AI enablement, governance, and scalability based upon agentic engineering principles: getting AI from prototype to production with self-enforced guardrails, fully compliant audit trails, and deterministic workflow automation that is replicable and repeatable at scale.
| Repository | What it is | What it shows |
|---|---|---|
| frontier-operating-manual | An operating discipline for AI coding agents, shipped as a Claude Code skill: standing rules with failure conditions, risk tiers, calibration labels, a written pre-send self-test | Governance as a runnable harness |
| ai-knowledge-repository | A validated knowledge graph of hard platform constraints and decision-enabling capabilities for Claude Code, Lovable, Git, reMarkable, n8n, Python and Atlassian, with a contract validator | Knowledge management built for decision time, with receipts |
| claude-code-swarm-kit | A model-tiered multi-agent research kit: pinned roster, five-stage workflow, spawn doctrine, PreToolUse gates and linters | Cost governance as code, root-cause work, honest verification records |
| reasoning-bundle | A Claude Code plugin of structured-reasoning skills, opt-in calibration and convergence hooks, and a graph-of-thought tournament, with zero data egress | Packaging discipline as a distributable, adversarially reviewed artifact |
| remarkable-agent-push | A security-audited, hardened build of a CLI that lets an AI agent push markdown to a reMarkable tablet as a native notebook | Source-level security audit, fail-closed fixes, a rebuilt release pipeline |
Every repository above was produced under the same discipline: the ask restated and counted, load-bearing claims labeled by how they are known, verification by an independent path, an adversarial pass before shipping, and a written record of what was and was not executed and their respective decision trees. The manual is the runbook; the work is the PoC.