Aug 24, 2026
One company gateway, any coding harness
HarnezPad routes Claude Code, Codex, ChatGPT, and OpenCode through one company LLM gateway without putting the management key on disk.
claude-codeintermediate
Now · Aug 2026
Notes from the frontier of coding agents.
Practical notes on experiments, case studies, workflows, and techniques for using Claude, Codex, and similar coding agents effectively.
Articles
18 posts- Aug 24, 2026
Resume work across coding agents with a session handoff
A read-only adapter resolves Claude Code, Codex, or Cursor history as inert data, builds a minimal handoff, and verifies current repository state before continuation.
ai-skillsintermediate - Aug 22, 2026
Customize OpenCode v2 for enterprise without replacing the harness
How to restrict and extend stock OpenCode through a pinned v2 seam and a redistribution template: composition slots, managed policy, seeded plugins, and branded packaging.
architectureintermediate - Aug 10, 2026
Herdr is the runtime around the coding agent
How an agent-aware terminal multiplexer owns live panes, processes, and lifecycle, and how Agent Factory sits above it as a control plane rather than a second runtime.
agentsadvanced - Jul 21, 2026
ACP is a client protocol, not a control plane
What the Agent Client Protocol standardizes, what it leaves to the host, and how Coding Agent Control Plane composes project, environment, provider, model, and harness before any handshake.
architectureadvanced - Jul 7, 2026
How codex-action sandboxes Codex in GitHub Actions
How codex-action separates command permissions, host privileges, proxy key handling, actor authorization, and post-execution isolation on a GitHub runner.
automationadvanced - Jun 23, 2026
Codex hooks: enforce policy at lifecycle boundaries
Codex hooks run deterministic commands at 11 lifecycle events, with distinct contracts for tool policy, approval decisions, context injection, and completion gates.
codexadvanced - Jun 16, 2026
Agent skills: package task knowledge for coding agents
A SKILL.md file turns repeated operating instructions into discoverable, scoped task knowledge that Codex and Claude Code load on demand.
ai-skillsintermediate - Jun 9, 2026
Codex sandboxing: separate filesystem scope from approvals
Codex treats sandbox enforcement and approval policy as separate controls, and subagents inherit the active parent runtime before role defaults apply.
codexintermediate - May 12, 2026
Building a local viewer for Claude Code sessions
A local session viewer turns Claude Code JSONL logs into checkpoints, tool-call groups, token counts, and side-by-side comparisons.
claude-codeintermediate - May 11, 2026
Codex as a function in the incident loop
How Triage Copilot embeds the Codex SDK in a production incident SDLC: three parallel sub-agents, MCP-scoped context, Zod-validated output, and draft PRs that never auto-merge.
ci-cdadvanced - May 11, 2026
Lost in the middle: test context position, not just size
Long-context benchmarks show that relevant-information position can change accuracy, but the effect is task- and model-dependent rather than a universal attention curve.
attentionbasic - May 5, 2026
Fix broken project paths in Claude Code and Codex
A macOS migration script discovers stale project paths in four Claude Code and Codex sources, then updates the related local state with explicit safety limits.
automationintermediate - Apr 16, 2026
Treat the agent contract as versioned infrastructure
Production agent behavior comes from a versioned contract spanning instructions, tools, schemas, context assembly, model selection, and release gates.
claudeadvanced - Apr 6, 2026
Turn an OpenAPI spec into an agent-facing CLI
A spec-driven CLI gives coding agents a discoverable, executable API surface without hand-maintaining one command per endpoint.
api-explorationintermediate - Apr 5, 2026
Workflows vs. agents: a pragmatic decision framework
A reliability-first approach to choosing between predictable workflows and flexible agents, with four reusable patterns and concrete selection heuristics.
agentsintermediate - Apr 2, 2026
Inside the Agent SDK loop: how Claude Code runs your prompts
How Claude Code and the Agent SDK execute prompts through a five-step tool loop, expose typed lifecycle messages, and bound work with permissions, turns, and budgets.
agent-sdkintermediate - Mar 25, 2026
What a prompt lab actually validates
Three fixture-backed extraction lessons show how prompt contracts grow — and why an evaluation can only prove the fields its grader checks.
data-extractionintermediate