations.

Generates DrawIO XML diagrams for Amazon Web Services architectures from text descriptions or images. Analyzes existing .drawio files to extract AWS components. Use for AWS architecture diagrams, cloud infrastructure documentation, or when converting AWS diagram images to editable DrawIO format.

Generates DrawIO XML diagrams for Google Cloud Platform architectures from text descriptions or images. Analyzes existing .drawio files to extract GCP components. Use for GCP architecture diagrams, cloud infrastructure documentation, or when converting GCP diagram images to editable DrawIO format.

Ad mediation skill for rewarded video.

Mobile GPU optimization skill for thermal management.

Generate SKILL.md files with proper YAML frontmatter, capabilities documentation, and usage examples following Babysitter SDK conventions.

Integration with hosted documentation platforms GitBook and Notion. Manage spaces, synchronize content with Git, export/import between formats, configure webhooks, and retrieve analytics.

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)

Start a babysitter workflow from a GitHub issue.

Set or view model routing policy for plan/execute/review phases.

Resume orchestrating an existing babysitter run.

Start babysitting in non-interactive mode — no user interaction or breakpoints, fully autonomous execution.

Assimilate an external methodology, harness, or specification into babysitter process definitions.

Diagnose babysitter run health — journal integrity, state cache, effects, locks, sessions, logs, and disk usage.

Start a never-ending babysitter run with infinite loops and sleep gates.

Launch the babysitter observer dashboard for real-time run monitoring.