Agent Skills
› phuc-nt/my-translator
› ck:scout
ck:scout
GitHub利用并行代理快速扫描代码库,发现文件、收集任务上下文及搜索目录。适用于跨目录功能开发、调试前理解项目结构或定位文件位置等场景。
Trigger Scenarios
需要查找或定位特定文件
开始涉及多目录的功能开发
需要了解项目结构或功能分布
调试前需理解文件间关系
Install
npx skills add phuc-nt/my-translator --skill ck:scout -g -y
SKILL.md
Frontmatter
{
"name": "ck:scout",
"metadata": {
"author": "claudekit",
"version": "1.0.0"
},
"description": "Fast codebase scouting using parallel agents. Use for file discovery, task context gathering, quick searches across directories. Supports internal (Explore) and external (Gemini\/OpenCode) agents.",
"argument-hint": "[search-target] [ext]"
}
Scout
Fast, token-efficient codebase scouting using parallel agents to find files needed for tasks.
Arguments
- Default: Scout using built-in Explore subagents in parallel (
./references/internal-scouting.md) ext: Scout using external Gemini/OpenCode CLI tools in parallel (./references/external-scouting.md)
When to Use
- Beginning work on feature spanning multiple directories
- User mentions needing to "find", "locate", or "search for" files
- Starting debugging session requiring file relationships understanding
- User asks about project structure or where functionality lives
- Before changes that might affect multiple codebase parts
Quick Start
- Analyze user prompt to identify search targets
- Use a wide range of Grep and Glob patterns to find relevant files and estimate scale of the codebase
- Spawn parallel agents with divided directories
- Collect results into concise report
Configuration
Read from .opencode/.ck.json:
gemini.model- Gemini model (default:gemini-3-flash-preview)
Workflow
1. Analyze Task
- Parse user prompt for search targets
- Identify key directories, patterns, file types, lines of code
- Determine optimal SCALE value of subagents to spawn
2. Divide and Conquer
- Split codebase into logical segments per agent
- Assign each agent specific directories or patterns
- Ensure no overlap, maximize coverage
3. Register Scout Tasks
- Skip if: Agent count ≤ 2 (overhead exceeds benefit)
- Skip if: Task tools unavailable (VSCode extension) — use
TodoWriteinstead TaskListfirst — check for existing scout tasks in session- If not found,
TaskCreateper agent with scope metadata - See
references/task-management-scouting.mdfor patterns and examples
4. Spawn Parallel Agents
Load appropriate reference based on decision tree:
- Internal (Default):
references/internal-scouting.md(Explore subagents) - External:
references/external-scouting.md(Gemini/OpenCode)
Notes:
TaskUpdateeach task toin_progressbefore spawning its agent (skip if Task tools unavailable)- Prompt detailed instructions for each subagent with exact directories or files it should read
- Remember that each subagent has less than 200K tokens of context window
- Amount of subagents to-be-spawned depends on the current system resources available and amount of files to be scanned
- Each subagent must return a detailed summary report to a main agent
5. Collect Results
IMPORTANT: Invoke "/ck:project-organization" skill to organize the outputs.
- Timeout: 3 minutes per agent (skip non-responders)
TaskUpdatecompleted tasks; log timed-out agents in report (skip if Task tools unavailable)- Aggregate findings into single report
- List unresolved questions at end
Report Format
# Scout Report
## Relevant Files
- `path/to/file.ts` - Brief description
- ...
## Unresolved Questions
- Any gaps in findings
References
references/internal-scouting.md- Using Explore subagentsreferences/external-scouting.md- Using Gemini/OpenCode CLIreferences/task-management-scouting.md- Claude Task patterns for scout coordination
Version History
- 3495f99 Current 2026-07-25 07:20


