Skip to content

Dezycro CLI

The Dezycro CLI (dezycro) brings Dezycro's workbook, verification, and PRD/TRD authoring flows directly into your coding agent. Once installed, the Dezycro commands appear in your agent session as slash commands, your team's Agent Playbook reaches the agent as team rules, and the Companion background loop quietly guards the work your agent does for you against silent regressions.

Supported agents: Claude Code and Cursor — one install covers every supported agent on your machine, including Cursor's app and CLI.

What you get

Commands for the day-to-day Dezycro flow without leaving your editor. One command is built in — /dezycro:init, which binds a repo to a workspace. The rest are platform skills: Dezycro ships them into every workspace and they sync to your machine under the workspace's prefix, so a command always says which workspace it acts on. The examples use the prefix acme; yours is on the Skills page.

Command What it does
/dezycro:init Connect a repo to a Dezycro workspace + project
/acme:dz-work <feature> Start or resume work on a feature; binds the session to the workbook
/acme:dz-author --doc prd \| trd Guided PRD/TRD authoring with a built-in quality gate
/acme:dz-status Compact workbook snapshot for the active feature
/acme:dz-sync Sync the current chunk of work to the workbook
/acme:dz-publish-spec Auto-detect + upload an OpenAPI spec; triggers the verifier build
/acme:dz-verify Pull the verifier binary and run it; results self-report to the workbook
/acme:dz-import-features Reverse-engineer a codebase into Dezycro features with PRDs + TRDs
/acme:dz-kb-learn Record a durable team rule in the Agent Playbook
/acme:dz-kb-recall Consult the Agent Playbook before substantive work
Command What it does
/dezycro-init Connect a repo to a Dezycro workspace + project
/acme-dz-work <feature> Start or resume work on a feature; binds the session to the workbook
/acme-dz-author --doc prd \| trd Guided PRD/TRD authoring with a built-in quality gate
/acme-dz-status Compact workbook snapshot for the active feature
/acme-dz-sync Sync the current chunk of work to the workbook
/acme-dz-publish-spec Auto-detect + upload an OpenAPI spec; triggers the verifier build
/acme-dz-verify Pull the verifier binary and run it; results self-report to the workbook
/acme-dz-import-features Reverse-engineer a codebase into Dezycro features with PRDs + TRDs
/acme-dz-kb-learn Record a durable team rule in the Agent Playbook
/acme-dz-kb-recall Consult the Agent Playbook before substantive work

Cursor command names use a - where Claude Code uses : — /acme-dz-work is the same flow as /acme:dz-work. Workspace-authored skills follow the same rule: /acme:db-migration in Claude Code is /acme-db-migration in Cursor.

Because they're skills, your team can read, fork, or opt out of any of them on the Skills page — see Platform skills.

Team rules — launch your agent with dezycro run claude (or dezycro run cursor) and the workspace's Agent Playbook travels with every request, in full or as a compact index the agent fetches from on demand. See Team rules delivery.

Companion — background guardrails that work the same in every supported agent:

  • Block tasks from going to DONE / PUSHED without recent passing verifier evidence
  • Nudge you to re-publish your OpenAPI spec when you touch a controller
  • Sweep the workbook for decisions, issues, and assumptions worth recording — only when you ask (e.g. "save progress") or right after a verify
  • Surface coverage gaps before you push

Everything is opt-in per-trigger. Companion stays out of your way unless something material happened.

Next steps