@kaitranntt/ccs 4.3.2 → 4.3.3

package/.claude/commands/ccs/continue.md

@@ -0,0 +1,15 @@
+---
+description: Continue last CCS delegation session [AUTO ENHANCE]
+argument-hint: [follow-up instruction]
+---
+
+Activate `ccs-delegation` skill. The skill contains all execution logic.
+
+Task: Detect last-used profile from `~/.ccs/delegation-sessions.json`, parse `$ARGUMENTS`, enhance with previous context, execute continuation via CCS CLI.
+
+**Examples:**
+```
+/ccs:continue "also update the examples section"  # Use last profile
+/ccs:continue --glm "add unit tests"              # Switch profiles
+/ccs:continue "/commit with message"              # Nested slash command
+```

package/.claude/commands/ccs.md

@@ -0,0 +1,17 @@
+---
+description: Delegate task with intelligent profile selection [AUTO ENHANCE]
+argument-hint: [task description]
+---
+
+Activate `ccs-delegation` skill. The skill contains all execution logic.
+
+Task: Parse `$ARGUMENTS`, select optimal profile from `~/.ccs/config.json`, enhance prompt, execute delegation via CCS CLI.
+
+**Examples:**
+```
+/ccs "refactor auth.js to use async/await"    # Simple task
+/ccs "analyze entire architecture"            # Long-context task
+/ccs "think about caching strategy"           # Reasoning task
+/ccs --glm "add tests for UserService"        # Force specific profile
+/ccs "/cook create landing page"              # Nested slash command
+```

package/.claude/skills/ccs-delegation/CLAUDE.md.template

@@ -2,6 +2,16 @@
 
 Activate `ccs-delegation` skill for automatic delegation of eligible tasks.
 
+**Commands:**
+- `/ccs "task"` - Auto-select best profile (glm/kimi/custom)
+- `/ccs:continue "follow-up"` - Continue last session
+- `/ccs --glm "task"` - Force specific profile
+
 **Auto-delegates:** typo fixes, test additions, refactoring, JSDoc, docs updates
 **Override:** Say "don't delegate" to bypass automation
-**Commands:** `/ccs:glm "task"` or `/ccs:kimi "task"` for explicit delegation
+
+**Examples:**
+- "use ccs to fix typos in README" → Auto-selects glm
+- "use ccs to analyze architecture" → Auto-selects kimi
+- "use ccs --glm to add tests" → Forces glm
+- "use ccs:continue to commit" → Continues last session

package/.claude/skills/ccs-delegation/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: ccs-delegation
-description: AUTO-ACTIVATE for delegation-eligible tasks. Triggers on patterns like "fix typos", "add tests", "refactor to use", "add JSDoc", "analyze architecture". Also activates when user says "use ccs glm/kimi". Handles task validation, prompt enhancement, and execution via CCS CLI headless mode.
-version: 2.6.0
+description: Auto-activate CCS CLI delegation for deterministic tasks. Parses user input, auto-selects optimal profile (glm/kimi/custom) from ~/.ccs/config.json, enhances prompts with context, executes via `ccs {profile} -p "task"` or `ccs {profile}:continue`, and reports results. Trigger: "use ccs [task]" patterns, typo/test/refactor keywords. Excludes: complex architecture, security-critical code, performance optimization, breaking changes.
+version: 3.0.0
 ---
 
 # CCS Delegation
@@ -10,50 +10,94 @@ Delegate deterministic tasks to cost-optimized models via CCS CLI.
 
 ## Core Concept
 
-Execute tasks via alternative models using `ccs {profile} -p "task"` equivalent to `claude --settings ~/.ccs/{profile}.settings -p "task"`
+Execute tasks via alternative models using:
+- **Initial delegation**: `ccs {profile} -p "task"`
+- **Session continuation**: `ccs {profile}:continue -p "follow-up"`
 
-**Profiles:** GLM (cost-optimized), Kimi (long-context)
+**Profile Selection:**
+- Auto-select from `~/.ccs/config.json` via task analysis
+- Profiles: glm (cost-optimized), kimi (long-context/reasoning), custom profiles
+- Override: `--{profile}` flag forces specific profile
 
 ## User Invocation Patterns
 
 Users trigger delegation naturally:
-- "use ccs glm [task]" - Delegate to GLM (cost-optimized)
-- "use ccs kimi [task]" - Delegate to Kimi (long-context)
-- "use ccs glm:continue [task]" - Continue GLM session
-- "use ccs kimi:continue [task]" - Continue Kimi session
+- "use ccs [task]" - Auto-select best profile
+- "use ccs --glm [task]" - Force GLM profile
+- "use ccs --kimi [task]" - Force Kimi profile
+- "use ccs:continue [task]" - Continue last session
 
 **Examples:**
-- "use ccs glm to fix typos in README.md"
-- "use ccs kimi to analyze the entire architecture"
-- "use ccs glm:continue to add unit tests"
+- "use ccs to fix typos in README.md"
+- "use ccs to analyze the entire architecture"
+- "use ccs --glm to add unit tests"
+- "use ccs:continue to commit the changes"
 
 ## Agent Response Protocol
 
-When user says "use ccs {profile} [task]":
-
-1. **Validate eligibility** against Decision Framework
-   - Check: Simple, mechanical, <5 files
-   - Check: No design decisions required
-   - Check: Clear acceptance criteria exists
-
-2. **Enhance prompt** with context:
-   - Add file paths if mentioned
-   - Include working directory
-   - Specify success criteria
-   - Add relevant constraints
-
-3. **Execute via Bash tool**:
-   ```bash
-   ccs {profile} -p "enhanced prompt"
-   ```
-
-4. **Report results** to user:
-   - Cost (USD)
-   - Duration (seconds)
-   - Session ID (for continuation)
-   - Exit code/status
-
-**If ineligible:** Explain why and handle in main session.
+**For `/ccs [task]`:**
+
+1. **Parse override flag**
+   - Scan task for pattern: `--(\w+)`
+   - If match: `profile = match[1]`, remove flag from task, skip to step 5
+   - If no match: continue to step 2
+
+2. **Discover profiles**
+   - Read `~/.ccs/config.json` using Read tool
+   - Extract `Object.keys(config.profiles)` → `availableProfiles[]`
+   - If file missing → Error: "CCS not configured. Run: ccs doctor"
+   - If empty → Error: "No profiles in config.json"
+
+3. **Analyze task requirements**
+   - Scan task for keywords:
+     - `/(think|analyze|reason|debug|investigate|evaluate)/i` → `needsReasoning = true`
+     - `/(architecture|entire|all files|codebase|analyze all)/i` → `needsLongContext = true`
+     - `/(typo|test|refactor|update|fix)/i` → `preferCostOptimized = true`
+
+4. **Select profile**
+   - For each profile in `availableProfiles`: classify by name pattern (see Profile Characteristic Inference table)
+   - If `needsReasoning`: filter profiles where `reasoning=true` → prefer kimi
+   - Else if `needsLongContext`: filter profiles where `context=long` → prefer kimi
+   - Else: filter profiles where `cost=low` → prefer glm
+   - `selectedProfile = filteredProfiles[0]`
+   - If `filteredProfiles.length === 0`: fallback to `glm` if exists, else first available
+   - If no profiles: Error
+
+5. **Enhance prompt**
+   - If task mentions files: gather context using Read tool
+   - Add: file paths, current implementation, expected behavior, success criteria
+   - Preserve slash commands at task start (e.g., `/cook`, `/commit`)
+
+6. **Execute delegation**
+   - Run: `ccs {selectedProfile} -p "$enhancedPrompt"` via Bash tool
+
+7. **Report results**
+   - Log: "Selected {profile} (reason: {reasoning/long-context/cost-optimized})"
+   - Report: Cost (USD), Duration (sec), Session ID, Exit code
+
+**For `/ccs:continue [follow-up]`:**
+
+1. **Detect profile**
+   - Read `~/.ccs/delegation-sessions.json` using Read tool
+   - Find most recent session (latest timestamp)
+   - Extract profile name from session data
+   - If no sessions → Error: "No previous delegation. Use /ccs first"
+
+2. **Parse override flag**
+   - Scan follow-up for pattern: `--(\w+)`
+   - If match: `profile = match[1]`, remove flag from follow-up, log profile switch
+   - If no match: use detected profile from step 1
+
+3. **Enhance prompt**
+   - Review previous work (check what was accomplished)
+   - Add: previous context, incomplete tasks, validation criteria
+   - Preserve slash commands at start
+
+4. **Execute continuation**
+   - Run: `ccs {profile}:continue -p "$enhancedPrompt"` via Bash tool
+
+5. **Report results**
+   - Report: Profile, Session #, Incremental cost, Total cost, Duration, Exit code
 
 ## Decision Framework
 
@@ -69,18 +113,58 @@ When user says "use ccs {profile} [task]":
 - Performance optimization
 - Breaking changes/migrations
 
-## Profile Selection
+## Profile Selection Logic
+
+**Task Analysis Keywords** (scan task string with regex):
+
+| Pattern | Variable | Example |
+|---------|----------|---------|
+| `/(think\|analyze\|reason\|debug\|investigate\|evaluate)/i` | `needsReasoning = true` | "think about caching" |
+| `/(architecture\|entire\|all files\|codebase\|analyze all)/i` | `needsLongContext = true` | "analyze all files" |
+| `/(typo\|test\|refactor\|update\|fix)/i` | `preferCostOptimized = true` | "fix typo in README" |
+
+**Profile Characteristic Inference** (classify by name pattern):
+
+| Profile Pattern | Cost | Context | Reasoning |
+|----------------|------|---------|-----------|
+| `/^glm/i` | low | standard | false |
+| `/^kimi/i` | medium | long | true |
+| `/^claude/i` | high | standard | false |
+| others | low | standard | false |
+
+**Selection Algorithm** (apply filters sequentially):
+
+```
+profiles = Object.keys(config.profiles)
+classified = profiles.map(p => ({name: p, ...inferCharacteristics(p)}))
+
+if (needsReasoning):
+  filtered = classified.filter(p => p.reasoning === true).sort(['kimi'])
+else if (needsLongContext):
+  filtered = classified.filter(p => p.context === 'long').sort(['kimi'])
+else:
+  filtered = classified.filter(p => p.cost === 'low').sort(['glm', ...])
+
+selected = filtered[0] || profiles.find(p => p === 'glm') || profiles[0]
+if (!selected): throw Error("No profiles configured")
+
+log("Selected {selected} (reason: {reasoning|long-context|cost-optimized})")
+```
 
-- **GLM**: Simple tasks (<5 files, clear scope, cost-optimized)
-- **Kimi**: Long-context (multi-file analysis, architecture docs)
+**Override Logic**:
+- Parse task for `/--(\w+)/`. If match: `profile = match[1]`, remove from task, skip selection
 
 ## Example Delegation Tasks
 
 **Good candidates:**
-- "add unit tests for UserService using Jest"
-- "fix typos in README.md"
-- "refactor parseConfig to use destructuring"
-- "add JSDoc comments to auth.js"
+- "/ccs add unit tests for UserService using Jest"
+  → Auto-selects: glm (simple task)
+- "/ccs analyze entire architecture in src/"
+  → Auto-selects: kimi (long-context)
+- "/ccs think about the best database schema design"
+  → Auto-selects: kimi (reasoning)
+- "/ccs --glm refactor parseConfig to use destructuring"
+  → Forces: glm (override)
 
 **Bad candidates (keep in main):**
 - "implement OAuth" (too complex, needs design)
@@ -89,9 +173,15 @@ When user says "use ccs {profile} [task]":
 
 ## Execution
 
-Slash commands: `/ccs:glm "task"` or `/ccs:glm:continue "follow-up"`
+**Commands:**
+- `/ccs "task"` - Intelligent delegation (auto-select profile)
+- `/ccs --{profile} "task"` - Force specific profile
+- `/ccs:continue "follow-up"` - Continue last session (auto-detect profile)
+- `/ccs:continue --{profile} "follow-up"` - Continue with profile switch
 
-Agent via Bash: `ccs glm -p "task"` or `ccs glm:continue -p "follow-up"`
+**Agent via Bash:**
+- Auto: `ccs {auto-selected} -p "task"`
+- Continue: `ccs {detected}:continue -p "follow-up"`
 
 ## References
 

package/.claude/skills/ccs-delegation/references/troubleshooting.md

@@ -195,11 +195,6 @@ jq '.glm.turns' ~/.ccs/delegation-sessions.json
 rm ~/.ccs/delegation-sessions.json  # Fresh start (loses all sessions)
 ```
 
-**Bypass delegation (use CLI directly):**
-```bash
-claude -p "task" --settings ~/.ccs/{profile}.settings.json
-```
-
 **Interactive mode (no -p flag):**
 ```bash
 ccs {profile}  # Opens interactive session

package/README.md

@@ -322,7 +322,7 @@ graph LR
 ```plaintext
 ~/.ccs/
 ├── .claude/                 # CCS items (ships with package, v4.1)
-│   ├── commands/ccs/        # Delegation commands (/ccs:glm, /ccs:kimi)
+│   ├── commands/ccs/        # Delegation commands (/ccs, /ccs:continue)
 │   ├── skills/ccs-delegation/  # AI decision framework
 │   └── agents/ccs-delegator.md # Proactive delegation agent
 ├── shared/                  # Symlinks to ~/.claude/ (for profiles)
@@ -401,7 +401,7 @@ ccs --help       # Show all commands and options
 
 ### What is Delegation?
 
-CCS Delegation lets you **send tasks to alternative models** (`glm`, `kimi`) **from your main Claude session** using the `-p` flag or slash commands (`/ccs:glm`, `/ccs:kimi`).
+CCS Delegation lets you **send tasks to alternative models** (`glm`, `kimi`) **from your main Claude session** using the `-p` flag or intelligent slash commands (`/ccs`, `/ccs:continue`).
 
 **Why use it?**
 - **Token efficiency**: Simple tasks cost 81% less on GLM vs main Claude session
@@ -426,9 +426,10 @@ ccs glm:continue -p "run the tests and fix any failures"
 **Via Slash Commands** (inside Claude sessions):
 ```bash
 # In your main Claude session:
-/ccs:glm "refactor auth.js to use async/await"
-/ccs:kimi "find all deprecated API usages across codebase"
-/ccs:glm:continue "also update the README examples"
+/ccs "refactor auth.js to use async/await"           # Auto-selects best profile
+/ccs --glm "fix typo in documentation"               # Forces GLM profile
+/ccs --kimi "analyze entire architecture"            # Forces Kimi profile
+/ccs:continue "also update the README examples"      # Continues last session
 ```
 
 **Via Natural Language** (Claude auto-delegates):

package/VERSION

@@ -1 +1 @@
-4.3.2
+4.3.3

package/bin/ccs.js

@@ -172,8 +172,10 @@ function handleHelpCommand() {
 
   // Delegation (inside Claude Code CLI)
   console.log(colored('Delegation (inside Claude Code CLI):', 'cyan'));
-  console.log(`  ${colored('/ccs:glm "task"', 'yellow')}             Delegate to GLM-4.6 for simple tasks`);
-  console.log(`  ${colored('/ccs:kimi "task"', 'yellow')}            Delegate to Kimi for long context`);
+  console.log(`  ${colored('/ccs "task"', 'yellow')}                Delegate task (auto-selects best profile)`);
+  console.log(`  ${colored('/ccs --glm "task"', 'yellow')}           Force GLM-4.6 for simple tasks`);
+  console.log(`  ${colored('/ccs --kimi "task"', 'yellow')}          Force Kimi for long context`);
+  console.log(`  ${colored('/ccs:continue "follow-up"', 'yellow')}    Continue last delegation session`);
   console.log('  Save tokens by delegating simple tasks to cost-optimized models');
   console.log('');
 

package/bin/delegation/README.md

@@ -25,7 +25,7 @@ Enhanced Claude Code delegation system for multi-model task delegation.
 
 ### Session Management
 - Persistence: `~/.ccs/delegation-sessions.json`
-- Resume via `/ccs:glm:continue` and `/ccs:kimi:continue`
+- Resume via `/ccs:continue` (auto-detects profile)
 - Auto-cleanup expired sessions (>30 days)
 - Cost aggregation across turns
 
@@ -91,12 +91,13 @@ Automatically applied as CLI flags:
 The delegation system is invoked via simple slash commands in `.claude/commands/ccs/`:
 
 ### Basic Commands
-- `/ccs:glm "task"` - Delegate to GLM-4.6
-- `/ccs:kimi "task"` - Delegate to Kimi (long-context)
+- `/ccs "task"` - Delegate task (auto-selects best profile)
+- `/ccs --glm "task"` - Force GLM-4.6 delegation
+- `/ccs --kimi "task"` - Force Kimi delegation (long-context)
 
-### Multi-Turn Commands
-- `/ccs:glm:continue "follow-up"` - Resume last GLM session
-- `/ccs:kimi:continue "follow-up"` - Resume last Kimi session
+### Session Continuation
+- `/ccs:continue "follow-up"` - Resume last delegation session (auto-detect profile)
+- `/ccs:continue --glm "follow-up"` - Resume with specific profile switch
 
 Each command directly invokes:
 ```bash
@@ -143,7 +144,8 @@ node tests/unit/delegation/result-formatter.test.js
 ## Architecture
 
 ```
-User → SlashCommand (/ccs:glm)
+User → SlashCommand (/ccs)
+  → ccs-delegation skill (auto-selects profile)
   → Directly invokes: claude -p
     → HeadlessExecutor (monitors execution)
       → SessionManager (load last session)

package/bin/management/doctor.js

@@ -364,12 +364,12 @@ class Doctor {
   checkDelegation() {
     const spinner = ora('Checking delegation').start();
 
-    // Check if delegation commands exist in ~/.ccs/.claude/commands/ccs/
-    const ccsClaudeCommandsDir = path.join(this.ccsDir, '.claude', 'commands', 'ccs');
-    const hasGlmCommand = fs.existsSync(path.join(ccsClaudeCommandsDir, 'glm.md'));
-    const hasKimiCommand = fs.existsSync(path.join(ccsClaudeCommandsDir, 'kimi.md'));
+    // Check if delegation commands exist in ~/.ccs/.claude/commands/
+    const ccsClaudeCommandsDir = path.join(this.ccsDir, '.claude', 'commands');
+    const hasCcsCommand = fs.existsSync(path.join(ccsClaudeCommandsDir, 'ccs.md'));
+    const hasContinueCommand = fs.existsSync(path.join(ccsClaudeCommandsDir, 'ccs', 'continue.md'));
 
-    if (!hasGlmCommand || !hasKimiCommand) {
+    if (!hasCcsCommand || !hasContinueCommand) {
       spinner.warn(`  ${'Delegation'.padEnd(26)}${colored('[!]', 'yellow')}  Not installed`);
       this.results.addCheck(
         'Delegation',

package/lib/ccs

@@ -2,7 +2,7 @@
 set -euo pipefail
 
 # Version (updated by scripts/bump-version.sh)
-CCS_VERSION="4.3.2"
+CCS_VERSION="4.3.3"
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 readonly CONFIG_FILE="${CCS_CONFIG:-$HOME/.ccs/config.json}"
 readonly PROFILES_JSON="$HOME/.ccs/profiles.json"
@@ -191,8 +191,10 @@ show_help() {
   echo ""
 
   echo -e "${CYAN}Delegation (inside Claude Code CLI):${RESET}"
-  echo -e "  ${YELLOW}/ccs:glm \"task\"${RESET}             Delegate to GLM-4.6 for simple tasks"
-  echo -e "  ${YELLOW}/ccs:kimi \"task\"${RESET}            Delegate to Kimi for long context"
+  echo -e "  ${YELLOW}/ccs \"task\"${RESET}                Delegate task (auto-selects best profile)"
+  echo -e "  ${YELLOW}/ccs --glm \"task\"${RESET}           Force GLM-4.6 for simple tasks"
+  echo -e "  ${YELLOW}/ccs --kimi \"task\"${RESET}          Force Kimi for long context"
+  echo -e "  ${YELLOW}/ccs:continue \"follow-up\"${RESET}    Continue last delegation session"
   echo -e "  Save tokens by delegating simple tasks to cost-optimized models"
   echo ""
 

package/lib/ccs.ps1

@@ -12,7 +12,7 @@ param(
 $ErrorActionPreference = "Stop"
 
 # Version (updated by scripts/bump-version.sh)
-$CcsVersion = "4.3.2"
+$CcsVersion = "4.3.3"
 $ScriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
 $ConfigFile = if ($env:CCS_CONFIG) { $env:CCS_CONFIG } else { "$env:USERPROFILE\.ccs\config.json" }
 $ProfilesJson = "$env:USERPROFILE\.ccs\profiles.json"
@@ -238,8 +238,10 @@ function Show-Help {
     Write-Host ""
 
     Write-ColorLine "Delegation (inside Claude Code CLI):" "Cyan"
-    Write-ColorLine "  /ccs:glm `"task`"             Delegate to GLM-4.6 for simple tasks" "Yellow"
-    Write-ColorLine "  /ccs:kimi `"task`"            Delegate to Kimi for long context" "Yellow"
+    Write-ColorLine "  /ccs `"task`"                Delegate task (auto-selects best profile)" "Yellow"
+    Write-ColorLine "  /ccs --glm `"task`"           Force GLM-4.6 for simple tasks" "Yellow"
+    Write-ColorLine "  /ccs --kimi `"task`"          Force Kimi for long context" "Yellow"
+    Write-ColorLine "  /ccs:continue `"follow-up`"    Continue last delegation session" "Yellow"
     Write-Host "  Save tokens by delegating simple tasks to cost-optimized models"
     Write-Host ""
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kaitranntt/ccs",
-  "version": "4.3.2",
+  "version": "4.3.3",
   "description": "Claude Code Switch - Instant profile switching between Claude Sonnet 4.5 and GLM 4.6",
   "keywords": [
     "cli",

package/.claude/commands/ccs/glm/continue.md

@@ -1,21 +0,0 @@
----
-description: Continue last GLM delegation session [AUTO ENHANCE]
-argument-hint: [follow-up instruction]
----
-
-Continue last GLM delegation session for iterative refinement.
-
-**Workflow:**
-- Review what was accomplished in previous session
-- Analyze the follow-up instruction in `$ARGUMENTS`
-- Enhance prompt with context (reference files, incomplete tasks, next steps)
-- Execute continuation via `ccs glm:continue -p "$ENHANCED_PROMPT"`
-
-**Note:** `$ENHANCED_PROMPT` is an enhanced version that references previous work, highlights incomplete tasks, and adds specific validation criteria. If the follow-up contains a slash command (e.g., /commit), keep it at the start of the enhanced prompt.
-
-**Usage:**
-```
-/ccs:glm "fix typo in README"
-/ccs:glm:continue "also update the examples section"
-/ccs:glm:continue "/commit with descriptive message"
-```

package/.claude/commands/ccs/glm.md

@@ -1,21 +0,0 @@
----
-description: Delegate task to GLM-4.6 (cost-optimized model) [AUTO ENHANCE]
-argument-hint: [task description]
----
-
-Delegate simple, deterministic tasks to GLM-4.6 for token optimization.
-
-**Workflow:**
-- Analyze the task description in `$ARGUMENTS`
-- Gather context if needed (read files, check structure)
-- Enhance prompt with specific details (file paths, context, success criteria)
-- Execute delegation via `ccs glm -p "$ENHANCED_PROMPT"`
-
-**Note:** `$ENHANCED_PROMPT` is an enhanced version that adds specifics like file paths, current implementation context, expected behavior, and success criteria. If the task contains a slash command (e.g., /cook, /plan), keep it at the start of the enhanced prompt.
-
-**Usage:**
-```
-/ccs:glm "refactor auth.js to use async/await"
-/ccs:glm "add tests for UserService"
-/ccs:glm "/cook create a landing page"
-```

package/.claude/commands/ccs/kimi/continue.md

@@ -1,21 +0,0 @@
----
-description: Continue last Kimi delegation session [AUTO ENHANCE]
-argument-hint: [follow-up instruction]
----
-
-Continue last Kimi delegation session for multi-turn analysis.
-
-**Workflow:**
-- Review analysis/work from previous session
-- Analyze the follow-up instruction in `$ARGUMENTS`
-- Enhance prompt with comprehensive context (findings, scope, deliverables, priority)
-- Execute continuation via `ccs kimi:continue -p "$ENHANCED_PROMPT"`
-
-**Note:** `$ENHANCED_PROMPT` is an enhanced version that references previous findings, specifies next scope, and adds actionable deliverables with priorities. If the follow-up contains a slash command (e.g., /plan), keep it at the start of the enhanced prompt.
-
-**Usage:**
-```
-/ccs:kimi "analyze all files in src/"
-/ccs:kimi:continue "suggest architectural improvements"
-/ccs:kimi:continue "/plan for refactoring with phases"
-```

package/.claude/commands/ccs/kimi.md

@@ -1,21 +0,0 @@
----
-description: Delegate task to Kimi (long-context model) [AUTO ENHANCE]
-argument-hint: [task description]
----
-
-Delegate long-context, multi-file tasks to Kimi for comprehensive analysis.
-
-**Workflow:**
-- Analyze the task description in `$ARGUMENTS`
-- Gather context across multiple files/directories
-- Enhance prompt with comprehensive details (structure, relationships, scope)
-- Execute delegation via `ccs kimi -p "$ENHANCED_PROMPT"`
-
-**Note:** `$ENHANCED_PROMPT` is an enhanced version that adds directory structures, cross-file relationships, architecture context, and deliverables. If the task contains a slash command (e.g., /plan, /commit), keep it at the start of the enhanced prompt.
-
-**Usage:**
-```
-/ccs:kimi "analyze all files in src/ and document architecture"
-/ccs:kimi "find all deprecated API usages across codebase"
-/ccs:kimi "/plan for authentication system"
-```