Claude Code workflow mastery for .NET developers. Covers parallel execution with git worktrees, plan mode strategy, verification loops, auto-formatting hooks, permission setup for dotnet CLI, prompting techniques, subagent patterns, and context discipline — token budget management, MCP-first navigat

Workflow Mastery for .NET Core Principles 1. Parallel over sequential — Run 3 5 Claude sessions simultaneously using git worktrees. Build a feature in one, fix a bug in another, run tests in a third. The single biggest productivity unlock. 2. Plan then execute — For any non trivial task, start in plan mode, iterate until the plan is bulletproof, then switch to auto accept. A good plan means Claude 1 shots the implementation. 3. Verification closes the loop — Give Claude a way to prove its work: dotnet build , dotnet test , get diagnostics via MCP. This single practice 2 3x the quality of the output. 4. Context is a budget, not a dumping ground — The context window fills fast: a typical .cs file is 500 2000 tokens, and 50 file reads can burn a large share of the budget. Spend tokens like sprint capacity — deliberately. 5. Automate the repetitive — If you do it more than once a day, make it a hook, a slash command, or a subagent. Pre allow safe permissions. Eliminate friction. 6. Compound your knowledge — Every correction becomes a rule in MEMORY.md (see instinct system skill). Every PR review adds a learning. Over time, Claude's mistake rate drops because your project's knowledge base grows. Patterns Parallel Sessions with Git Worktrees The biggest productivity multiplier. Each worktree gets its own Claude session, its own files, zero conflicts. Practical .NET workflow: Worktree Task Claude Session feature Build new endpoint + handler Main development bugfix Fix the failing CI test Autonomous bug fix tests Write integration tests for existing feature Test generation analysis Query the Roslyn MCP, read logs, review architecture Read only research Tips: Name your terminal tabs by task so you never lose track Use shell aliases ( alias zf='cd ../my project feature' ) for one keystroke switching Enable terminal notifications so you know when a session needs input Auto Format Hook for .NET Catch formatting issues on every file write — eliminates the "CI failed on formatting" loop. Why true : The hook should never block Claude's workflow. If formatting fails (e.g., on a non C file), silently continue. Pre Allow Safe .NET Permissions Stop clicking "allow" for every dotnet command. Add these to .claude/settings.json : Check this into git so the whole team gets frictionless workflows. Plan Mode Strategy For any task touching 3+ files or involving architecture decisions: Advanced pattern: Have one Claude write the plan, then spin up a second Claude session to review it as a staff engineer: When things go sideways: The moment implementation deviates from the plan, STOP. Don't push through. Switch back to plan mode, understand what changed, re plan, then resume. Verification Loop for .NET For the full 7 phase verification pipeline (build, diagnostics, anti patterns, tests, security, format, diff review) with structured PASS/FAIL reporting, see the verify skill. Boris's 1 tip: "Give Claude a way to verify its work." The short version: always tell Claude to run dotnet build , dotnet test , get diagnostics , and dotnet format verify no changes before declaring done. The verify skill has the complete pipeline with short circuit rules and report templates. Compounding Knowledge via Corrections For the full correction capture system — detection, generalization, categorized storage, and periodic audits — see the instinct system skill. The short version: after every correction, capture a generalized rule in MEMORY.md so the same mistake never recurs. Prompting Techniques for .NET Challenge Claude's work: Demand proof: After a mediocre fix: For EF Core migrations: Subagent Patterns for .NET The kit ships 10 specialist agents — route to them before writing your own: dotnet architect , code reviewer , refactor cleaner , test engineer , security auditor , build error resolver , ef core specialist , api designer , performance analyst , devops engineer . Each carries pre loaded skills and domain context a generalist session lacks. Use them: For workflows the kit does not cover, create project specific subagents in .claude/agents/ — a markdown file with a role, a numbered job list, and a required report format (PASS with summary / FAIL with specifics). Keep one concern per agent so its output stays reviewable. When to offload vs. stay in main context: see Context Discipline below — subagents are also your context isolation chambers, not just task runners. Context Discipline The rules in .claude/rules/agents.md already mandate MCP first navigation ( find symbol before file reads, get diagnostics over builds). This section is the strategy layer on top: how to budget, when to offload, and how to recover. Token Economics A Roslyn MCP query costs 30 150 tokens; a file read costs 500 2000+. To understand OrderService , four MCP calls ( find symbol → get public api → find references → get type hierarchy ) cost ~310 tokens; reading the four related files costs ~2900. Then read only the method you'll modify. Reserve full file reads for files you are about to edit. Subagent Offloading Decision Matrix Ask subagents for compressed answers: "Trace the auth flow from login to token validation. Return numbered steps with file:line references." You get ~300 tokens of findings instead of 15k tokens of raw files. File Reading Prioritization Budget Planning and Recovery Before a complex task, sketch the spend: understand ~5k (MCP + subagent), plan ~2k, implement ~15k (read targets + write + iterate), verify ~3k — leaving the bulk of the window for conversation. Lazy Skill Loading Don't front load skills "just in case" — 15 skills at ~300 tokens each is ~4500 tokens spent before any work starts. Load modern csharp at session start if relevant; pull ef core , testing , etc. the moment the topic actually arises. Anti patterns Don't Skip Plan Mode for Complex Tasks Don't Work in a Single Session When You Could Parallelize Don't Accept the First Solution Don't Load Everything Because the Window Is Large Decision Guide Scenario Recommendation Task touches 3+ files Plan mode first Task is a simple bug fix Just fix it, verify with dotnet test Need to build + test + review 3 parallel worktrees CI keeps failing on format Add PostToolUse format hook Tired of permission prompts Pre allow dotnet commands Claude made a mistake "Update CLAUDE.md so you don't make that mistake again" Code feels hacky "Knowing everything you know now, implement the elegant solution" Want to verify architecture Spin up a second session as staff reviewer Repetitive PR workflow Route to kit agents (code reviewer, refactor cleaner) or create a project subagent Learning a new codebase Use "Explanatory" output style via /config Need a type's API or location get public api / find symbol — don't read the file Need to modify a file Read it fully — exact content required Exploring unfamiliar code Spawn a subagent — keep main context clean 10+ files read in a session Pause — switch to MCP + subagents Context feels heavy or sluggish Summarize what you know, subagents going forward Large codebase (50+ projects) MCP first, subagent heavy, read only files you modify New topic mid session Load the relevant skill on demand, not in advance

workflow-mastery