foremanDispatch-and-acceptance control desk for farming coding work out to background agents. Sends executable tasks to worker agents via the handoff CLI, takes delivery against a path whitelist, then gates the merge behind an acceptance protocol whose core rule is that the builder may never touch the tests, assertions, or CI config that judge it. Use it when batching implementation work out to background agents, or when accepting code that someone else — human or agent — built.
Install via ClawdBot CLI:
clawdbot install halfdeadcat/foremanGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Sep 2, 2026
A SaaS company needs to implement multiple independent features simultaneously. The foreman skill dispatches each feature as a task to a background agent, which develops it in an isolated worktree with limited credentials. After delivery, the main agent accepts only those that pass the whitelist and meet the acceptance criteria, protecting the core test suite from tampering.
An enterprise with a legacy codebase has a backlog of low-risk bug fixes. The foreman skill batches these fixes, assigning each to a background agent. Each agent works in isolation, ensuring they don't inadvertently modify tests or CI config. The acceptance protocol verifies that patches only change intended files, maintaining system stability.
A media company uses AI agents to draft articles and reports. The foreman skill manages the dispatch of writing tasks to agents, which produce drafts in separate workspaces. Acceptance checks focus on content criteria, not code, but the same principles apply: agents cannot alter the acceptance criteria (like style guides). This ensures high-quality, consistent content.
A research consortium needs to clean and preprocess large datasets. Using foreman, tasks are dispatched to multiple agents, each handling a subset of data. The agents operate in sandboxes with limited access, and acceptance verifies the data outputs against predefined schemas. This parallelizes the work while maintaining data integrity.
A consultancy offers development and maintenance services using AI-assisted workflows. Foreman enables the consultancy to automate the coordination of multiple AI developers, increasing throughput. The acceptance protocol ensures high-quality deliverables, building client trust.
A company builds a platform that integrates with this skill to provide task management and acceptance testing as a service to other dev teams. They offer infrastructure and workflows that leverage foreman's capabilities.
An enterprise uses this skill internally to manage a fleet of AI agents for software development tasks, replacing or augmenting human developers. This reduces cost and increases scalability.
💬 Integration Tip
Set up a secure dispatch environment with '~/.handoff' and configured credentials. Ensure workers have minimal permissions and that acceptance runs are isolated from test modifications.
Scored Sep 2, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...
AI agent for finance search agent tasks