Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency graphs, quality gates, and actor attribution. Schemas define what agents must produce — the server blocks the call if they don't. Works with any MCP-compatible client.
Latest release v3.16.0 · 2 Oct 2026
15 files for Claude Code: check_schema_version, deploy_to_docker, task-orchestrator, api-compat-review and 11 more — 3,738 tokens loaded in every session.
CLAUDE.md A 3,738 tok .claude/settings.json A — .claude/skills/api-compat-review/SKILL.md A 49 tok .claude/skills/feature-implementation/SKILL.md A 112 tok .claude/skills/implement/SKILL.md A 101 tok .claude/skills/migration-review/SKILL.md A 47 tok .claude/skills/perf-review/SKILL.md A 40 tok .claude/skills/plugin-impact-review/SKILL.md A 47 tok .claude/skills/prepare-release/SKILL.md A 95 tok .claude/skills/review-quality/SKILL.md A 60 tok .claude/skills/spec-quality/SKILL.md A 72 tok .claude/skills/test-author/SKILL.md A 103 tok .claude/skills/add-component/SKILL.md A 81 tok .claude/commands/check_schema_version.md A 14 tok .claude/commands/deploy_to_docker.md A 23 tok These files are jpicklyk/task-orchestrator's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.