Mission Claw

Log agent activities to Mission Claw dashboard with token usage tracking. Use when completing significant tasks, subagent work, or any action worth recording in the activity feed. Triggers on task completion, activity logging, or tracking agent work.

Security Scan

The skill's instructions, required tools, and behavior are coherent with a local activity-logging CLI; nothing requested appears disproportionate to that purpose.

Purpose & Capability

Name/description (activity logging, token tracking) lines up with the instructions: it tells the agent to call the mclaw CLI or POST to a local API and to include token counts. No unrelated credentials, binaries, or external services are requested.

Instruction Scope

Instructions are narrowly scoped to running the mclaw CLI or POSTing to a local daemon (http://localhost:3100) and to use the built-in session_status tool for token counts. This is appropriate for logging, but the skill will send task descriptions/details (which can include sensitive text) to a local service — verify that the local daemon is trusted before logging sensitive content.

Install Mechanism

SKILL.md recommends installing via `npm install -g mission-claw` (a standard npm global CLI install). That is a common install method but does carry the usual npm-package risk (third-party code executed on install). There is no direct download URL in the SKILL.md and no archive extract step.

Credentials

No environment variables, credentials, or config paths are requested. The reliance on a local daemon and the session_status built-in is proportional to token-usage logging.

Persistence & Privilege

Skill is instruction-only, has no install spec in the registry metadata, and is not always-enabled. It does not request persistent platform privileges or modification of other skills.

Assessment

This skill appears to do exactly what it says: log agent actions to a local Mission Claw service. Before installing or using it, verify the mclaw npm package and the GitHub repo (confirm the package owner and review code if possible). Be cautious about logging sensitive content (task descriptions or details may include secrets or PII) — ensure the local daemon (http://localhost:3100) is controlled and properly secured. If you cannot inspect the npm package, consider running the CLI in a restricted environment/container or only logging non-sensitive summary data.

Mission Claw Activity Logging

Log significant tasks to the Mission Claw activity feed for tracking agent work, token usage, and project progress.

Prerequisites

• Mission Claw CLI: The mclaw binary must be installed on the host system.
• OpenClaw Built-ins: Relies on the session_status tool to retrieve current token usage.

CLI Usage

mclaw log "Task description" \
  --agent "AgentName" \
  --project "ProjectName" \
  --status completed \
  --duration "Xm Ys" \
  --input-tokens N \
  --output-tokens N \
  --total-tokens N

Required Fields

• action - Brief task description (positional argument)
• --agent - Agent name (e.g., "J", "mission-claw", "type-alchemy")
• --total-tokens - Total tokens used (always include)

Optional Fields

• --details - Longer description of work done
• --project - Project name
• --status - completed (default), in_progress, or failed
• --duration - Time taken (e.g., "5m", "1h 30m")
• --input-tokens / --output-tokens - Token breakdown

When to Log

Log after completing:

• Significant development tasks
• Bug fixes or feature implementations
• Research or investigation work
• Configuration changes
• Any task worth tracking

Getting Token Usage

Before logging, check your session's token usage:

• Use the built-in session_status tool to see current tokens
• For subagents, tokens are in the completion announcement

Examples

# Feature implementation
mclaw log "Added date-time filter to dashboard" \
  --agent "mission-claw" \
  --project "Mission Claw" \
  --status completed \
  --duration "10m" \
  --total-tokens 15000

# Quick fix
mclaw log "Fixed timezone bug" \
  --agent "J" \
  --project "ContentMorph" \
  --duration "2m" \
  --total-tokens 3500

# In-progress work
mclaw log "Implementing payment flow" \
  --agent "J" \
  --project "TypeAlchemy" \
  --status in_progress

Other Commands

mclaw list                    # Recent activities
mclaw list --agent J          # Filter by agent
mclaw status                  # Quick stats and service status
mclaw dashboard start         # Start web dashboard (localhost:3101 by default)

API Alternative

The CLI logs to a local daemon (defaulting to http://localhost:3100). You can also POST directly to the API:

POST http://localhost:3100/api/activity

{
  "action": "Task name",
  "agent": "J",
  "project": "Project",
  "status": "completed",
  "totalTokens": 5000,
  "inputTokens": 4000,
  "outputTokens": 1000
}