My agentic coding tools:

bkmr

Knowledge Management for Humans and Agents.

twmux

Race-condition-safe tmux wrapper giving LLM agents reliable shell I/O, a consistent JSON contract, and socket isolation.

twsrt

Translates one canonical set of security rules into agent-specific permission configs for Claude Code, Copilot CLI, and others — single source of truth, no drift.

twagent

Define your agents configuration canonically in TOML. Compile agent-specific artifacts for Claude Code, Copilot CLI, IntelliJ, and pi. No duplication. Handles instructions, skills, subagents and MCP configurations.

pi-extensions

Adds sandboxing, access control, and vim editing to the pi coding agent.

sandbox-runtime-improved

Lightweight OS-level sandboxing for filesystem and network restrictions on arbitrary processes — no container required.

• Giving everyone a LLM no more replaces engineers, than giving everyone a saw replaces carpenters.

• The AI-native developer is not the engineer who ships the most with a model. It is the engineer whose system still tells the truth about itself after the model has been working on it for six months.

• The danger is not that agents are wrong. The danger is that they are right often enough, along the visible spikes, that we stop verifying the gaps.

• Help agents move us into higher level of abstractions? Beware, a higher level of ambiguity is not a higher level of abstraction.

• If you outsource thinking to LLMs, you stop upskilling, learning, and becoming competent.

Agent’s Playbook:

• Specs constrain intent.
• Plans constrain approach.
• Tasks constrain sequencing.
• Tests, schemas, linter constrain behavior.
• Harnesses constrain execution.