---
description: Generate an actionable, dependency-ordered tasks.md for the active Rust MCP feature.
handoffs:
  - label: Analyze For Consistency
    agent: speckit.analyze
    prompt: Run a cross-artifact consistency analysis for the Rust MCP feature
    send: true
  - label: Implement Project
    agent: speckit.implement
    prompt: Start implementation in phases for the Rust MCP feature
    send: true
---

## User Input

```text
$ARGUMENTS
```

You **MUST** consider the user input before proceeding (if not empty).

## Outline

1. **Setup**: Run `.specify/scripts/bash/check-prerequisites.sh --json` from repo root and parse `FEATURE_DIR` and `AVAILABLE_DOCS`.
   - `FEATURE_DIR` under `specs/<feature>/` is the only valid output location for `tasks.md`.

2. **Load design documents** from `FEATURE_DIR`:
   - **Required**: `plan.md`, `spec.md`, `ux_reference.md`
   - **Optional**: `data-model.md`, `contracts/`, `research.md`, `quickstart.md`
   - **Required when referenced by plan**: ADR artifacts under `docs/adr/` or feature-local planning docs

3. **Build the task model**:
   - Extract user stories and priorities from `spec.md`
   - Extract repository structure, tool/resource scope, verification stack, and semantic constraints from `plan.md`
   - Extract accepted-path and rejected-path memory from ADRs and `contracts/modules.md`
   - Map entities, tool payloads, runtime evidence, and verification scenarios to stories
   - Generate tasks grouped by story and ordered by dependency
   - Validate that no task schedules an ADR-rejected path

4. **Generate `tasks.md`** using `.specify/templates/tasks-template.md` as the structure:
   - Phase 1: Setup
   - Phase 2: Foundational work
   - Phase 3+: one phase per user story in priority order
    - Final phase: polish and cross-cutting verification
    - Every task must use the strict checklist format and include exact file paths
    - Write the final document to `FEATURE_DIR/tasks.md`, never to `.kilo/plans/` or other side folders

5. **Report** the generated path and summarize:
   - total task count
   - task count per user story
   - parallel opportunities
   - story-level independent verification criteria
   - inherited ADR/guardrail coverage

## Task Generation Rules

### Story Organization

Tasks MUST be grouped by user story so each story can be implemented and verified independently.

### Required Format

Every task MUST follow:

```text
- [ ] T001 [P] [US1] Description with exact file path
```

Rules:

1. `- [ ]` checkbox is mandatory
2. sequential task IDs (`T001`, `T002`, ...)
3. `[P]` only for truly parallelizable tasks
4. `[USx]` required only for user-story phases
5. exact file paths required in the description

### Rust / MCP Pathing

Prefer real repository paths such as:

- `src/server/*.rs`
- `src/services/**/*.rs`
- `src/models/*.rs`
- `src/semantics/*.rs`
- `tests/*.rs`
- `docs/adr/*.md`
- `specs/<feature>/contracts/*.md`

Do **not** generate default tasks for:

- `backend/` or `frontend/`
- `*.py`
- `.svelte`
- `__tests__/`

### Verification Discipline

Each story phase must end with:

- a verification task against `ux_reference.md` interpreted as the caller/operator interaction contract
- a semantic audit / verification task tied to repository validators and touched contracts

Typical verification tasks may include:

- focused `cargo test` commands
- `cargo test --all-targets --all-features -- --nocapture`
- `cargo clippy --all-targets --all-features -- -D warnings`
- `python3 scripts/static_verify.py`

Only include the commands that are truly required by the feature scope.

### Contract and ADR Propagation

If a task implements or depends on a guarded contract, append a concise guardrail summary derived from `@RATIONALE` and `@REJECTED`.

Examples:

- `- [ ] T021 [US1] Implement deterministic tool envelope mapping in src/server/tools.rs (RATIONALE: preserve task-shaped MCP parity; REJECTED: ad-hoc per-tool response shapes)`
- `- [ ] T033 [US2] Add runtime evidence verification in tests/server_protocol.rs (RATIONALE: C4/C5 flows must expose belief markers; REJECTED: relying on manual log inspection only)`

If no safe executable task wording exists because the accepted path is still unclear, stop and emit `[NEED_CONTEXT: target]`.

### Test Tasks

Tests are optional only when the feature truly has no new verification surface. In this repository, test tasks are usually expected for:

- new MCP tools/resources
- new query/mutation flows
- C4/C5 semantic contracts
- runtime evidence / belief-state behavior
- rejected-path regression coverage

### Decision-Memory Validation Gate

Before finalizing `tasks.md`, verify that:

- blocking ADRs are inherited into setup/foundational or downstream story tasks
- no task text schedules a rejected path
- story tasks remain executable within the actual Rust crate structure
- at least one explicit verification task protects against rejected-path regression