SuperAPI AI Directory

harness-setup

Deployment & operations

View repository

Updated 10-15 17:33

About this skill

Harness Setup

Harness integrated setup skill. Integrated the following legacy skills:

  • setup — Integrated setup hub
  • harness-init — Project initialization
  • harness-update — Harness update
  • maintenance — File organization and cleanup

Quick Reference

Subcommand Operation Details
/harness-setup init New project initialization (CLAUDE.md + Plans.md + hooks + sync + doctor) ${CLAUDE_SKILL_DIR}/references/init.md
/harness-setup ci CI/CD pipeline configuration ${CLAUDE_SKILL_DIR}/references/ci.md
/harness-setup codex Codex CLI installation and configuration ${CLAUDE_SKILL_DIR}/references/codex.md
/harness-setup harness-mem harness-mem integration and memory configuration ${CLAUDE_SKILL_DIR}/references/harness-mem.md
/harness-setup mirrors skills/ → public mirror bundle update ${CLAUDE_SKILL_DIR}/references/mirrors-agents-localize.md
/harness-setup agents agents/ agent configuration ${CLAUDE_SKILL_DIR}/references/mirrors-agents-localize.md
/harness-setup localize Localization of CLAUDE.md rules ${CLAUDE_SKILL_DIR}/references/mirrors-agents-localize.md
marketplace / update Plugin install, update, dependency policy ${CLAUDE_SKILL_DIR}/references/marketplace.md
maintenance File organization and cleanup ${CLAUDE_SKILL_DIR}/references/maintenance.md

Built-in slash discovery (CC 2.1.108+): /init built-in slash commands like these are also discovered. Use this only when Harness-specific bootstrap is needed, and use /harness-setup init accordingly.

Claude Code setup guidance (CC 2.1.120+): MCP alwaysLoad、${CLAUDE_EFFORT}、claude plugin prune、claude project purge、 ANTHROPIC_BEDROCK_SERVICE_TIER、claude_code.skill_activated.invocation_trigger、 Windows PowerShell primary shell、forked skills / subagents の deferred tools は docs/claude-code-setup-mcp-telemetry-provider.md as the source of truth.

Codex plugin workflows: Codex /goal と Plans.md is not managed in duplicate. plugin-bundled hooks are opt-in, external agent imports must state ownership explicitly, MultiAgentV2 / agents.max_threads = 8 are treated as upper limits, sticky environments / app-server artifacts prioritize safe defaults. Codex 0.130.0 stable の codex remote-control、large thread pagination、 selected-environment view_image、live app-server config refresh、 accurate turn diffs、plugin details bundled hooks、sharing discoverability controls は docs/codex-plugin-workflows-policy.md as the source of truth. For details, refer to docs/codex-plugin-workflows-policy.md と ${CLAUDE_SKILL_DIR}/references/codex.md .

Execution

  1. Select the Quick Reference row that corresponds to the user's objective.
  2. Read the applicable ${CLAUDE_SKILL_DIR}/references/*.md .
  3. Follow the procedure in the referenced file, and for operations that have a dry-run, run the dry-run first.
  4. After setup, verify as needed with harness doctor、bash scripts/sync-skill-mirrors.sh --check、bash scripts/ci/check-consistency.sh .

Upstream Policy Anchors

  • docs/plugin-managed-settings-policy.md — plugin managed settings policy; normal defaults must not inherit managed marketplace restrictions.
  • docs/codex-provider-setup-policy.md — Codex provider setup policy, including amazon-bedrock and model_provider = "amazon-bedrock" examples.
  • Codex 0.123.0 and later MCP diagnostics / plugin MCP loading guidance: use /mcp verbose and docs/codex-mcp-diagnostics.md for diagnostics.
  • Codex sandbox / execution policy (0.123.0+): see docs/codex-sandbox-execution-policy.md for remote_sandbox_config and execution constraints.

Cursor implementation backend setup

For detailed procedures, read ${CLAUDE_SKILL_DIR}/references/cursor.md . Contract anchor: set-impl-backend.sh can be executed by AI.permissions.json、.cursorignore、*.cursor.sh The allowlist is manually managed by the user and treated as a protected path that AI cannot edit. The governing rule is .claude/rules/cursor-cli-only.md と docs/sandbox-allowlist-recipe.md。

Reference Index

  • ${CLAUDE_SKILL_DIR}/references/init.md — init, Go binary verification, plugin sync, doctor.
  • ${CLAUDE_SKILL_DIR}/references/ci.md — GitHub Actions CI setup.
  • ${CLAUDE_SKILL_DIR}/references/codex.md — Codex CLI, provider/model metadata, app-server, MCP diagnostics, sandbox policy.
  • ${CLAUDE_SKILL_DIR}/references/cursor.md — Cursor implementation backend setup and boundaries.
  • ${CLAUDE_SKILL_DIR}/references/harness-mem.md — memory directory and template setup.
  • ${CLAUDE_SKILL_DIR}/references/mirrors-agents-localize.md — mirror sync, agent setup, localization.
  • ${CLAUDE_SKILL_DIR}/references/marketplace.md — plugin marketplace install/update and managed dependency policy.
  • ${CLAUDE_SKILL_DIR}/references/maintenance.md — cleanup commands and related skills.

Related skills

  • harness-sync — Sync verification of settings/Plans/git state
  • harness-work — Implementation task execution
  • harness-review — Quality review
  • maintenance — File organization (integrated)