Wanman CLI
Productivitywanman-cliWanman CLI is an Agent Skill for productivity published in the chekusu/wanman repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
wanman CLI command reference — inter-agent communication, task management, artifact storage
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/chekusu/wanman/blob/HEAD/packages/core/skills/wanman-cli/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/wanman-cli, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
wanman CLI
You are running inside the wanman Agent Matrix. Use the following CLI commands to collaborate with other agents.
Startup Protocol
On every startup, execute in order:
cat ./CLAUDE.md— Read your role guidewanman recv— Check for pending messageswanman task list --assignee $WANMAN_AGENT_NAME— View tasks assigned to you
Messages
| Command | Description |
|---|---|
wanman send <agent> "<message>" | Send a normal message |
wanman send <agent> "<message>" --steer | Urgent message (interrupts the target agent's current work) |
wanman send human --type decision "<message>" | Ask the human to make a decision |
wanman send human --type blocker "<message>" | Tell the human what is blocking progress |
wanman recv | Receive pending messages |
wanman escalate "<message>" | Escalate to the CEO agent |
Note: --steer forcefully interrupts the target agent's process and restarts it. Use only in urgent situations.
Prefer explicit --type decision|blocker when sending to human, so the product can render the right card.
Tasks
wanman task create "<title>" --assign <agent> [--priority 1-10] [--after id1,id2] [--desc "<description>"]
wanman task list [--status <pending|in_progress|done|blocked>] [--assignee <agent>]
wanman task get <id>
wanman task update <id> --status <in_progress|blocked|done> [--result "<text>"]
wanman task done <id> "<result>"
--after: Declare dependencies (comma-separated task IDs); the task will not execute until dependencies are complete--priority: 1 = highest, 10 = lowesttask doneis a shortcut fortask update --status done --result
Artifacts (Structured Outputs)
wanman artifact put --kind <kind> --path "<domain>/<category>/<item>" \
--source "<source>" --confidence <0-1> [--task <id>] [--file <path>] '<metadata json>'
wanman artifact list [--agent <a>] [--kind <k>]
wanman artifact get <id>
--file: Store file contents in the database (version-controlled storage)--source: Information source, e.g.,web_search:site.com,estimate,official_data--confidence: 0.3-0.5 (estimate) | 0.6-0.8 (data-backed) | 0.9+ (authoritative source)
Context (Cross-Agent Shared Key-Value Store)
wanman context set <key> "<value>"
wanman context get <key>
Used to share blueprints, summaries, and other information needed across agents.
Hypothesis Tracking
wanman hypothesis create "<title>" [--rationale "<text>"]
wanman hypothesis list [--status <proposed|active|validated|rejected>]
wanman hypothesis update <id> --status <validated|rejected> [--outcome "<text>"] [--evidence <artifact-ids>]
Agent Management
wanman agents # List all agents and states
wanman agents spawn <template> [name] # Spawn a clone (e.g. feedback-2)
wanman agents destroy <name> # Destroy a dynamic clone
Standard Workflow
wanman task update <id> --status in_progress- Do the work, write outputs to the
./output/directory wanman task done <id> "completion description"wanman send ceo "Task complete: <title>, output: output/<filename>"
Environment Variables
| Variable | Description |
|---|---|
WANMAN_AGENT_NAME | Your agent name (set automatically) |
WANMAN_URL | Supervisor address (default http://localhost:3120) |