Claude Code Workflow
Claude Code is good. But if you're prompting it cold — no codebase context, no plan, just a paragraph — you're not getting its best work. You're getting generic output that doesn't know your files, doesn't respect your architecture, and needs three rounds of correction before it's usable.
Tekk is the planning layer you run before Claude Code touches anything.
How Tekk.coach Fits Your Claude Code Workflow
Claude Code needs two things to work well: context and a plan. Most developers try to provide those through CLAUDE.md files, plan mode, and carefully crafted prompts. That works — if you're disciplined about it on every single task.
Tekk makes the structured spec the default output, not a discipline you have to maintain.
Tekk connects to your repo (GitHub, GitLab, Bitbucket) and reads your codebase before asking you anything. Semantic search. File search. Directory structure. Language and framework profiling. It knows your code.
Then it asks 3–6 questions grounded in what it found. Not generic planning questions — questions about your specific files, your actual dependencies, the real constraints in your repo.
The output is a structured spec: TL;DR, scope boundaries (what's building and what's explicitly not), subtasks with acceptance criteria and file references, assumptions with risk levels, and validation scenarios.
That spec goes to Claude Code via MCP tool extensions. Claude Code gets the context it needs at the file level, not the paragraph level.
Key Benefits
Specs Claude Code can actually execute Not a vague task description. A complete plan with subtasks broken into behavioral slices, file references, and acceptance criteria per step. Claude Code knows exactly what to do and where.
Codebase-grounded, not guessed Tekk reads your repo before generating anything. The spec references real files, real patterns, real dependencies. No hallucinated suggestions about architecture that doesn't match your codebase.
Scope protection built in Every spec has a "Not Building" section. Claude Code executes what's in the spec — nothing else. Scope creep doesn't happen when the boundaries are explicit before the first line of code.
Kanban tracking in the same workspace Visual To Do / In Progress / Done board. Each card links to the full planning session and spec. You see everything — what's planned, what's in progress, what shipped — without switching tools.
How It Works
- Connect your repo to Tekk — GitHub, GitLab, or Bitbucket. Takes about 60 seconds.
- Describe the feature — What you're building, in plain language.
- Tekk reads your codebase and asks questions — 3–6 questions grounded in your actual files. No generic planning prompts.
- Review options and lock in a plan — Tekk presents architecture options with honest tradeoffs, then generates a complete spec in a live document editor you can edit directly.
- Claude Code executes the spec via MCP — Your approved spec goes to Claude Code, which executes against the shared feature branch. (Execution dispatch is coming next.)
- PR lands on the feature branch — Review and merge when ready.
Steps 1–4 are live today. Step 5 (execution dispatch to Claude Code via MCP) is in progress.
Who This Is For
Claude Code users who want consistent output You know Claude Code works. You've seen it nail something complex. But you need it to work that way on every task — not just when you spend 20 minutes crafting the perfect prompt. Tekk makes the structured input the default.
Developers building on top of Claude Code Building a workflow around Claude Code — custom commands, MCP integrations, spec-to-PR automation? Tekk sits at the front of that pipeline and handles the planning phase.
Solo founders using Claude Code to ship No senior architect on the team. You're making architecture calls in domains you're not deep in. Tekk searches the web for current best practices and puts them in the spec. You get a real plan, not a guess.
What Is Claude Code?
Claude Code is Anthropic's CLI for AI-assisted development. It runs in your terminal, reads your codebase, and executes multi-step coding tasks on its own — writing code, running tests, fixing failures, opening PRs.
It's not inline autocomplete. It's not a chat window. It's agentic: you give it a task, it works through it end to end. It can read any file in your repo, run any shell command (with configurable permissions), and connect to external tools via MCP.
Quality depends almost entirely on the context it gets. A spec with file references and acceptance criteria produces fundamentally different output than a one-sentence description. That gap is exactly what Tekk fills.
Start Planning Free
Connect your repo. Describe the feature. Get a spec Claude Code can actually execute.