Context Loader
Reads AGENTS.md + project structure + existing skills to build an execution-aware context before any operation
- License 许可
- MIT
- 最近更新
- 2026-06-22
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- Context Loader
- tags
- [ "context", "initialization", "project-awareness" ]
- author
- ForgeWeave Core
- version
- 1.0.0
- skill_id
- context-loader
- description
- Reads AGENTS.md + project structure + existing skills to build an execution-aware context before any operation
- tui_compatibility
- [ "opencode", "claude", "gemini", "qwen" ]
02 资源文件 2
- 参考文档references/project-scan-checklist.md857 B
- 脚本scripts/scan_project.py1.8 KB
03 SKILL.md 正文
Context Loader
Purpose
Before any operation begins, load and understand the full project context: AGENTS.md, project structure, available skills, MCP server configuration, and key files. Ensures every subsequent action is informed by the project's conventions and capabilities.
When to Use
- Starting a new session on a ForgeWeave project
- Before running any skill or workflow that depends on project structure
- The agent needs to understand what agents and skills are available
- After
forge inithas scaffolded a new project
When Not to Use
- The task is outside the project (e.g., general knowledge question)
- Context has already been loaded in the current session
- The task is a simple isolated operation
Inputs
| Input | Type | Required | Description |
|---|---|---|---|
project_root |
string | No (default: cwd) | Path to project root |
Expected Outputs
| Output | Description |
|---|---|
| Project overview | Project type, TUI, key structure |
| Available agents | List of registered agents from AGENTS.md |
| Available skills | List of skills with their purposes |
| MCP configuration | Which MCP servers are configured |
| Key files | Paths to important config files |
Exact Workflow Steps
- Read AGENTS.md for agent registration and configuration
- Scan
.<tui>/skills/for available skills and their SKILL.md descriptions - Read
.<tui>/opencode.jsonor equivalent for MCP server config - Read RESEARCH_INSTRUCTIONS.md if present
- Identify the TUI being used from the project structure
- Compile a context summary for the agent to use
Required Checks
- [ ] AGENTS.md was found and parsed
- [ ] Skills directory was scanned
- [ ] MCP configuration was loaded
- [ ] TUI was identified
Failure Modes
| Failure Condition | Response |
|---|---|
| No AGENTS.md found | Report: "Not a ForgeWeave project — run forge init first" |
| Skills directory missing | Report: "No skills directory found — run forge init" |
| MCP config missing | Proceed with limited capabilities |
References
| Reference | Path |
|---|---|
| AGENTS.md | ./AGENTS.md |
| AGENT_SPEC.md | ./AGENT_SPEC.md |
04 同仓库更多 Skills
Workflow Orchestrator
Coordinates multi-skill execution pipelines (e.g., research → plan → build → test)
Web Research
Browser-driven or scraping-based skill for real-time internet extraction using Playwright and HTTP-based fetching
Validation Engine
Checks outputs from other skills for consistency, correctness, and adherence to AGENTS.md rules
Tool Selector
Determines which tools, APIs, MCP actions, or system capabilities are required for a given task
Test Generator
Creates test plans and test cases (unit, integration, edge cases) based on existing or planned code
Skill Generator
Meta-skill that creates new SKILL.md files from research outputs and patterns discovered in execution