Skip to content

A full-featured CRM built with React, shadcn/ui, and Supabase.

apply review

erwanMarmelabdd50d21da8d6
diff --git a/.claude/agents/developer.md b/.claude/agents/developer.md
index 8bfcf7b1..6e875c66 100644
--- a/.claude/agents/developer.md
+++ b/.claude/agents/developer.md
@@ -1,7 +1,7 @@
---
name: developer
description: Implementation agent for COMPLEX tickets. Spawned by the orchestrator (foreground) per ticket. Plans, implements, commits in a worktree, then emits an output contract line so the orchestrator can dispatch reviewers.
-model: opus
+model: sonnet
tools:
- Read
- Write
diff --git a/.claude/agents/planner.md b/.claude/agents/planner.md
index b85f62a7..7f85de41 100644
--- a/.claude/agents/planner.md
+++ b/.claude/agents/planner.md
@@ -1,7 +1,7 @@
---
name: planner
description: Product task planner. Use at the start of any new feature or project need (COMPLEX path) and at the end of FULL_SETUP (SETUP_MODE=true). Decomposes natural-language product needs into atomic, ordered, actionable tickets with best-guess file paths.
-model: sonnet
+model: opus
effort: xhigh
tools:
- Write
@@ -246,6 +246,12 @@ conventions, not invented criteria.
## Constraints
+- Favor small tickets — each one a coherent shippable slice that passes review
+ on its own (one entity, one view, one flow). Smaller tickets review faster,
+ merge cleaner, and fail smaller. Split a ticket that bundles unrelated
+ concerns or sprawls past ~6 files, and order the pieces with dependency waves.
+ The one exception: don't fragment a naturally cohesive change just to hit a
+ size target — a slightly larger ticket that ships one whole flow is fine.
- `files_to_modify`: 2-6 hints per ticket, not contracts.
- Don't specify implementation details (algorithms, component choices) — DEVELOPER's job.
- Don't invent acceptance criteria not implied by the need.
diff --git a/.claude/agents/quality-reviewer.md b/.claude/agents/quality-reviewer.md
index 7b628381..0878582e 100644
--- a/.claude/agents/quality-reviewer.md
+++ b/.claude/agents/quality-reviewer.md
@@ -1,7 +1,7 @@
---
name: quality-reviewer
description: Combined code quality, security, and QA review agent — the sole reviewer in a COMPLEX wave (code + security review AND runtime/integration validation), and single-shot in the SIMPLE flow when the diff touched `supabase/` (schema/view/RLS gating before merge).
-model: sonnet
+model: opus
tools:
- Read
- Grep
@@ -291,7 +291,7 @@ Supabase-specific:
Verify the implementation works to the extent the local environment allows.
Authoritative validation runs in CI on the PR (`make start-supabase-e2e`); this
is the local pre-filter. Behavior-verifiable acceptance criteria, integration
-wiring, and e2e presence are yours to check here — no second reviewer covers them.
+wiring, and e2e presence are yours to check here.
### Sandbox awareness
diff --git a/CLAUDE.md b/CLAUDE.md
index e6d054e5..15a3036a 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -26,14 +26,14 @@ There is no cross-agent messaging: the orchestrator dispatches every agent as a
| Agent | Model | Role |
|---|---|---|
| chat-orchestrator | sonnet | User-facing. Routes, narrates. SIMPLE flow dispatches simple-developer + merger directly (no team). |
-| planner | sonnet | Decomposes the plan into tickets JSON with waves + file hints. |
-| developer | opus | Implements + commits in a worktree. Applies the **Ponytail** minimization ladder (full mode) automatically on every ticket, via an inline prompt directive. Writes ADRs for structural decisions. Never writes SQL migrations (deploy-time only). |
+| planner | opus | Decomposes the plan into tickets JSON with waves + file hints. |
+| developer | sonnet | Implements + commits in a worktree. Applies the **Ponytail** minimization ladder (full mode) automatically on every ticket, via an inline prompt directive. Writes ADRs for structural decisions. Never writes SQL migrations (deploy-time only). |
| simple-developer | sonnet | One cosmetic edit, one single-field entity change, or one filter reusing existing components. Applies the **Ponytail** ladder (full mode) automatically, via an inline prompt directive. No team, no review. |
-| quality-reviewer | sonnet | Sole reviewer: combined semantic code + security review AND QA/runtime validation (integration wiring, behavior criteria, e2e presence). Never re-runs validation. |
+| quality-reviewer | opus | Sole reviewer: combined semantic code + security review AND QA/runtime validation (integration wiring, behavior criteria, e2e presence). Never re-runs validation. |
| merger | haiku | `git merge --no-ff` only. Never `git add` / `git commit`. |
-| documentator | sonnet | Mode 1 — captures rules/skills on request. Mode 2 — appends business knowledge to `MEMORY.md` at COMPLEX session end. |
+| documentator | haiku | Mode 1 — captures rules/skills on request. Mode 2 — appends business knowledge to `MEMORY.md` at COMPLEX session end. |
-Only **developer** runs on opus; everything else is sonnet or haiku.
+**planner** and **quality-reviewer** run on opus; everything else is sonnet or haiku.
The **developer** and **simple-developer** apply the **Ponytail** minimization ladder (full mode) on every change, via inline directives in their prompts — the only mechanism that reaches `Agent`-dispatched subagents. Ponytail is also installed **natively** in-repo as on-demand skills (no plugin, no marketplace, no hooks): its skills live in `.claude/skills/ponytail*` and its `/ponytail*` commands in `.claude/commands/`, for interactive use in the main session (`/ponytail-review`, `/ponytail-audit`, …). These do not affect the dev agents, whose ladder comes from the inline directives above.