--- name: incremental-implementation description: Delivers changes incrementally and grills unspecified forks instead of silently picking among them. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step. --- # Incremental Implementation ## Overview Build in thin vertical slices — implement one piece, test it, verify it, then expand. Avoid implementing an entire feature in one pass. Each increment should leave the system in a working, testable state. This is the execution discipline that makes large features manageable. Each increment ends at a **user review gate**, not an auto-commit. The agent presents a standard summary and waits for explicit approval before starting the next slice. Staging and committing are the user's responsibility — the agent never runs `git add` or `git commit` on its own. ## When to Use - Implementing any multi-file change - Building a new feature from a task breakdown - Refactoring existing code - Any time you're tempted to write more than ~100 lines before testing **When NOT to use:** Single-file, single-function changes where the scope is already minimal. ## The Increment Cycle ``` ┌───────────────────────────────────────────────────┐ │ │ │ Implement ─→ Test ─→ Verify ─→ Request Review │ │ ▲ │ │ │ │ ▼ │ │ Revise ◄── (changes requested) ── Gate │ │ │ │ │ (approved) ───┘ │ │ ▼ │ │ Next slice │ │ │ └───────────────────────────────────────────────────┘ ``` For each slice: 1. **Implement** the smallest complete piece of functionality 2. **Test** — run the test suite (or write a test if none exists) 3. **Verify** — confirm the slice works as expected (tests pass, build succeeds, manual check) 4. **Request review** — present the Standard Slice Summary (below) and ask the user to confirm before moving to the next slice. Use the `AskUserQuestion` tool if available; otherwise ask in chat and wait for explicit confirmation. Do **not** stage or commit — the user handles git operations manually after approval. See `git-workflow-and-versioning` for the atomic-commit guidance the user should follow when committing approved slices. 5. **Move to the next slice** only after explicit approval — carry forward, don't restart ## Standard Slice Summary When requesting review, present the slice in this exact shape so the user can scan quickly: - **Slice N: ``** - **Files changed:** bulleted list, each as `path:line-range` with a 3–6 word note - **What it does:** 1–2 sentences describing the behavior delivered - **How it was verified:** tests run, build status, manual checks performed - **Risks / things to double-check:** anything non-obvious, assumptions made, edge cases skipped - **Next slice (if approved):** one-line preview of what comes next Keep it tight. The summary is a review aid, not a report. ## Requesting Approval Prefer the `AskUserQuestion` tool with these options: - **Approve & continue** — slice is accepted; agent proceeds to the next slice (changes remain unstaged for the user to commit) - **Request changes** — user will describe what to change; agent revises within the same slice, re-summarizes, and re-asks - **Compact & continue** *(pi only, when the `compact-and-continue` extension is installed)* — call `request_compaction` with a self-contained `continuationPrompt` summarizing the remaining slices; the turn terminates, pi compacts context, then auto-resumes from the continuation prompt - **Stop here** — end the session without modifying git state If the `request_compaction` tool is not registered (e.g. running outside pi, or the extension is not installed), omit "Compact & continue" — the other three options are the universal fallback. If `AskUserQuestion` is not available, ask the same question in chat and **wait** — do not proceed on silence or ambiguous responses. On "Request changes", revise inside the current slice and re-present the summary. On "Stop here", leave the working tree untouched and end. ## Slicing Strategies ### Vertical Slices (Preferred) Build one complete path through the stack: ``` Slice 1: Create a task (DB + API + basic UI) → Tests pass, user can create a task via the UI Slice 2: List tasks (query + API + UI) → Tests pass, user can see their tasks Slice 3: Edit a task (update + API + UI) → Tests pass, user can modify tasks Slice 4: Delete a task (delete + API + UI + confirmation) → Tests pass, full CRUD complete ``` Each slice delivers working end-to-end functionality. ### Contract-First Slicing When backend and frontend need to develop in parallel: ``` Slice 0: Define the API contract (types, interfaces, OpenAPI spec) Slice 1a: Implement backend against the contract + API tests Slice 1b: Implement frontend against mock data matching the contract Slice 2: Integrate and test end-to-end ``` ### Risk-First Slicing Tackle the riskiest or most uncertain piece first: ``` Slice 1: Prove the WebSocket connection works (highest risk) Slice 2: Build real-time task updates on the proven connection Slice 3: Add offline support and reconnection ``` If Slice 1 fails, you discover it before investing in Slices 2 and 3. ## Implementation Rules ### Rule 0: Simplicity First Before writing any code, ask: "What is the simplest thing that could work?" After writing code, review it against these checks: - Can this be done in fewer lines? - Are these abstractions earning their complexity? - Would a staff engineer look at this and say "why didn't you just..."? - Am I building for hypothetical future requirements, or the current task? ``` SIMPLICITY CHECK: ✗ Generic EventBus with middleware pipeline for one notification ✓ Simple function call ✗ Abstract factory pattern for two similar components ✓ Two straightforward components with shared utilities ✗ Config-driven form builder for three forms ✓ Three form components ``` Three similar lines of code is better than a premature abstraction. Implement the naive, obviously-correct version first. Optimize only after correctness is proven with tests. ### Rule 0.5: Scope Discipline Touch only what the task requires. Do NOT: - "Clean up" code adjacent to your change - Refactor imports in files you're not modifying - Remove comments you don't fully understand - Add features not in the spec because they "seem useful" - Modernize syntax in files you're only reading If you notice something worth improving outside your task scope, note it — don't fix it: ``` NOTICED BUT NOT TOUCHING: - src/utils/format.ts has an unused import (unrelated to this task) - The auth middleware could use better error messages (separate task) → Want me to create tasks for these? ``` ### Rule 0.6: Grill unspecified forks; do not re-ask settled ones A plan does not freeze every decision. Before (and during) a slice, if a load-bearing choice is **not** already explicit in the task, plan, PRD, chat, prompt, or rules — multiple valid approaches, a contradiction, or several existing code patterns — read [`../_internal/grilling.md`](../_internal/grilling.md) and ask one question at a time, with a recommended option. Wait. Do not pick silently and do not re-confirm what those sources already stated. If grilling produces zero questions, proceed with the slice. ### Rule 1: One Thing at a Time Each increment changes one logical thing. Don't mix concerns: **Bad:** One commit that adds a new component, refactors an existing one, and updates the build config. **Good:** Three separate commits — one for each change. ### Rule 2: Keep It Compilable After each increment, the project must build and existing tests must pass. Don't leave the codebase in a broken state between slices. ### Rule 3: Feature Flags for Incomplete Features If a feature isn't ready for users but you need to merge increments: ```typescript // Feature flag for work-in-progress const ENABLE_TASK_SHARING = process.env.FEATURE_TASK_SHARING === 'true'; if (ENABLE_TASK_SHARING) { // New sharing UI } ``` This lets you merge small increments to the main branch without exposing incomplete work. ### Rule 4: Safe Defaults New code should default to safe, conservative behavior: ```typescript // Safe: disabled by default, opt-in export function createTask(data: TaskInput, options?: { notify?: boolean }) { const shouldNotify = options?.notify ?? false; // ... } ``` ### Rule 5: Rollback-Friendly Each increment should be independently revertable: - Additive changes (new files, new functions) are easy to revert - Modifications to existing code should be minimal and focused - Database migrations should have corresponding rollback migrations - Avoid deleting something in one commit and replacing it in the same commit — separate them Rollback safety now depends on the user committing promptly after approval. If the user defers committing across multiple approved slices, they accept the risk of a larger uncommitted diff — the agent should still not stage or commit on their behalf. ## Working with Agents When directing an agent to implement incrementally: ``` "Let's implement Task 3 from the plan. Start with just the database schema change and the API endpoint. Don't touch the UI yet — we'll do that in the next increment. After implementing, run `npm test` and `npm run build` to verify nothing is broken, then present the Standard Slice Summary and wait for my approval before the next slice. Do not stage or commit — I'll handle git manually after reviewing." ``` Be explicit about what's in scope and what's NOT in scope for each increment. ## Increment Checklist After each increment, verify: - [ ] The change does one thing and does it completely - [ ] All existing tests still pass (`npm test`) - [ ] The build succeeds (`npm run build`) - [ ] Type checking passes (`npx tsc --noEmit`) - [ ] Linting passes (`npm run lint`) - [ ] The new functionality works as expected - [ ] Unspecified load-bearing forks were grilled (or grilling found none); already-stated requirements were not re-asked - [ ] The Standard Slice Summary was presented to the user - [ ] Explicit user approval was received before starting the next slice - [ ] The agent did not run `git add`, `git commit`, `git reset`, or `git restore` during this slice (whatever the user staged or committed between slices is preserved as-is) **Note:** Run each verification command after a change that could affect it. After a successful run, don't repeat the same command unless the code has changed since — re-running on unchanged code adds no information. ## Common Rationalizations | Rationalization | Reality | |---|---| | "I'll test it all at the end" | Bugs compound. A bug in Slice 1 makes Slices 2-5 wrong. Test each slice. | | "It's faster to do it all at once" | It *feels* faster until something breaks and you can't find which of 500 changed lines caused it. | | "These changes are too small to commit separately" | Small commits are free. Large commits hide bugs and make rollbacks painful. | | "I'll add the feature flag later" | If the feature isn't complete, it shouldn't be user-visible. Add the flag now. | | "This refactor is small enough to include" | Refactors mixed with features make both harder to review and debug. Separate them. | | "I'll just stage it to make their life easier" | Don't. The user explicitly controls staging and commits. Do not run any git state-changing command — and do not "tidy up" by unstaging or resetting what the user staged between slices. | | "They didn't answer but it's obviously fine, I'll continue" | No. Silence is not approval. Wait for an explicit response before starting the next slice. | | "The plan didn't specify which existing pattern to follow, I'll just pick one" | That is an unspecified fork. Grill it. The programmer needs to know which variant was chosen and why. | | "I'll re-confirm the PRD acceptance criteria before coding" | Already-stated requirements are not re-asked. Grill only what is still open. | | "Let me run the build command again just to be sure" | After a successful run, repeating the same command adds nothing unless the code has changed since. Run it again after subsequent edits, not as reassurance. | ## Red Flags - More than 100 lines of code written without running tests - Multiple unrelated changes in a single increment - "Let me just quickly add this too" scope expansion - Skipping the test/verify step to move faster - Build or tests broken between increments - Starting the next slice without explicit user approval - Staging or committing changes on the user's behalf - Unstaging, resetting, restoring, or stashing changes the user staged or committed between slices ("enforcing" an unstaged working tree is not the agent's job) - Building abstractions before the third use case demands it - Silently picking among several valid approaches or existing code patterns - Re-asking a requirement already explicit in the task, plan, PRD, chat, or rules - Touching files outside the task scope "while I'm here" - Creating new utility files for one-time operations - Running the same build/test command twice in a row without any intervening code change ## Verification After completing all increments for a task: - [ ] Each increment was individually tested and approved by the user - [ ] The full test suite passes - [ ] The build is clean - [ ] The feature works end-to-end as specified - [ ] The agent performed no git state changes during the task (no `git add`, `git commit`, `git reset`, `git restore`, `git stash`, etc.) — whatever the user staged or committed between slices is preserved ## See Also Per-increment verification is the local check. Before declaring a task done, apply the project-wide Definition of Done as the final gate, the standing bar every increment clears regardless of the task. See `references/definition-of-done.md`.