- Home
- Skills
- Agents & Orchestration
- Senior Planner
Works with the AI Agents you already use
Senior Planner
Transforms software architecture into atomic, TDD-ready implementation tasks with strict review boundaries.
$5
Senior Planner
Example session with this skill installed
Plan the implementation for Project Phoenix. Architecture is at docs/arch.md, infra at docs/infra.md, and P0 stories at docs/reqs.md. The goal is a local-first CLI for log parsing.
- Read your context and instructions
- Compiled the senior planner
Handoff processed for Project Phoenix. I have inventoried the P0 behaviors and mapped them to the local-first architecture.
Implementation Plan: Project Phoenix
Status: READY
P0 Coverage: 100% (3 stories)
Task Count: 4
Review Bar
- No Architecture Changes: Do not add HTTP listeners, external databases, or cloud SDKs.
- File Integrity: Modifications are strictly limited to the
fileslist in each task. - TDD Mandatory: The
test_firstassertion must fail before implementation begins. - Scope Lock: No implementation of P1/P2 "Future Analytics" stories.
Task List
| ID | Title | Story | Files | Test First | Estimate |
|---|---|---|---|---|---|
| T-001 | Initialize SQLite Schema | S-01 | src/db/schema.sql | tests/db_test.py: Table 'logs' must exist | S |
| T-002 | Implement Log Ingestion | S-01 | src/db/client.py | tests/db_test.py: save_log() inserts one row | M |
| T-003 | Parse Plaintext Streams | S-02 | src/parser/core.py | tests/parse_test.py: Regex handles ISO-8601 | M |
| T-004 | CLI Output Table | S-03 | src/cli/main.py | tests/ui_test.py: Output contains 'Timestamp' header | S |
Out of Slice
- Web Dashboard (P1)
- Multi-user authentication (Will-not-build)
Next steps
- Review the
plans/tasks.mdfile for dependency logic. - Initialize the repository with the defined folder structure.
- Assign T-001 to a junior-tdd agent or developer.
implemented: no
tests_written: no
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Vague software architectures lead to bloated junior tasks, scope creep, and architectural drift. Developers often waste time debating implementation details during sprints because the handoff lacked specific file boundaries and test-first requirements.
What it does
- Converts software architecture and requirements into atomic, junior-sized implementation tasks.
- Maps every P0 story to specific file paths, avoiding "the usual places" ambiguity.
- Defines a strict review bar that explicitly forbids architectural changes and out-of-scope work.
- Sequences tasks by dependency (storage before UI) with realistic S/M session estimates.
- Enforces test-first assertions for every task to ensure measurable completion.
Why this beats prompting it yourself
Generic prompts often hallucinate new features or ignore architectural constraints. This skill uses a strict binding process that halts execution if the architecture is blocked, preventing the creation of a "wish list" disguised as a plan. It ensures zero architectural drift by refusing to add stubs, APIs, or stores not defined by the architect.
Use cases
- Slicing a new feature architecture into a TDD-ready task list for a junior dev or agent.
- Creating a dependency-aware roadmap for a P0 product launch.
- Setting a quality gate for contractors by defining "must-not" implementation boundaries.
Known limitations
Requires pre-existing architecture, infrastructure, and requirement documents. It will not generate tasks for P1/P2 features or invent solutions for missing architectural components.
Requires architecture, infra, and requirements docs to be 'ready'. Does not write code or tests. Only plans P0 stories. Will block if tasks require stack changes.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago