メニュー
How to use Forge to submit headless agent jobs, check status, and retrieve output via MCP tools. Use when the user wants to delegate work to a background agent, run a task on another LLM, or interact with forge.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Create or update the project security baseline, profile, suppressions file, and gitignore entries for security scans
Fix or guide remediation for a specific security finding from the latest scan report
Run a security assessment using deterministic static analysis tools with LLM-powered triage
Inspect and optionally install security scanning tools for the security plugin
Query ctx memory and inject results into context
Show ctx memory status (node counts, types, tiers, tokens)
SOC 職業分類に基づく
| name | use |
| description | How to use Forge to submit headless agent jobs, check status, and retrieve output via MCP tools. Use when the user wants to delegate work to a background agent, run a task on another LLM, or interact with forge. |
| user-invocable | true |
Forge runs tasks on LLM agents in the background via a daemon. Interact through MCP tools.
Submit a job. Returns a job ID.
Required: task (string) - the prompt/task description.
Optional:
| Parameter | Type | Description |
|---|---|---|
agent | string | claude (default), gemini, local, lmstudio |
model | string | Agent-specific: sonnet, haiku, opus, gemini-2.5-pro, etc. |
timeout | string | Duration: 30s, 10m (default), 1h |
input_files | string[] | File paths to include as context |
output_format | string | markdown (default), json, yaml, code, raw |
constraints | string[] | Output validation constraints |
tags | string[] | Tags for filtering/organization |
Check job status. Required: job_id (string).
Get completed job result. Required: job_id (string).
Returns: output content, metadata (agent, model, duration, tokens, cost).
List jobs. Optional: status filter (pending, running, completed, failed), limit (default 20).
1. forge_submit → returns job_id
2. forge_status → poll until "completed" or "failed"
3. forge_output → retrieve the result
pending → claimed → dispatched → running → validating → delivering → completed
Any state can transition to failed.
pending, check with forge_status or run /forge:setup.forge_list to monitor.["non-empty", "min-length:100"]).