feat: add action-validator and clean up CI workflows (#513)

* chore(pre-commit): update hooks and add action-validator

Update uv-pre-commit 0.10.9→0.10.11 and checkov 3.2.508→3.2.510.
Normalize single quotes to double quotes in hook args.
Add action-validator v0.8.0 hook for GitHub Actions validation.

* fix(ci): clean up workflow path filters

Remove non-existent action.yaml paths from action-security workflow.
Fix glob patterns (**.md → **/*.md) in pr-lint workflow.
Remove unused trigger paths (yarn.lock, pnpm-lock.yaml,
requirements.txt, .github/labels.yml, docs/**) from security-suite
and sync-labels workflows.

* feat(make): add lint-actions target for action-validator

Add lint-actions target that runs action-validator via pre-commit.
Include it in the lint dependency list and .PHONY declaration.

* docs: add context-mode routing rules to CLAUDE.md

Add mandatory routing rules section for context-mode MCP plugin,
documenting blocked commands, redirected tools, tool selection
hierarchy, and output constraints.

* fix(lint): resolve action-validator failure on language-version-detect

- Remove unsupported `deprecated: true` from language-version-detect/action.yml
  (deprecation already communicated via description field)
- Scope action-validator pre-commit hook to workflow and action.yml files only
- Make missing pre-commit a hard error in lint-actions target

* fix(deps): update action pins and fix trivy-action version comment

Update SHA-pinned action references to latest versions:
- github/codeql-action v4.32.6 → v4.33.0
- nick-fields/retry v3.0.2 → v4.0.0
- actions/cache v5.0.3 → v5.0.4
- oven-sh/setup-bun v2.1.3 → v2.2.0
- softprops/action-gh-release v2.5.0 → v2.6.1
- github/issue-metrics v4.1.0 → v4.1.1
- shivammathur/setup-php 2.36.0 → 2.37.0
- astral-sh/setup-uv v7.5.0 → v7.6.0
- terraform-linters/setup-tflint v6.2.1 → v6.2.2
- aquasecurity/trivy-action: pin from master to v0.35.0

Fix pinact warning in docker-build by adding missing v prefix
to trivy-action version comment (0.35.0 → v0.35.0).

CLAUDE.md

@@ -168,3 +168,78 @@ Check: `make check-version-refs`
 ---
 
 All actions modular and externally usable. No exceptions to any rule.
+
+## 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`, `npm 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 |