Help us improve
Share bugs, ideas, or general feedback.
From hb
Generates multi-phase implementation plans from PRDs using tracer-bullet vertical slices. Useful for breaking down features into demoable phases.
npx claudepluginhub helderberto/agent-skills --plugin hbHow this skill is triggered — by the user, by Claude, or both
Slash command
/hb:plan [slug][slug]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Break a PRD into phased vertical slices (tracer bullets).
Creates structured product plans and build plans with acceptance criteria, architecture, and verification using the planr CLI.
Share bugs, ideas, or general feedback.
Break a PRD into phased vertical slices (tracer bullets).
Interactive prompts: present options as a numbered list and wait for the user's choice.
Output: .specs/plans/<slug>.md.
The argument (if provided) is: $ARGUMENTS
Use argument as <slug>. If empty, list PRDs as numbered options and wait for the user's choice.
Read .specs/prds/<slug>.md. If missing, list PRDs as numbered options and wait for the user's choice.
If .specs/plans/<slug>.md exists, present options and wait:
Map architecture, patterns, integration points. Skip if codebase context exists from prior step.
Research protocol: codebase first, then docs. Unverifiable claims → flag as uncertain, never fabricate.
Before slicing, extract decisions that hold across all phases:
Each phase: thin vertical slice through all layers (schema → service → API → UI → tests). Demoable alone.
Deriving tasks from the PRD:
| PRD Section | Becomes |
|---|---|
| New Modules | Implement module with interface |
| Schema Changes | Migration + validation |
| API Contracts | Route returning shape |
| Navigation | Wire component to route |
| User Stories | Verify coverage; add task if missing |
| Testing Decisions | Tests land in the phase where their module lands |
| Out of Scope | Never create tasks for these |
Within each slice, order by dependency: schema → service → API → UI → tests. Happy paths before edge cases.
Phase naming: use a goal phrase answering "what can we demo when this is done?" (e.g., "Phase 1 — Revenue visible end-to-end"), not a layer name.
Done when: checkbox list of atomic, verifiable conditions. Each must name a test file/name, a shell command, or a file+content to verify. No prose-only conditions. Test: "Can an agent verify by reading files, running a command, or checking a test?"
Layer-by-layer exception: if complex schema changes underpin all modules and no story stands alone, build data foundation first, then slice vertically.
Phase count thresholds:
Count "modules touched" by scanning the PRD's New Modules and Schema Changes sections.
Assign an agent tag to tasks where appropriate:
[agent:debugger] — tracing a bug or unexpected runtime behavior[agent:test-auditor] — writing or reviewing tests[agent:code-reviewer] — reviewing API surfaces, interfaces, or public contractsPresent breakdown (title, user stories covered, done-when per phase). Present options and wait:
Iterate until approved.
Save to .specs/plans/<slug>.md (create dir if missing).
# Plan: <Feature Name>
Use this structure for the plan body:
## Architectural Decisions
Durable decisions that apply across all phases:
- **Key decision**: ...
---
## Phase 1 — <Goal>
**User stories**: <list from PRD>
### What to build
Concise description of this vertical slice — end-to-end behavior, not layer-by-layer.
### Done when
- [ ] Atomic, testable condition
- [ ] Another testable condition
---
<!-- Repeat for each phase -->
## Out of Scope
Carried forward from PRD verbatim.
## Open Questions
Gaps found in the PRD needing resolution. Blank if none.
Print one line per phase: Phase N — <title> (<condition summary>). Present options and wait:
/hb:build <slug> (Recommended)/hb:check <slug>To implement this plan phase by phase, run /hb:build <slug>. It handles branch creation, implementation, feedback loops, checkbox marking, and commits — one phase per invocation.