Articles
Writing on context leadership
Resolute for the company, C² for the codebase, and essays on leading when half the crew is AI. 79 articles in C² Method.
- C² MethodNov 20, 2026 · 6 min readAGENTS.md vs CLAUDE.md: what Claude Code actually loads (tested)AGENTS.md vs CLAUDE.md, tested in Claude Code 2.1.329: which file loads when both exist, how @AGENTS.md imports work, and the CLAUDE.local.md trap.
- C² MethodNov 20, 2026 · 7 min readClaude Code compaction ate my work: recovery and preventionClaude Code compaction lost context mid-task? Nothing on disk is gone. How to recover from git, your briefs and the session transcript, and how to prevent it.
- C² MethodNov 20, 2026 · 8 min readClaude Code hooks I actually run, and the one I turned offClaude Code hooks examples from a real repo: a SessionStart brief list, a SessionEnd worktree prune, a PostToolUse reminder, and the block I turned off.
- C² MethodNov 20, 2026 · 8 min readHow to rescue a vibe-coded app without rewriting itHow to fix a vibe coded app without a rewrite: freeze features, map it, add a router and contextbase, pin behaviour with tests, fix in small briefs.
- C² MethodNov 20, 2026 · 9 min readHow to write a prompt brief an agent can run without youHow to write instructions for an AI coding agent that runs unattended: standing approval, pre-flight reads, one item at a time, exact commands, and a real DoD.
- C² MethodNov 20, 2026 · 8 min readWhat goes in a session brief: a template and three real briefsA Claude Code session handoff template, section by section, with three real session briefs from my repos and what each part bought the next session.
- C² MethodNov 20, 2026 · 8 min readTask Master vs BMAD vs Agent OS: which fits your repo?Task Master vs BMAD vs Agent OS: what each is, how it installs, what files it adds to your repo, licences, and who each suits. Checked on their own docs.
- C² MethodNov 20, 2026 · 8 min readThe gotchas folder: the cheapest context your agent readsHow to stop an AI agent repeating mistakes: a gotchas folder of one-file traps, how to name and write them, when to add one, and how the router points at them.
- C² MethodNov 18, 2026 · 3 min readHow to customise the C² Method for your team and projectC²'s folders are a starting shape, not a rulebook. What's load-bearing, how to adapt the rest to your team, and a worked example: adding a metrics folder.
- C² MethodNov 18, 2026 · 7 min readHow to stop Claude Code losing context between sessionsClaude Code loses context when a session ends or compacts. What CLAUDE.md and auto memory keep, and the session-brief routine that carries the rest in git.
- C² MethodNov 18, 2026 · 9 min readSpec-driven development tools compared (2026)Spec Kit, Kiro, BMAD, Agent OS, Task Master and OpenSpec compared from their own docs: artefacts, workflow, agents, licence and who each one is for.
- C² MethodNov 18, 2026 · 7 min readWhy Claude Code ignores your CLAUDE.md, and how to fix itClaude Code ignores CLAUDE.md rules when the file is too long, the rule is buried, or it needed a hook. Why it happens, and the router pattern that fixes it.
- C² MethodAug 28, 2026 · 4 min readThe repo you hand over is a deliverable from day oneA client repo is a deliverable from its first commit. The rule I keep for what context may compound there, and the near-miss that taught it.
- C² MethodAug 3, 2026 · 6 min readClosing the flight plan: the gate nobody runsFlight Planning spends context. Closing is where context gets made. The landing gate, its four parts, and why it scales from a room to one person.
- C² MethodAug 3, 2026 · 5 min readDon't draw the graph on day oneDiagramming a big agent workflow before you have watched the work behave produces brittle structure. Why your contextbase is already the trace collection.
- C² MethodAug 3, 2026 · 5 min readDon't loop on confidence. Loop on evidence.A system of agents checking each other's reports is consistent and unverified. Anchors, frozen rules, and what makes a result actually count as done.
- C² MethodAug 3, 2026 · 5 min readThe pilot's bottleneck changesThe Pilot model was never static. Attention, then review throughput, then trust in the loop, then knowing what to automate. Four stages, four questions.
- C² MethodAug 3, 2026 · 5 min readThe prompt brief is a node contractA fan-out returns twelve confident, unusable outputs unless every agent has a contract. What that contract specifies — and why the prompt brief already is one.
- C² MethodAug 3, 2026 · 5 min readThe shape of the work is a graph, not a queueWork has a shape, and the shape is a graph. Nodes, edges and barriers in plain terms — and why your prompt briefs were always a fan-out.
- C² MethodAug 3, 2026 · 5 min readThe two ladders of AI adoptionRisk of the work and agent count are orthogonal axes, and confusing them is why adoption advice keeps missing. The 2x2, and how to find where you sit.
- C² MethodAug 3, 2026 · 7 min readWhen can AI agents actually run in parallel?Multi-agent vs single agent, decided by two questions: is there an edge, and is there a shared surface? When to fan out, sequence, or stay with one.
- C² MethodAug 3, 2026 · 5 min readWhich layer broke your agent? Environment, loop, topologyAt the 30-minute limit, name the layer that owns the failure before you escalate: the environment, the loop and its stop rule, or the topology.
- C² MethodAug 3, 2026 · 4 min readYour agent fleet forgets everythingA fleet fans out, converges, prints an answer, and the shape that produced it evaporates. A field note on what makes an expensive run worth doing twice.
- C² MethodJun 26, 2026 · 8 min readFlight Planning: file the plan before you take offFlight Planning is the C² review where you file your plan — scope, briefs, and ETA — before an agent builds. What it is, who's in the room, and why.
- C² MethodJun 9, 2026 · 5 min readC² vs enterprise AI coding platformsEnterprise platforms sell governance, SSO and control for AI coding. C² gives you a method and context you own. What each is for, and where they meet.
- C² MethodJun 9, 2026 · 5 min readContext files vs fine-tuning for your codebaseWant an agent that knows your codebase? You could fine-tune a model or write context files. Why context wins for most teams — cheaper, faster, and yours.
- C² MethodJun 9, 2026 · 4 min readCrawl, walk, run: adopting AI agents safelyTeams that jump straight to autonomous agents fail. The crawl-walk-run path that gets AI agents from first try to production work — without the wreckage.
- C² MethodJun 9, 2026 · 5 min readDefend against prompt injection in coding agentsPrompt injection turns content your agent reads into commands it follows. Why coding agents are exposed, the real incidents, and the defences that hold.
- C² MethodJun 9, 2026 · 5 min readDocument an inherited codebase with an agentInherited a codebase with no docs? How to have an agent draft the documentation, verify it, and grow a contextbase into a legacy project one change at a time.
- C² MethodJun 9, 2026 · 5 min readGreenfield vs brownfield: building with agentsStarting fresh and working in a legacy codebase are different sports with AI agents. What changes, why brownfield is harder, and how to handle each.
- C² MethodJun 9, 2026 · 5 min readLeast privilege for coding agents: scope the blast radiusAn agent can only do damage where you let it reach. How to apply least privilege to coding agents — file scope, command limits, no prod, sandboxes.
- C² MethodJun 9, 2026 · 5 min readOnboard to any codebase in hours with an agentUnderstanding an unfamiliar codebase used to take weeks. An agent can guide you through it in hours — here's how to use one to get oriented fast.
- C² MethodJun 9, 2026 · 3 min readOnboarding a new dev with the contextbaseA field note on a new developer who got productive in a day instead of a fortnight, because the contextbase already held what usually lives in people's heads.
- C² MethodJun 9, 2026 · 5 min readPRD-first vs prototype-first with AIShould an agent write the spec or build the prototype first? The case for each, when a clickable prototype beats a document, and how C² uses both.
- C² MethodJun 9, 2026 · 3 min readRolling C² out to my team: what stuck, what didn'tA field note on introducing C² to a team — the parts that caught on immediately, the parts that met resistance, and what I'd do differently.
- C² MethodJun 9, 2026 · 5 min readKeep secrets safe when coding with agentsAn agent with shell access and secrets in scope is the worst-case setup. How to keep API keys and credentials out of an agent's reach — and out of its context.
- C² MethodJun 9, 2026 · 5 min readThe Cascade: from PRD to Prompt BriefBig goals don't fit in one prompt. The C² Cascade breaks work from Platform PRD down to the Prompt Brief an agent can actually build. How the tiers fit.
- C² MethodJun 9, 2026 · 3 min readThe legacy codebase the agent couldn't readA field note on pointing an agent at a ten-year-old codebase, watching it confidently misunderstand everything, and the context that finally let it help.
- C² MethodJun 9, 2026 · 3 min readThe prompt injection I almost shippedA field note on an agent that read a malicious instruction buried in a dependency's docs, nearly acted on it, and what caught it before it shipped.
- C² MethodJun 9, 2026 · 3 min readThe secret that leaked into contextA field note on an API key that ended up in an agent's context window, where it didn't belong, and the rule I keep now to stop it happening again.
- C² MethodJun 9, 2026 · 5 min readWhat is a PRD, and why agents need oneA PRD (product requirements document) says what to build and why. Why AI agents need one more than human teams, what goes in it, and how to draft one.
- C² MethodJun 9, 2026 · 5 min readWhy most AI agent pilots never reach productionMost AI agent pilots never ship — and it's rarely the agent's fault. The real blockers are governance, context and trust, and how to clear them.
- C² MethodJun 8, 2026 · 5 min readWrite acceptance criteria your agent can check itselfThe difference between an agent that drifts and one that self-verifies is acceptance criteria you can run. How to write briefs with criteria the agent checks itself.
- C² MethodJun 8, 2026 · 5 min readAgentic coding vs AI pair programmingPair programming has the AI beside you, suggesting. Agentic coding has it running the loop while you direct. The difference, and which one you're doing.
- C² MethodJun 8, 2026 · 5 min readAI agent teams, explained: lead, bench, specialistWhen one agent isn't enough you reach for a team — but more agents on one problem makes things worse, not better. The roles that actually work, and why.
- C² MethodJun 8, 2026 · 5 min readSet up AI code review with a bench agentAn independent agent reviewing the work — not the one that wrote it — catches what the author misses. How to run a bench-agent review that adds signal.
- C² MethodJun 8, 2026 · 5 min readC² vs AWS AI-DLC: pilot versus approver at the gateAWS AI-DLC and C² are the closest AI-native peers. The two telling differences: human as approver-at-gates vs pilot, and context as delivery vs investment.
- C² MethodJun 8, 2026 · 5 min readC² vs GUARDRAILS.md: safety that compoundsGUARDRAILS.md captures safety lessons so an autonomous agent stops repeating failures. A useful file — and how it relates to a contextbase that compounds.
- C² MethodJun 8, 2026 · 5 min readC² vs native rule files: when one CLAUDE.md isn't enoughCLAUDE.md, AGENTS.md and cursorrules are where everyone starts. An honest look at what a single rules file does well, where it breaks, and how C² extends it.
- C² MethodJun 8, 2026 · 5 min readC² vs spec-driven development: specs that persistSpec-driven development makes an executable spec the source of truth. C² agrees — and adds the part SDD leaves out: a contextbase that compounds across every spec.
- C² MethodJun 8, 2026 · 5 min readContext rot: how compaction keeps your agent sharpContext rot: every model degrades as its window fills. What it looks like, how I diagnosed it, and the compaction habits that keep the context lean.
- C² MethodJun 8, 2026 · 5 min readContext engineering, explained: the skill that replaced promptingContext engineering is the discipline that overtook prompt engineering: curating what your AI agent knows before it acts. What it is, why it matters, and how to start.
- C² MethodJun 8, 2026 · 5 min readContext engineering for people who aren't engineers yetContext engineering is the skill of writing down what your AI agent needs to know so it acts well. A plain-English guide for builders from business, not CS.
- C² MethodJun 8, 2026 · 5 min readContext engineering vs RAG for coding agentsRAG retrieves context on the fly; context engineering curates and keeps it. How they differ for coding agents, where each fits, and why a contextbase isn't RAG.
- C² MethodJun 8, 2026 · 5 min readCursor vs Claude Code: why C² works with eitherCursor or Claude Code or Codex — the tool debate misses the point. Why an agent-agnostic method means you can pick any, and switch without losing context.
- C² MethodJun 8, 2026 · 5 min readHow to build software with AI agents: a starting guideA plain-English guide to building real software with AI coding agents — the loop, the context, and the habits that separate shipping from vibe-coding into a mess.
- C² MethodJun 8, 2026 · 9 min readHow to stop your AI agent forgetting what it learnedAI agents forget when the session ends or the window fills, and the model never learns your project. The written-context fix that makes learning stick.
- C² MethodJun 8, 2026 · 5 min readHow to write an AGENTS.md that agents actually followAGENTS.md (and CLAUDE.md) is the file your coding agent reads first. What belongs in it, a worked example line by line, and how to keep it lean.
- C² MethodJun 8, 2026 · 3 min readI ran five agents at once and regretted itA field note on spinning up five agents on one feature to go faster, the contradictory mess that followed, and what I got wrong for a year about why it failed.
- C² MethodJun 8, 2026 · 8 min readParallel Claude Code agents with git worktreesRun parallel Claude Code agents in git worktrees: isolation, sequential merges, and the disk, cleanup and CI-minute costs that arrive once you do it for real.
- C² MethodJun 8, 2026 · 6 min readPrompt engineering vs context engineering for codingPrompt engineering tunes the instruction. Context engineering curates what the agent knows. Why the second is the skill that now pays — and how C² operationalises it.
- C² MethodJun 8, 2026 · 3 min readHow to run AI coding agents overnight, safelyUnattended agents can ship real work while you sleep — or wreck things. The guardrails that make overnight runs safe: branches, scopes, cost caps, no prod.
- C² MethodJun 8, 2026 · 5 min readSubagents, MCP and skills: fitting tools into C²Subagents, MCP servers, slash commands, skills — the agent harness has a lot of tools. How they fit a C² contextbase, and which to reach for without losing the plot.
- C² MethodJun 8, 2026 · 5 min readTest-driven development with AI agentsTDD turns an agent from hopeful to reliable: write the test first, let the agent go red-green-refactor at machine speed. How to run it, and what it needs.
- C² MethodJun 8, 2026 · 4 min readThe 30-minute debug limit: when to stop the agentAn agent stuck on a bug will burn an hour going in circles. The pilot's move is a time limit and an escalation — here's how to set and use one.
- C² MethodJun 8, 2026 · 3 min readThe CLAUDE.md that got too bigA short field note: my Router file bloated into an unreadable wall of rules. How I noticed, what I moved where, and the line-count rule I now keep.
- C² MethodJun 8, 2026 · 3 min readThe overnight run that went wrongA field note on letting an agent run unattended overnight, waking to a branch full of confident damage, and the guardrails I never skip now.
- C² MethodJun 8, 2026 · 5 min readThe Pilot model: directing agents instead of typingThe biggest shift in building with AI isn't the code the agent writes — it's that you stop being crew and start being the pilot. What that changes, in practice.
- C² MethodJun 8, 2026 · 3 min readThe test that saved the refactorA field note on a big agent-driven refactor that should have broken everything, and the test suite that turned a risky change into a boring one.
- C² MethodJun 8, 2026 · 3 min readI vibe-coded into a corner — here's the climb outA field note on letting an agent vibe-code a feature with no spec, the mess that followed, and how a brief with acceptance criteria turned it around.
- C² MethodJun 8, 2026 · 6 min readWhat is a contextbase? The asset that makes agents rememberA contextbase is the version-controlled folder of markdown your AI coding agent reads before it acts. What goes in it, why it compounds, and how to start one today.
- C² MethodJun 8, 2026 · 5 min readWhat is agentic coding? Beyond autocompleteAgentic coding is the shift from AI autocomplete to an agent that plans, edits, runs and verifies in a loop. What it is, how it differs, and how to start.
- C² MethodJun 8, 2026 · 5 min readWhat is an agent harness? Agent = model + harnessAn AI agent is the model plus the harness around it — the tools, memory, and the gather-act-verify loop that make it act. What a harness is, and where C² fits.
- C² MethodJun 8, 2026 · 6 min readWhy AI agents get expensive (and how to fix it)Agentic tasks burn far more tokens than chat, mostly from re-sending context. Why the bill climbs, and how lean context and model routing bring it down.
- C² MethodJun 8, 2026 · 3 min readWrite your first session briefA session brief is a short note at the end of each working session: what changed, why, what's verified, what's next. How to write one and why it compounds.
- C² MethodJun 1, 2026 · 5 min readAI development methodologies compared: C², BMAD & moreAn honest comparison of the methods for building with AI agents — native rule files, BMAD, ACE, Shape Up, AWS AI-DLC and C² — with a side-by-side table and how to choose.
- C² MethodJun 1, 2026 · 6 min readAn alternative to Agile for AI-native teamsAgile coordinated humans at human speed. With AI agents in the loop the bottleneck moves from execution to direction, and the ceremonies become drag.
- C² MethodMay 31, 2026 · 3 min readC² vs BMAD: two ways to build with AI agentsBMAD and C² both bring discipline to building with AI agents — BMAD runs personas through a heavier SDLC, C² centres on a contextbase you own that compounds.
- C² MethodMay 29, 2026 · 3 min readC² vs Shape Up: from human teams to human + AI teamsShape Up gave product teams appetite-based betting and an escape from sprint theatre. C² keeps those instincts and adds what AI needs — a contextbase that compounds.
Subscribe
One real leadership decision in the news, connected to the framework. Weekly. Fifteen minutes. Free.