feat: template-based dual-target generator for Claude + Codex

Replace generate-codex.sh with unified generate.sh that produces both
claude/ and codex/ output from template source files.

Agent bodies use ${PLANS_DIR}, ${WEB_SEARCH}, ${SEARCH_TOOLS} placeholders
expanded per-target via envsubst. Skills and rules made tool-agnostic
(no Claude tool names or .claude/ paths). Orchestrate skill stays
Claude-only.

install.sh now symlinks from claude/agents/ instead of agents/ directly.
flake.nix adds gettext (envsubst) to devShell.

rules/01-session.md

@@ -1,12 +1,12 @@
 # Session Behavior
 
 - Treat each session as stateless — do not assume context from prior sessions
-- The CLAUDE.md hierarchy and `.claude/memory/` are the only sources of persistent context
+- The instruction hierarchy and `memory/` are the only sources of persistent context
 - If something needs to carry forward across sessions, persist it in the appropriate file — not in session memory
 
 # Project Memory
 
-- Project-specific memory lives in `.claude/memory/` at the project root
+- Project-specific memory lives in `memory/` at the project root
 - Use `MEMORY.md` in that directory as the index (one line per entry pointing to a file)
 - Memory files use frontmatter: `name`, `description`, `type` (user/feedback/project/reference)
-- Commit `.claude/memory/` with the repo so memory persists across machines and sessions
+- Commit `memory/` with the repo so memory persists across machines and sessions

rules/04-tools.md

@@ -14,4 +14,4 @@
 
 - Use subagents for exploratory reads and investigations to keep the main context clean
 - Prefer scoped file reads (offset/limit) over reading entire large files
-- When a task is complete or the topic shifts significantly, suggest /clear
+- When a task is complete or the topic shifts significantly, suggest clearing context or starting a new session