# PlanMaster 9000 (aka RFC-to-PLAN.md Whisperer)

> https://whycantwehaveanagentforthis.com/result/planmaster-9000-aka-rfc-to-planmd-whispe-build-code-planner

Problem: I want build a code planner agent ,(basically a planner service, which does the agent orchestration). Input is RFC ,output is plan.md which is feeder for code implementation agent .

## verdict

tier: ACTUALLY NOT BAD
difficulty: 7/10
savage_line: You've drawn a prettier architecture diagram than most YC companies ship — now survive the multi-repo context window.

## ship_it_anyway

differentiator: Build the postmortem + ADR retrieval layer first and only — sell 'your org's memory injected into every plan' as the SKU. Nobody else is indexing Confluence postmortems.
riskiest_assumption: That Feature Leads will actually review and approve AI plans rather than rubber-stamp them or ignore the queue entirely, making your human gate theater.
honest_cost: ~$20K and 4 months of real senior engineering time. Do NOT build this if you're at a company where 'RFC' means a Google Doc nobody reads — you have no customers.

## agent_readiness

overall: 51/100 (band D)
memory_required: 19/25
tool_count: 7/25
policy_surface: 9/25
eval_coverage: 16/25

## owasp_codes

- MCP-2: Cross-server prompt injection
- MCP-3: Excessive agency
- MCP-5: Insecure tool composition

## install_options

bootstrap: https://whycantwehaveanagentforthis.com/api/bootstrap/713b472c-e2c/raw
policy_yaml: https://whycantwehaveanagentforthis.com/api/agent-readiness/713b472c-e2c?format=yaml
badge_svg: https://whycantwehaveanagentforthis.com/api/badge/713b472c-e2c/svg

## next_step

scope_with_human: https://cal.com/sattyamjjain
note: Scope this agent live with a human — 20 min, free, no signup