openclaw/docs/prose.md

title, sidebarTitle, summary, read_when

title	sidebarTitle	summary	read_when
OpenProse	OpenProse	OpenProse is a markdown-first workflow format for multi-agent AI sessions. In OpenClaw it ships as a plugin with a /prose slash command and a skill pack.	You want to run or write .prose workflow files You want to enable the OpenProse plugin You need to understand how OpenProse maps to OpenClaw primitives

OpenProse is a portable, markdown-first workflow format for orchestrating AI sessions. In OpenClaw it ships as a plugin that installs an OpenProse skill pack and a /prose slash command. Programs live in .prose files and can spawn multiple sub-agents with explicit control flow.

Enable the OpenProse plugin and restart the Gateway. Use `/prose run` to execute a `.prose` file or remote program. Author multi-agent workflows with parallel and sequential steps.

Install

Bundled plugins are disabled by default. Enable OpenProse:

```bash
openclaw plugins enable open-prose
```

```bash openclaw gateway restart ``` ```bash openclaw plugins list | grep prose ```

You should see `open-prose` as enabled. The `/prose` skill command is now
available in chat.

For a local checkout: openclaw plugins install ./path/to/local/open-prose-plugin

Slash command

OpenProse registers /prose as a user-invocable skill command:

/prose help
/prose run <file.prose>
/prose run <handle/slug>
/prose run <https://example.com/file.prose>
/prose compile <file.prose>
/prose examples
/prose update

/prose run <handle/slug> resolves to https://p.prose.md/<handle>/<slug>. Direct URLs are fetched as-is using the web_fetch tool.

Top-level remote runs are explicit. Remote imports inside a .prose program are transitive code dependencies: before OpenProse fetches any remote use target, it shows the resolved import list and requires the operator to reply exactly approve remote prose imports for that run.

What it can do

• Multi-agent research and synthesis with explicit parallelism.
• Repeatable, approval-safe workflows (code review, incident triage, content pipelines).
• Reusable .prose programs you can run across supported agent runtimes.

Example: parallel research and synthesis

# Research + synthesis with two agents running in parallel.

input topic: "What should we research?"

agent researcher:
  model: sonnet
  prompt: "You research thoroughly and cite sources."

agent writer:
  model: opus
  prompt: "You write a concise summary."

parallel:
  findings = session: researcher
    prompt: "Research {topic}."
  draft = session: writer
    prompt: "Summarize {topic}."

session "Merge the findings + draft into a final answer."
context: { findings, draft }

OpenClaw runtime mapping

OpenProse programs map to OpenClaw primitives:

OpenProse concept	OpenClaw tool
Spawn session / Task tool	sessions_spawn
File read / write	read / write
Web fetch	web_fetch

If your tool allowlist blocks `sessions_spawn`, `read`, `write`, or `web_fetch`, OpenProse programs will fail. Check your [tools allowlist config](/gateway/config-tools).

File locations

OpenProse keeps state under .prose/ in your workspace:

.prose/
├── .env
├── runs/
│   └── {YYYYMMDD}-{HHMMSS}-{random}/
│       ├── program.prose
│       ├── state.md
│       ├── bindings/
│       └── agents/
└── agents/

User-level persistent agents live at:

~/.prose/agents/

State backends

State is written to `.prose/runs/...` in the workspace. No extra dependencies required. Transient state kept in the context window. Suitable for small, short-lived programs. Requires the `sqlite3` binary on `PATH`. Requires `psql` and a connection string.

<Warning>
  Postgres credentials flow into sub-agent logs. Use a dedicated,
  least-privileged database.
</Warning>

Security

Treat .prose files like code. Review them before running, including remote use imports. Top-level /prose run https://... requests are explicit, but transitive remote imports require per-run approval before they are fetched or executed. Use OpenClaw tool allowlists and approval gates to control side effects. For deterministic, approval-gated workflows, compare with Lobster.

Related

How OpenProse's skill pack loads and what gates apply. OpenClaw's native multi-agent coordination layer. Add audio output to your workflows. All available chat commands including /prose.

Official site: https://www.prose.md