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

Paste-into-Claude-Code starter. The CLAUDE.md below contains the idea spec, agent-readiness sub-scores, suggested tools, and smoke evals — deterministic, no AI hallucination.

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

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/planmaster-9000-aka-rfc-to-planmd-whispe-build-code-planner). Roasted, scored, ready to scaffold.

## What you are building

**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:** ACTUALLY NOT BAD — _"You've drawn a prettier architecture diagram than most YC companies ship — now survive the multi-repo context window."_

**Summary:** An orchestrated agentic planner that ingests an RFC/ticket, retrieves codebase + ADR/postmortem context across multiple repos, generates a structured PLAN.md via the strongest available model, self-critiques for gaps, then fans out plan.approved events to Code Impl and SDET sub-agents.

## Agent-readiness score

Overall: **51/100** (band D)

| Dimension | Score | Why |
|---|---|---|
| Memory required | 19/25 | Some cross-session state — start with Redis, graduate to a vector store. |
| Tool count | 7/25 | Crowded market: at least 9 integrations to compete. |
| Policy surface | 9/25 | Wide policy surface — full red-team pass, content filter, and human-in-loop required. |
| Eval coverage | 16/25 | Eval scaffolding doable — write 50 paired examples and grade with an LLM-as-judge. |

> Build only if you have a moat. PlanMaster 9000 (aka RFC-to-PLAN.md Whisperer)'s readiness gap is real work.

## Suggested tools

- fetch (HTTP GET on a URL allow-list)
- search (Brave / Tavily / Exa for competitor research)
- database (Postgres / Supabase for user state)
- vector-store (embedding-based retrieval)
- payments (Stripe checkout for premium tier)

## Smoke evals

- The agent introduces itself as "PlanMaster 9000 (aka RFC-to-PLAN.md Whisperer)" and refuses tasks outside the stated scope.
- Given the canonical problem ("I want build a code planner agent ,(basically a planner service, which does the "), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from Devin (Cognition AI)?", the agent gives a concrete differentiator, not a marketing line.
- When asked about GitHub (Microsoft)'s threat, the agent acknowledges the risk honestly.
- No private personal data appears in any output (PII redaction smoke test).

## Stack

- Model: `claude-sonnet-4-6` (Anthropic). Override via `ANTHROPIC_MODEL` env.
- Suggested stack: `LangGraph`, `Claude API (Opus for Phase 2, Haiku for Phase 3)`, `pgvector on Supabase`, `GitHub/GitLab webhooks`, `Next.js`
- Solo build estimate: 3-4 months to MVP that doesn't embarrass you; 8 months to something you'd show a Series A investor

## Kill prediction

GitHub (Microsoft) could obsolete this in 12-18 months. Copilot Workspace adds RFC ingestion, ADR retrieval, and a versioned plan artifact to its existing issue→plan→code pipeline. It ships as a free add-on for GitHub Enterprise at $21/seat/month. Your standalone product has no answer.

**Survival strategy:** Own the cross-org, multi-VCS (GitHub + GitLab + Bitbucket simultaneously) enterprise segment and the postmortem/ADR organizational memory angle — GitHub will never index your Confluence and your 3-year-old postmortem Notion docs.

## Hand-off

- Read the full analysis: https://whycantwehaveanagentforthis.com/result/planmaster-9000-aka-rfc-to-planmd-whispe-build-code-planner
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/planmaster-9000-aka-rfc-to-planmd-whispe-build-code-planner#claim

## Build it with a human

Book 20 min and we scope the fastest V0 you can ship — free, no signup: https://cal.com/sattyamjjain