docs(claude): improve CLAUDE.md with mise, secrets.d, and cleanup

Add mise tool manager section to Architecture. Add secrets.d gotcha
documenting the auto-source pattern. Remove duplicated context-mode
boilerplate block (already in global CLAUDE.md). Unpin Yarn version.

CLAUDE.md

@@ -98,6 +98,13 @@ and most scripts in `local/bin/`.
 - `dfm scripts` — run scripts from `scripts/` (discovered via `@description` tags)
 - `dfm tests` — test visualization helpers
 
+### mise — Unified Tool Manager
+
+`config/mise/config.toml` manages language runtimes (Node LTS, Python 3,
+Go latest, Rust stable) and CLI tools (fd, ripgrep, eza, neovim, delta,
+zoxide, etc.). Activated via `eval "$(mise activate bash)"` in
+`config/exports`. Run `mise install` after adding new tools.
+
 ### Submodules
 
 External dependencies are git submodules (Dotbot, plugins,
@@ -148,6 +155,10 @@ SC2174 (mkdir -p -m), SC2016 (single-quote expressions).
   and excluded from prettier (see `.prettierignore`).
 - **Python**: Two scripts (`x-compare-versions.py`,
   `x-git-largest-files.py`) linted by Ruff (config in `pyproject.toml`).
+- **Fish secrets**: `config/fish/secrets.d/*.fish` files are auto-sourced
+  by `exports.fish`. Copy `github.fish.example` → `github.fish` for local
+  secrets. These files are gitignored; only `*.example` and `README.md`
+  are tracked.
 
 ## Claude Code Configuration
 
@@ -168,88 +179,4 @@ SC2174 (mkdir -p -m), SC2016 (single-quote expressions).
 
 ## Package Manager
 
-Yarn (v4.12.0) is the package manager. Do not use npm.
+Yarn (v4+) is the package manager. Do not use npm.
-
-# context-mode — MANDATORY routing rules
-
-You have context-mode MCP tools available. These rules are NOT optional —
-they protect your context window from flooding.
-A single unrouted command can dump 56 KB into context and waste the entire session.
-
-## BLOCKED commands — do NOT attempt these
-
-### curl / wget — BLOCKED
-Any Bash command containing `curl` or `wget` is intercepted and replaced with an error message. Do NOT retry.
-Instead use:
-- `ctx_fetch_and_index(url, source)` to fetch and index web pages
-- `ctx_execute(language: "javascript", code: "const r = await fetch(...)")` to run HTTP calls in sandbox
-
-### Inline HTTP — BLOCKED
-Any Bash command containing `fetch('http`, `requests.get(`, `requests.post(`,
-`http.get(`, or `http.request(` is intercepted and replaced with an error message.
-Do NOT retry with Bash.
-Instead use:
-- `ctx_execute(language, code)` to run HTTP calls in sandbox — only stdout enters context
-
-### WebFetch — BLOCKED
-WebFetch calls are denied entirely. The URL is extracted and you are told to use `ctx_fetch_and_index` instead.
-Instead use:
-- `ctx_fetch_and_index(url, source)` then `ctx_search(queries)` to query the indexed content
-
-## REDIRECTED tools — use sandbox equivalents
-
-### Bash (>20 lines output)
-Bash is ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `yarn install`, `pip install`,
-and other short-output commands.
-For everything else, use:
-- `ctx_batch_execute(commands, queries)` — run multiple commands + search in ONE call
-- `ctx_execute(language: "shell", code: "...")` — run in sandbox, only stdout enters context
-
-### Read (for analysis)
-If you are reading a file to **Edit** it → Read is correct (Edit needs content in context).
-If you are reading to **analyze, explore, or summarize** →
-use `ctx_execute_file(path, language, code)` instead.
-Only your printed summary enters context. The raw file content stays in the sandbox.
-
-### Grep (large results)
-Grep results can flood context.
-Use `ctx_execute(language: "shell", code: "grep ...")` to run searches in sandbox.
-Only your printed summary enters context.
-
-## Tool selection hierarchy
-
-1. **GATHER**: `ctx_batch_execute(commands, queries)` — Primary tool.
-  Runs all commands, auto-indexes output, returns search results.
-  ONE call replaces 30+ individual calls.
-2. **FOLLOW-UP**: `ctx_search(queries: ["q1", "q2", ...])` —
-  Query indexed content. Pass ALL questions as array in ONE call.
-3. **PROCESSING**: `ctx_execute(language, code)` |
-  `ctx_execute_file(path, language, code)` —
-  Sandbox execution. Only stdout enters context.
-4. **WEB**: `ctx_fetch_and_index(url, source)` then
-  `ctx_search(queries)` — Fetch, chunk, index, query.
-  Raw HTML never enters context.
-5. **INDEX**: `ctx_index(content, source)` —
-  Store content in FTS5 knowledge base for later search.
-
-## Subagent routing
-
-When spawning subagents (Agent/Task tool), the routing block is automatically
-injected into their prompt. Bash-type subagents are upgraded to general-purpose
-so they have access to MCP tools.
-You do NOT need to manually instruct subagents about context-mode.
-
-## Output constraints
-
-- Keep responses under 500 words.
-- Write artifacts (code, configs, PRDs) to FILES — never return them
-  as inline text. Return only: file path + 1-line description.
-- When indexing content, use descriptive source labels so others can `ctx_search(source: "label")` later.
-
-## ctx commands
-
-| Command       | Action                                                                                |
-|---------------|---------------------------------------------------------------------------------------|
-| `ctx stats`   | Call the `ctx_stats` MCP tool and display the full output verbatim                    |
-| `ctx doctor`  | Call the `ctx_doctor` MCP tool, run the returned shell command, display as checklist  |
-| `ctx upgrade` | Call the `ctx_upgrade` MCP tool, run the returned shell command, display as checklist |