Skip to content
Skills Library
AI & agents · Tool integration

use

/use

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.

Author
Zate ↗
Repository
cc-plugins ↗
Licence
MIT
Last repository change
13.05.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 13.05.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

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.

Original author 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.

How it works

  1. MCP Tools
  2. Workflow
  3. Job States
  4. Tips
  5. When NOT to Use
Original SKILL.md headings · 61 lines, 321 words
SKILL.md preview
---
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: Headless Agent Job Runner

Forge runs tasks on LLM agents in the background via a daemon. Interact through MCP tools.

## MCP Tools

### forge_submit
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 |

### forge_status
Check job status. **Required:** `job_id` (string).

### forge_output
Get completed job result. **Required:** `job_id` (string).
Returns: output content, metadata (agent, model, duration, tokens, cost).

### forge_list
List jobs. **Optional:** `status` filter (`pending`, `running`, `completed`, `failed`), `limit` (default 20).

## Workflow

```
1. forge_submit  →  returns job_id
2. forge_status  →  poll until "completed" or "failed"
3. forge_output  →  retrieve the result
```

## Job States

`pending` → `claimed` → `dispatched` → `running` → `validating` → `delivering` → `completed`

Any state can transition to `failed`.

## Tips

- **Daemon must be running** for jobs to process. If jobs stay `pending`, check with `forge_status` or run `/forge:setup`.
- **Jobs are async** - submit returns immediately. Poll status or use `forge_list` to monitor.
- **Claude agent** uses Claude CLI with full tool use (file editing, bash). Other agents are completion-only.
- **Input files** let you pass context files to the job agent.
- **Constraints** validate output (e.g., `["non-empty", "min-length:100"]`).

## When NOT to Use

- For tasks that should happen in the current session (just do them directly).
- When you need interactive back-and-forth with the user during the task.
- Forge is for fire-and-forget background work.

Versions

RepositoryScoreLicence
This page · Zate/cc-plugins100MIT
melodic-software/claude-code-plugins84MIT

Database snapshot: 13.11.2026 · package version 539b44120252 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90Core NXTG-Forge
    Ground truth for the NXTG-Forge platform — the real forge CLI subcommands, the /nxtg-forge:* slash commands, the .forge/state.json + events.jsonl model, both MCP servers (Rust orchestrator + Node governance), the agent roster, and the security hooks. Use when working inside or…
  • 100skf-setup
    Initialize forge environment, detect tools, and set capability tier (Quick/Forge/Forge+/Deep). Use when the user requests to "set up the forge" or "initialize the forge".
  • 100tool-forge
    自适应工具铸造:探测 TOOL_GAP 后为当前 Agent 铸造工具与技能骨架并登记能力目录。触发词:缺工具、TOOL_GAP、造一个工具、自适应构建、forge、工具铸造、补技能。
  • 100forge-install
    This skill should be used when the user wants to "install the Forge plugin", "set up Forge", "install forge-agent-lens-for-claude-code", "configure Forge for the first time", "get started with Forge tracing", or needs to complete the initial setup of the Forge Agent Lens for…
  • 100background-prompt
    Execute a task in the background with a prompt through the core engine LLM provider and return plain text output. Use when the user wants to run a prompt as a background task via the Agent CLI.
  • 100forge-status
    This skill should be used when the user wants to "check Forge status", "verify the Forge plugin is running", "see if Forge is set up correctly", "check Forge configuration", "is Forge working", "Forge is running an older config", "the daemon is on an old config", or needs to…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.