plugins/core-claude/skills/plan-manager/SKILL.md
Rosetta skill for plan creation, tracking, and execution coordination via local JSON files.
npx skillsauth add griddynamics/rosetta plan-managerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Senior execution planner and tracker for plan-driven workflows.
</role><when_to_use_skill>
Primary plan manager for orchestrators and subagents. Creates, tracks, and executes plans as local JSON files.
</when_to_use_skill>
<core_concepts>
<feature_plan_folder_full_path>/plan.jsonnpx rosettify plan <subcommand> <plan_file> [args...]help, create, next, update_status, show_status, query, upsertnext returns four groups: (1) in_progress steps (resume=true), (2) open eligible steps, (3) blocked steps (previously_blocked=true), (4) failed steps (previously_failed=true)entire_plan target is rejected for update_status (invalid_target)upsert silently ignores status fields in patch -- only update_status modifies statusplan-manager/assets/pm-schema.md FROM KB for data structure reference</core_concepts>
<process>Orchestrator flow:
npx rosettify plan create <plan_file> '<json>' -- see pm-schema.md for JSON structurenpx rosettify plan upsert <plan_file> entire_plan [kind] '<json>'next until plan_status: complete and count: 0Subagent flow:
npx rosettify plan next <plan_file> [limit]resume flag -- if true, continue interrupted work; if false, start freshnpx rosettify plan update_status <plan_file> <step-id> complete<validation_checklist>
npx rosettify plan help exits without error and returns structured help JSONshow_status output: plan root status is derived (never manually set)next output: in_progress steps appear before open steps; blocked and failed steps are included with flagsshow_status phase status matches aggregate of its steps after update_status</validation_checklist>
<pitfalls>resume flag on next results -- causes duplicate work on resumed sessionsupdate_status after step completion -- plan remains staleplan-manager/assets/pm-schema.md FROM KB -- plan JSON structureadhoc-flowdata-ai
Rosetta MUST skill. MUST activate when you ARE a subagent — you were spawned by an orchestrator, you received a delegated task, you are executing within a subagent context. Defines your input contract, output contract, behavior boundaries, and escalation protocol.
development
Rosetta CRITICAL MUST skill. MUST activate when you suspect, there is a slight chance, encounter, read, process, or are about to output any sensitive or possibly sensitive data including PII, PCI, HIPAA, PHI, GDPR, SOC2, FedRAMP, secrets, API keys, passwords, credentials, tokens, certificates, or any data that could potentially be sensitive.
development
Rosetta MUST skill for proactive planning, large-file restructuring (~500+ lines or 10K+ size), cleanup of stale information. MUST activate when conversation is long, or context reaches 65% / 100K tokens, or scope exceeds 2h / 15+ files / 350+ lines, or output size risks overloading the context.
data-ai
Rosetta MUST skill. MUST activate when execution fails, user is unhappy or upset, mistake is detected, result is unexpected, mismatch between expected and actual outcome occurs, or after two consecutive mismatches with user expectations.