refactor: trim agents to production/ + simulation/, drop site-sim

AGENTS.md

@@ -14,7 +14,7 @@ This file is for implementation operators. See `skills/webster-lp-audit/SKILL.md
 Two active workstreams:
 
 - **Production Webster** — Nicolette's weekly landing-page improvement council runs on `main` via `prompts/second-wbs-session.md`. This is live for her business; do not break it.
-- **Hackathon expansion** — Dual-substrate demo (Richer Health LP + Northwest Home Renovations 3-page site) with a simulation runner producing timelapse assets. Deadline **2026-04-28**. Working branch: `dev/`. See `context/VISION.md` for canonical north-star.
+- **Hackathon expansion** — Single-substrate Richer Health LP demo with a simulation runner producing timelapse assets. Deadline **2026-04-28**. Working branch: `dev/`. See `context/VISION.md` for canonical north-star.
 
 ## First actions every session
 
@@ -89,7 +89,7 @@ Hackathon rollup procedure (after T10 completes):
 - Bypass validation (`--no-verify`, `--no-gpg-sign`, `--force`)
 - Fabricate analytics numbers or business stats
 - Silently catch errors to make things look green
-- Touch the existing 9 production `webster-*` agents during hackathon expansion — they run Nicolette's real council. Sim agents are additive (`webster-lp-sim-*`, `webster-site-sim-*`).
+- Touch the 9 specs in `agents/production/` during hackathon expansion — they run Nicolette's real council. Sim agents in `agents/simulation/` (`webster-lp-sim-*`) are additive.
 - Touch `prompts/second-wbs-session.md` — it's the production orchestrator. Sim orchestrator is a fork at `prompts/sim-council.md`.
 
 ## Quality gates

README.md

@@ -1,6 +1,6 @@
 # Webster
 
-> A council of 7 Claude Managed Agents that autonomously audits a small-business landing page every week, synthesizes the findings, and opens a PR with the proposed redesign.
+> A council of 9 Claude Managed Agents that autonomously audits a small-business landing page every week, synthesizes the findings, and opens a PR with the proposed redesign.
 
 **Built with Opus 4.7** — Anthropic × Cerebral Valley Hackathon submission (deadline 2026-04-26).
 
@@ -14,7 +14,7 @@ Small businesses pay marketing agencies $2K–$20K/month for landing-page optimi
 weekly trigger
    │
    ▼
-Planner ──► SEO / brand / compliance / conversion / copy / monitor
+Planner ──► SEO / brand / compliance / conversion / copy / monitor / visual-reviewer
    │                         │
    │                         └── out-of-scope overlap found
    ▼
@@ -46,15 +46,15 @@ bun scripts/critic-genealogy.ts --fixtures scripts/__tests__/fixtures/genealogy
                       Planner (Opus 4.7)
                  memory + verdicts → plan.md
                               │
-               fans out 6 sessions in parallel ─┐
-                                                │
-  ┌───────┬──────────┬──────────┬────────┬──────┴─┐
-  │  SEO  │  brand   │ FH-compl │  CRO   │ copy   │  monitor
-  │ Sonnet│ Sonnet   │  Sonnet  │ Sonnet │ Sonnet │  Haiku
-  │  4.6  │   4.6    │   4.6    │  4.6   │  4.6   │   4.5
-  └───┬───┴────┬─────┴─────┬────┴────┬───┴────┬───┘
-      │        │           │         │        │
-      └────────┴─── each critic commits via GitHub MCP ──┐
+               fans out 7 sessions in parallel ─────────────┐
+                                                            │
+  ┌───────┬──────────┬──────────┬────────┬────────┬─────────┴─┬───────────────┐
+  │  SEO  │  brand   │ FH-compl │  CRO   │  copy  │  monitor  │ visual-review │
+  │ Sonnet│ Sonnet   │  Sonnet  │ Sonnet │ Sonnet │  Haiku    │   Opus 4.7    │
+  │  4.6  │   4.6    │   4.6    │  4.6   │  4.6   │   4.5     │    (post)     │
+  └───┬───┴────┬─────┴─────┬────┴────┬───┴────┬───┴─────┬─────┴──────┬────────┘
+      │        │           │         │        │         │            │
+      └────────┴─── each critic commits via GitHub MCP ──┴────────────┘
                   to council/<week-date> branch          │
                                                          ▼
                      Critic Genealogy (Opus 4.7, runtime)
@@ -77,7 +77,7 @@ bun scripts/critic-genealogy.ts --fixtures scripts/__tests__/fixtures/genealogy
 
 ## For judges
 
-**30-second pitch:** Webster is an autonomous landing-page improvement council. Seven Claude Managed Agents plan, audit, monitor, synthesize, and package one weekly redesign proposal; the standout demo is Critic Genealogy, where Opus 4.7 detects an unowned audit gap and registers a new specialist at runtime.
+**30-second pitch:** Webster is an autonomous landing-page improvement council. Nine Claude Managed Agents plan, audit, monitor, synthesize, and package one weekly redesign proposal; the standout demo is Critic Genealogy, where Opus 4.7 detects an unowned audit gap and registers a new specialist at runtime.
 
 **Live-run evidence:** the full operator path is [`prompts/second-wbs-session.md`](prompts/second-wbs-session.md), registration IDs live in `environments/webster-council-env.id` and `context/*/id.txt`, and run artifacts are written under `history/<week>/` when the weekly prompt is executed.
 
@@ -91,7 +91,9 @@ bun scripts/critic-genealogy.ts --fixtures scripts/__tests__/fixtures/genealogy
 
 ```text
 webster/
-├── agents/              7 Managed Agent JSON specs (5 critics + monitor + redesigner)
+├── agents/
+│   ├── production/      9 Managed Agent specs that run Nicolette's live council
+│   └── simulation/      9 LP-sim specs (1:1 mirror) that drive the timelapse demo
 ├── context/             architecture, features, quality gates, per-critic findings dirs
 ├── environments/        webster-council-env.json (single Anthropic environment)
 ├── prompts/             first-wbs-session.md (bootstrap), second-wbs-session.md (weekly run)
@@ -109,14 +111,14 @@ The live council runner is a bash-in-markdown prompt: [`prompts/second-wbs-sessi
 1. Seeds 10 weeks of mock analytics on first run (monitor needs baselines to diff).
 2. Prepares a shared `council/YYYY-MM-DD` branch.
 3. Runs the planner — marshals `history/memory.jsonl`, recent verdicts, and monitor anomalies; writes `history/YYYY-MM-DD/plan.md`.
-4. Fans out 6 Managed Agent sessions (monitor + 5 critics) — each commits `context/critics/<scope>/findings.md` via GitHub MCP.
+4. Fans out 7 Managed Agent sessions (monitor + 5 critics + visual-reviewer) — each commits `context/critics/<scope>/findings.md` via GitHub MCP.
 5. Validates findings via `bun scripts/validate-findings.ts`.
 6. Runs the redesigner — commits `history/YYYY-MM-DD/proposal.md` + `decision.json`.
 7. Opens a draft PR.
 
 Expected wall-clock: 30–50 min. Expected API cost: ~$0.16–0.25 per run.
 
-**Submission note**: all 7 agent specs are registered against the live Anthropic API (IDs in `environments/webster-council-env.id` + `context/*/id.txt`), the genealogy hero is live-validated (~$0.03 Opus 4.7 dry-run documented above), and the full orchestration prompt is committed. The end-to-end 6-agent fan-out that produces `history/YYYY-MM-DD/` artifacts is the operator-triggered weekly run — `history/` is empty at submission time by design. Loop has been exercised component-by-component.
+**Submission note**: all 9 agent specs are registered against the live Anthropic API (IDs in `environments/webster-council-env.id` + `context/*/id.txt`), the genealogy hero is live-validated (~$0.03 Opus 4.7 dry-run documented above), and the full orchestration prompt is committed. The end-to-end fan-out that produces `history/YYYY-MM-DD/` artifacts is the operator-triggered weekly run — `history/` is empty at submission time by design. Loop has been exercised component-by-component.
 
 ## Quality gates
 
@@ -128,11 +130,11 @@ bun run validate
 
 Chains: `tsc --noEmit` → `eslint --max-warnings 0` → `prettier --check` → agent+environment schema validation → findings format validation → markdownlint → `bun test`. Every gate is blocking. Pre-commit hook enforces the same set. CI enforces the same set on push + PR. See [`context/QUALITY-GATES.md`](context/QUALITY-GATES.md).
 
-Current state: 29 tests passing, 0 lint warnings, 0 type errors, 8 JSON specs valid, 6 findings files valid.
+Current state: 175 tests passing, 0 lint warnings, 0 type errors, 18 JSON specs valid, 6 findings files valid.
 
 ## Prize-lane alignment
 
-- **Best Use of Claude Managed Agents** — 7 pre-registered agents + runtime-registered genealogy critics, all invoked via `/v1/sessions` with vault-bound GitHub MCP (no tokens in `user.message`).
+- **Best Use of Claude Managed Agents** — 9 pre-registered production agents (with a 1:1 sim mirror in `agents/simulation/`) + runtime-registered genealogy critics, all invoked via `/v1/sessions` with vault-bound GitHub MCP (no tokens in `user.message`).
 - **Creative Exploration** — runtime critic genealogy. Gap detection → template-cloned spec → live `POST /v1/agents` → immediate invocation. The emergent-capability demo beat.
 
 ## Running it yourself
@@ -151,7 +153,7 @@ Current state: 29 tests passing, 0 lint warnings, 0 type errors, 8 JSON specs va
 wbs @prompts/first-wbs-session.md
 ```
 
-Registers the single environment + 7 agents against the Anthropic API. Runs an SEO hello-world to prove the council loop end-to-end. Artifacts: `environments/webster-council-env.id` + `context/{monitor,redesigner,critics/*}/id.txt`.
+Registers the single environment + 9 production agents against the Anthropic API. Runs an SEO hello-world to prove the council loop end-to-end. Artifacts: `environments/webster-council-env.id` + `context/{monitor,redesigner,critics/*}/id.txt`.
 
 ### Weekly council run
 
@@ -173,13 +175,13 @@ Reads the week's findings, asks Opus 4.7 if any scope is unowned, and spawns + r
 
 Every layer uses Opus 4.7 as author:
 
-| Layer                           | Opus 4.7 role                                                             |
-| ------------------------------- | ------------------------------------------------------------------------- |
-| 7 agent specs (`agents/*.json`) | Drafted during bootstrap session, validated against live API              |
-| Bootstrap + weekly prompts      | Opus-authored during dispatcher sessions; in git history                  |
-| Critic Genealogy script         | Opus-authored; see `dcf5726` + `e474301`                                  |
-| Redesigner synthesis            | Opus 4.7 at runtime — its decision.json outputs live in `history/<date>/` |
-| Runtime critic spawning         | Opus 4.7 selects the gap AND authors the new spec via `tool_use`          |
+| Layer                                      | Opus 4.7 role                                                             |
+| ------------------------------------------ | ------------------------------------------------------------------------- |
+| 9 agent specs (`agents/production/*.json`) | Drafted during bootstrap session, validated against live API              |
+| Bootstrap + weekly prompts                 | Opus-authored during dispatcher sessions; in git history                  |
+| Critic Genealogy script                    | Opus-authored; see `dcf5726` + `e474301`                                  |
+| Redesigner synthesis                       | Opus 4.7 at runtime — its decision.json outputs live in `history/<date>/` |
+| Runtime critic spawning                    | Opus 4.7 selects the gap AND authors the new spec via `tool_use`          |
 
 Repo is entirely MIT. No Anthropic or third-party proprietary code.
 

agents/AGENTS.md

@@ -43,12 +43,9 @@ Environments are a **separate resource** (`POST /v1/environments`). Reference by
 
 ## Two agent sets (hackathon expansion)
 
-The existing 9 `webster-*` specs are the **production set**. They run Nicolette's real weekly council. **Do not modify them.**
+The 9 specs in `agents/production/` are the **production set**. They run Nicolette's real weekly council. **Do not modify them.**
 
-Sim expansion adds 18 new specs:
-
-- `webster-lp-sim-*` (9) — Richer Health simulation, MCP-native (no WebFetch)
-- `webster-site-sim-*` (9) — Northwest Home Renovations simulation, MCP-native. Fifth critic is `licensing-and-warranty-critic` replacing `fh-compliance-critic`
+The 9 specs in `agents/simulation/` are the **LP-sim set** — Richer Health simulation, MCP-native (no WebFetch). They mirror the production set 1:1 and drive the timelapse demo.
 
 Sim agents read the site via `get_file_contents` (GitHub MCP) at demo branch refs — never WebFetch, never localhost.