CC 2.1.116 adoption — version bump + matrix sync + agent-hooks audit

Bumps MIN_CC_VERSION 2.1.113 → 2.1.116. Registers 10 new features from the 2.1.116 block. Backfills 2.1.113/2.1.114 rows that never made it into the doc table. Audits all 14 OrchestKit agent hooks against the new main-thread firing behavior — all safe.

The shape of the change

-export const MIN_CC_VERSION = '2.1.113';
+export const MIN_CC_VERSION = '2.1.116';

// cc-version-matrix.ts — 323 → 333 entries
+ agent_hooks_main_thread            2.1.116
+ sandbox_rm_dangerous_path_fix      2.1.116
+ reload_plugins_auto_deps           2.1.116
+ doctor_while_responding            2.1.116
+ config_search_option_values        2.1.116
+ slash_no_match_empty_state         2.1.116
+ bash_gh_rate_limit_hint            2.1.116
+ usage_tab_immediate                2.1.116
+ terminal_setup_scroll_tuning       2.1.116
+ resume_large_sessions_fast         2.1.116

The one behavior change worth thinking about

agent_hooks_main_thread — main-thread firing of agent hooks

Before 2.1.116: agent-scoped hooks: frontmatter fired only when the agent ran as a subagent via the Task tool.
After 2.1.116: they also fire when a user invokes the agent as their main thread via claude --agent <name>.

Every existing OrchestKit agent hook was written with subagent context in mind. The question the audit had to answer: is any one of them broken or net-negative when it fires on the main thread too?

Agent hooks audit — all 14 unique hook commands

HookCategoryAgents using itMain-thread verdict
dangerous-command-blockerpretool/bash20 agentsNET POSITIVE — tool-level deny/ask/allow, context-agnostic
restrict-bashagent7 read-only agentsINTENTIONAL — read-only bash is the agent's design contract; main-thread should honor it
block-writesagent4 agentsNET POSITIVE — Write tool block, same semantics in both contexts
security-command-auditagent3 security agentsNET POSITIVE — logs only, uses CLAUDE_AGENT_ID for tagging
ci-safety-checkagentci-cd-engineerNET POSITIVE
deployment-safety-checkagentdeployment-managerNET POSITIVE
migration-safety-checkagentdatabase-engineerNET POSITIVE
git-validatorpretool/bash3 agentsNET POSITIVE
changelog-generatorpretool/bashrelease-engineerNET POSITIVE
ci-simulationpretool/bashci-cd-engineerNET POSITIVE
conflict-predictorpretool/bashgit-operations-engineerNET POSITIVE
pre-commit-simulationpretool/bashgit-operations-engineerNET POSITIVE
version-syncpretool/bashrelease-engineerNET POSITIVE
merge-readiness-checkerskillgit-operations-engineerNET POSITIVE

14 / 14 safe. No code changes required. Users who run claude --agent <ork-agent> now get the same defensive rails that subagent invocations always got.

Files touched

src/hooks/src/lib/cc-version-matrix.ts

MIN_CC_VERSION bump + 10 new entries. 323 → 333.

src/hooks/src/__tests__/lib/cc-version-matrix.test.ts

3 new boundary tests; missing-count assertions updated. 56/56 pass.

src/skills/configure/references/cc-version-settings.md

New "CC 2.1.116 Settings" section covering sandbox hardening, /reload-plugins deps, agent hooks main-thread.

src/skills/doctor/references/version-compatibility.md

Added 10 rows for 2.1.116, plus backfilled 10 rows for 2.1.113 and 1 for 2.1.114 that had been missing from the doc table.

CLAUDE.md

Version line: >= 2.1.113>= 2.1.116.

plugins/ork/** + src/hooks/dist/** + docs/site/lib/generated/**

Auto-regenerated from npm run build. Expected as part of OrchestKit's source → plugins sync.

What's explicitly NOT in this PR

Test plan

$ npm run build                  plugins/ assembled, 338 KB unified bundle
$ npm run typecheck            
$ npx vitest run cc-version-matrix  56/56
$ npm run test:skills            98 skills pass
$ npm run test:agents            37 agents pass
$ npm run test:security        13/13
$ npm run test:manifests         106/106 delivered