Blog

Stories, insights, and lessons learned from building and using ctx.

Releases¶

ctx v0.8.0: The Architecture Release ¶

March 23, 2026: 374 commits, 1,708 Go files touched, and a near-complete architectural overhaul. Every CLI package restructured into cmd/ + core/ taxonomy, all user-facing strings externalized to YAML, MCP server for tool-agnostic AI integration, and the memory bridge connecting Claude Code's auto-memory to .context/.

Topics: release, architecture, refactoring, MCP, localization

Field Notes¶

Code Structure as an Agent Interface: What 19 AST Tests Taught Us ¶

April 2, 2026: We built 19 AST-based audit tests in a single session, touching 300+ files. In the process we discovered that "old-school" code quality constraints (no magic numbers, centralized error handling, 80-char lines, documentation) are exactly the constraints that make code readable to AI agents. If an agent interacts with your codebase, your codebase already is an interface. You just have not designed it as one.

Topics: ast, code quality, agent readability, conventions, field notes

We Broke the 3:1 Rule ¶

March 23, 2026: After v0.6.0, we ran 198 feature commits across 17 days before consolidating. The 3:1 rule says consolidate every 4^th session. We did it after the 66^th. The result: an 18-day, 181-commit cleanup marathon that took longer than the feature run itself. A follow-up to The 3:1 Ratio with empirical evidence from the v0.8.0 cycle.

Topics: consolidation, technical debt, development workflow, convention drift, field notes

Context Engineering¶

Agent Memory Is Infrastructure ¶

March 4, 2026: Every AI coding agent starts fresh. The obvious fix is "memory." But there's a different problem memory doesn't touch: the project itself accumulates knowledge that has nothing to do with any single session. This post argues that agent memory is L2 (runtime cache); what's missing is L3 (project infrastructure).

Topics: context engineering, agent memory, infrastructure, persistence, team knowledge

Context as Infrastructure ¶

February 17, 2026: Where does your AI's knowledge live between sessions? If the answer is "in a prompt I paste at the start," you are treating context as a consumable. This post argues for treating it as infrastructure instead: persistent files, separation of concerns, two-tier storage, progressive disclosure, and the filesystem as the most mature interface available.

Topics: context engineering, infrastructure, progressive disclosure, persistence, design philosophy

The Attention Budget: Why Your AI Forgets What You Just Told It ¶

February 3, 2026: Every token you send to an AI consumes a finite resource: the attention budget. Understanding this constraint shaped every design decision in ctx: hierarchical file structure, explicit budgets, progressive disclosure, and filesystem-as-index.

Topics: attention mechanics, context engineering, progressive disclosure, ctx primitives, token budgets

Before Context Windows, We Had Bouncers ¶

February 14, 2026: IRC is stateless. You disconnect, you vanish. Modern systems are not much different. This post traces the line from IRC bouncers to context engineering: stateless protocols require stateful wrappers, volatile interfaces require durable memory.

Topics: context engineering, infrastructure, IRC, persistence, state continuity

The Last Question ¶

February 28, 2026: In 1956, Asimov wrote a story about a question that spans the entire future of the universe. A reading of "The Last Question" through the lens of persistence, substrate migration, and what it means to build systems where sessions don't reset.

Topics: context continuity, long-lived systems, persistence, intelligence over time, field notes

Agent Behavior and Design¶

The Dog Ate My Homework: Teaching AI Agents to Read Before They Write ¶

February 25, 2026: You wrote the playbook. The agent skipped all of it. Five sessions, five failure modes, and the discovery that observable compliance beats perfect compliance.

Topics: hooks, agent behavior, context engineering, behavioral design, testing methodology, compliance monitoring

Skills That Fight the Platform ¶

February 4, 2026: When custom skills conflict with system prompt defaults, the AI has to reconcile contradictory instructions. Five conflict patterns discovered while building ctx.

Topics: context engineering, skill design, system prompts, antipatterns, AI safety primitives

The Anatomy of a Skill That Works ¶

February 7, 2026: I had 20 skills. Most were well-intentioned stubs. Then I rewrote all of them. Seven lessons emerged: quality gates prevent premature execution, negative triggers are load-bearing, examples set boundaries better than rules.

Topics: skill design, context engineering, quality gates, E/A/R framework, practical patterns

You Can't Import Expertise ¶

February 5, 2026: I found a well-crafted consolidation skill. Applied my own E/A/R framework: 70% was noise. This post is about why good skills can't be copy-pasted, and how to grow them from your project's own drift history.

Topics: skill adaptation, E/A/R framework, convention drift, consolidation, project-specific expertise

Not Everything Is a Skill ¶

February 8, 2026: I ran an 8-agent codebase audit and got actionable results. The natural instinct was to wrap the prompt as a skill. Then I applied my own criteria: it failed all three tests.

Topics: skill design, context engineering, automation discipline, recipes, agent teams

Defense in Depth: Securing AI Agents ¶

February 9, 2026: The security advice was "use CONSTITUTION.md for guardrails." That is wishful thinking. Five defense layers for unattended AI agents, each with a bypass, and why the strength is in the combination.

Topics: agent security, defense in depth, prompt injection, autonomous loops, container isolation

Development Practice¶

Code Is Cheap. Judgment Is Not.¶

February 17, 2026: AI does not replace workers. It replaces unstructured effort. Three weeks of building ctx with an AI agent proved it: YOLO mode showed production is cheap, the 3:1 ratio showed judgment has a cadence.

Topics: AI and expertise, context engineering, judgment vs production, human-AI collaboration, automation discipline

The 3:1 Ratio ¶

February 17, 2026: AI makes technical debt worse: not because it writes bad code, but because it writes code so fast that drift accumulates before you notice. Three feature sessions, one consolidation session.

Topics: consolidation, technical debt, development workflow, convention drift, code quality

Refactoring with Intent: Human-Guided Sessions in AI Development ¶

February 1, 2026: The YOLO mode shipped 14 commands in a week. But technical debt doesn't send invoices. This is the story of what happened when we started guiding the AI with intent.

Topics: refactoring, code quality, documentation standards, module decomposition, YOLO versus intentional development

How Deep Is Too Deep?¶

February 12, 2026: I kept feeling like I should go deeper into ML theory. Then I spent a week debugging an agent failure that had nothing to do with model architecture. When depth compounds and when it doesn't.

Topics: AI foundations, abstraction boundaries, agentic systems, context engineering, failure modes

Agent Workflows¶

Parallel Agents, Merge Debt, and the Myth of Overnight Progress ¶

February 17, 2026: You discover agents can run in parallel. So you open ten terminals. It is not progress: it is merge debt being manufactured in real time. The five-agent ceiling and why role separation beats file locking.

Topics: agent workflows, parallelism, verification, context engineering, engineering practice

Parallel Agents with Git Worktrees ¶

February 14, 2026: I had 30 open tasks that didn't touch the same files. Using git worktrees to partition a backlog by file overlap, run 3-4 agents simultaneously, and merge the results.

Topics: agent teams, parallelism, git worktrees, context engineering, task management

Field Notes and Signals¶

When a System Starts Explaining Itself ¶

February 17, 2026: Every new substrate begins as a private advantage. Reality begins when other people start describing it in their own language. "Better than Adderall" is not praise; it is a diagnostic.

Topics: field notes, adoption signals, infrastructure vs tools, context engineering, substrates

Why Zensical ¶

February 15, 2026: I needed a static site generator for the journal system. The instinct was Hugo. But instinct is not analysis. Why zensical was the right choice: thin dependencies, MkDocs-compatible config, and zero lock-in.

Topics: tooling, static site generators, journal system, infrastructure decisions, context engineering

Blog

Releases¶

ctx v0.8.0: The Architecture Release ¶

Field Notes¶

Code Structure as an Agent Interface: What 19 AST Tests Taught Us ¶

We Broke the 3:1 Rule ¶

Context Engineering¶

Agent Memory Is Infrastructure ¶

Context as Infrastructure ¶

The Attention Budget: Why Your AI Forgets What You Just Told It ¶

Before Context Windows, We Had Bouncers ¶

The Last Question ¶

Agent Behavior and Design¶

The Dog Ate My Homework: Teaching AI Agents to Read Before They Write ¶

Skills That Fight the Platform ¶

The Anatomy of a Skill That Works ¶

You Can't Import Expertise ¶

Not Everything Is a Skill ¶

Defense in Depth: Securing AI Agents ¶

Development Practice¶

Code Is Cheap. Judgment Is Not.¶

The 3:1 Ratio ¶

Refactoring with Intent: Human-Guided Sessions in AI Development ¶

How Deep Is Too Deep?¶

Agent Workflows¶

Parallel Agents, Merge Debt, and the Myth of Overnight Progress ¶

Parallel Agents with Git Worktrees ¶

Field Notes and Signals¶

When a System Starts Explaining Itself ¶

Why Zensical ¶

Releases¶

ctx v0.6.0: The Integration Release ¶

ctx v0.3.0: The Discipline Release ¶

ctx v0.2.0: The Archaeology Release ¶

Building ctx Using ctx: A Meta-Experiment in AI-Assisted Development ¶