rlaope/oh-my-hermes / skills/omh-routing
omh-routing
Verified[omh] Choosing among OMH skills for a request: router guidance for using oh-my-hermes workflow skills inside Hermes Agent.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.4 KB |
| references/catalog-index.md | markdown | 32.9 KB |
| references/coding-handoff-progress-reporting.md | markdown | 4.8 KB |
| references/evidence-boundaries.md | markdown | 2.6 KB |
| references/harness-registry.md | markdown | 21.4 KB |
| references/human-voice.md | markdown | 7.1 KB |
| references/jev-rail.md | markdown | 6.3 KB |
| references/operator-maintenance.md | markdown | 2.1 KB |
| references/skill-common-rail.md | markdown | 15.5 KB |
| references/structural-code-search.md | markdown | 3.8 KB |
| references/workflow-artifacts.md | markdown | 2.6 KB |
| references/workflow-registry.md | markdown | 33.4 KB |
| references/wrapper-routing.md | markdown | 11.3 KB |
references/harness-registry.md
View on GitHub# OMH Harness Registry
Harnesses shape gates; not proof that a separate runtime role exists.
Legend: Tier `quality-tier` is in each harness definition; Ladder: evidence steps; Actions: wrapper actions; Privacy `metadata_only`.
## Representative Harnesses
- `show-reel`: Keep audience, source-grounded motion production... L: `brief_prepared` -> `sources_verified` -> `concept_selected` -> `+3 more`. A: `prepare_show_reel`, `prepare_visual_qa`.
- `coding-handling`: Route implementation requests through scoped... L: `coding_delegation_prepared` -> `executor_dispatch_observed` -> `executor_result_observed` -> `+2 more`. A: `accept_plan`, `show_prompt_handoff`, `copy_prompt_handoff`, `+13 more`.
- `hermes-setup`: Walk a local Hermes setup change through... L: `prerequisite_check_recorded` -> `read_only_diagnosis_recorded` -> `guidance_delivered` -> `+2 more`. A: `show_setup_diagnosis`, `approve_config_diff`, `record_setup_verification`, `+1 more`.
- `goal-execution`: Keep long-running work tied to explicit goals... L: `goal_created` -> `story_started` -> `checkpoint_recorded` -> `+2 more`. A: `continue_goal`, `show_status`, `record_checkpoint`, `+2 more`.
- `planning`: Turn clarified requirements into an execution-ready... L: `request_clarified` -> `plan_drafted` -> `option_tradeoffs_recorded` -> `+3 more`. A: `accept_plan`, `revise_plan`, `cancel`, `+1 more`.
- `research`: Gather current or source-backed evidence before... L: `research_question_scoped` -> `source_boundaries_recorded` -> `primary_sources_checked` -> `+4 more`. A: `show_sources`, `ask_followup`, `record_source`, `+1 more`.
- `business-research`: Prepare source-backed business research briefs with... L: `business_question_scoped` -> `source_boundary_recorded` -> `source_quality_recorded` -> `+3 more`. A: `show_sources`, `ask_followup`, `prepare_strategy_brief`, `+1 more`.
- `strategy-synthesis`: Turn goals and evidence into strategy options... L: `decision_scope_recorded` -> `options_recorded` -> `tradeoffs_recorded` -> `+2 more`. A: `show_brief`, `revise_brief`, `record_decision`, `+1 more`.
- `meeting-facilitation`: Prepare agendas, discussion prompts, decisions, and... L: `meeting_goal_scoped` -> `agenda_recorded` -> `discussion_prompts_recorded` -> `+2 more`. A: `show_agenda`, `revise_brief`, `record_decision`, `+1 more`.
- `customer-insight-triage`: Cluster customer feedback and choose the next... L: `feedback_source_scoped` -> `clusters_recorded` -> `severity_opportunity_recorded` -> `+1 more`. A: `show_triage`, `ask_followup`, `prepare_plan`, `+1 more`.
- `ops-review`: Summarize observed operating status, risks... L: `review_scope_recorded` -> `status_evidence_recorded` -> `risks_blockers_recorded` -> `+2 more`. A: `show_status`, `record_blocker`, `record_checkpoint`, `+1 more`.
- `operating-rhythm`: Maintain meeting, scrum, sprint, retro, decision... L: `operation_rhythm_scoped` -> `record_structure_prepared` -> `decisions_actions_recorded` -> `+1 more`. A: `show_record`, `record_decision`, `record_action`, `+2 more`.
- `report-package`: Package supplied inputs into reports, executive... L: `report_scope_recorded` -> `inputs_organized` -> `package_outline_prepared` -> `+1 more`. A: `show_report`, `export_markdown`, `export_json`, `+2 more`.
- `materials-package`: Plan, hand off, and verify material-processing work... L: `material_scope_recorded` -> `source_inputs_organized` -> `format_qa_ladder_prepared` -> `+2 more`. A: `show_material_plan`, `choose_target_format`, `prepare_generation_handoff`, `+4 more`.
- `img-summary`: Prepare source-specific, premium domain-aware, and... L: `source_kind_selected` -> `visual_format_selected` -> `poster_archetype_selected` -> `visual_qa_observed_when_available` -> `+5 more`. A: `show_visual_prompt_card`, `copy_visual_prompt`, `revise_visual_card`, `record_visual_qa`, `+7 more`.
- `design-quality-gate`: Prepare superior visual quality gates for web... L: `design_quality_scope_recorded` -> `reference_packet_selected` -> `comparative_quality_rubric_prepared` -> `visual_qa_observed_when_available` -> `+5 more`. A: `prepare_design_quality_gate`, `show_design_quality_gate`, `record_design_reference`, `record_visual_qa`, `prepare_frontend_handoff`, `+6 more`.
- `frontend`: Prepare design-system-driven web UI creation... L: `frontend_scope_recorded` -> `initial_generation_contract_prepared_when_greenfield` -> `reference_packet_selected_when_available` -> `visual_qa_observed_when_available` -> `+6 more`. A: `prepare_frontend_handoff`, `show_frontend_handoff`, `record_design_reference`, `prepare_visual_qa`, `record_visual_qa`, `+5 more`.
- `accessibility-audit`: Prepare WCAG, keyboard, focus, screen-reader... L: `accessibility_scope_recorded` -> `wcag_level_recorded` -> `semantic_structure_review_prepared` -> `+6 more`. A: `prepare_accessibility_audit`, `show_accessibility_audit`, `record_accessibility_check`, `route_to_frontend_or_visual_qa`, `+5 more`.
- `visual-qa`: Prepare observed-only rendered visual QA gates for... L: `visual_qa_scope_recorded` -> `web_visual_qa_package_prepared` -> `message_attachment_projection_prepared` -> `web_visual_qa_message_card_prepared` -> `visual_qa_verdict_recorded` -> `+12 more`. A: `prepare_visual_qa`, `show_visual_qa`, `show_capture_package`, `record_visual_qa`, `record_visual_qa_verdict`, `+9 more`.
- `workspace-audit`: Map repository, skill, prompt, plugin, MCP/tool... L: `audit_scope_recorded` -> `surface_inventory_observed_when_available` -> `config_security_findings_redacted` -> `+2 more`. A: `prepare_workspace_audit`, `show_workspace_audit`, `record_workspace_inventory`, `+4 more`.
- `production-audit`: Evaluate release, deploy, security, observability... L: `production_scope_recorded` -> `readiness_matrix_prepared` -> `release_gate_verdict_recorded` -> `+2 more`. A: `prepare_production_audit`, `show_production_audit`, `record_release_gate`, `+4 more`.
- `verification-gate`: Define and record build, lint, typecheck, test... L: `verification_scope_recorded` -> `verification_matrix_prepared` -> `check_results_observed_when_available` -> `+2 more`. A: `prepare_verification_gate`, `show_verification_gate`, `record_build_check`, `+6 more`.
- `build-failure-triage`: Classify failing build, typecheck, lint, test, CI... L: `failure_surface_recorded` -> `failure_log_digest_observed_when_available` -> `failure_cluster_matrix_prepared` -> `+4 more`. A: `prepare_build_failure_triage`, `show_build_failure_triage`, `record_failure_log`, `+6 more`.
- `agent-evaluation`: Compare executor or agent choices on reproducible... L: `agent_eval_scope_recorded` -> `task_benchmark_set_prepared` -> `run_results_observed_when_available` -> `+2 more`. A: `prepare_agent_evaluation`, `show_agent_evaluation`, `record_eval_task`, `+5 more`.
- `rules-distill`: Extract repeated principles from skills, prompts... L: `rules_scope_recorded` -> `source_corpus_reviewed` -> `principle_candidates_prepared` -> `+3 more`. A: `prepare_rules_distillation`, `show_rules_distillation`, `record_rule_candidate`, `+4 more`.
- `codebase-onboarding`: Create a repo map, reading path, glossary, risk... L: `onboarding_scope_recorded` -> `repo_map_observed_when_available` -> `reading_path_prepared` -> `first_task_runway_prepared` -> `+2 more`. A: `prepare_codebase_onboarding`, `show_codebase_onboarding`, `record_repo_map`, `record_first_task_runway`, `+4 more`.
- `codegraph-refresh`: Refresh local code intelligence, summarize repo... L: `codegraph_scope_recorded` -> `codegraph_command_plan_prepared` -> `staleness_scope_report_prepared` -> `codegraph_handoff_prepared_when_task_scoped` -> `codegraph_handoff_observed_when_available` -> `+2 more`. A: `prepare_codegraph_refresh`, `show_codegraph_refresh`, `record_codegraph_build`, `record_codegraph_handoff`, `+2 more`.
- `context-budget-review`: Plan compact context, token/cost budgets... L: `context_budget_scope_recorded` -> `must_keep_context_pack_prepared` -> `checkpoint_plan_prepared` -> `overflow_recovery_route_prepared` -> `+2 more`. A: `prepare_context_budget_review`, `show_context_budget_review`, `record_must_keep_context`, `+4 more`.
- `security-safety-review`: Review prompt, tool, secret, dependency, network... L: `security_safety_scope_recorded` -> `threat_surface_map_prepared` -> `permission_secret_risk_matrix_prepared` -> `safe_action_policy_recorded` -> `remediation_handoff_prepared_when_needed` -> `+2 more`. A: `prepare_security_safety_review`, `show_security_safety_review`, `record_threat_surface`, `record_safe_action_policy`, `prepare_remediation_handoff`, `+4 more`.
- `source-finder`: Prepare typed source candidates, acquisition... L: `source_scope_named` -> `source_kind_selected` -> `candidate_set_prepared` -> `+3 more`. A: `prepare_source_finder_plan`, `show_source_candidates`, `record_source_candidate`, `+9 more`.
- `long-document-reading`: Read a very large document through Hermes in... L: `document_scoped` -> `page_count_observed` -> `range_plan_prepared` -> `+3 more`. A: `record_page_count_observed`, `record_range_text_observed`, `show_chunk_ledger`, `+2 more`.
- `paper-learning`: Explain supplied papers or paper PDFs at a chosen... L: `paper_source_scoped` -> `explanation_level_selected` -> `extraction_state_recorded` -> `+3 more`. A: `choose_explanation_level`, `show_paper_source_requirements`, `record_paper_metadata`, `+8 more`.
- `scheduled-ops-blueprint`: Prepare recurring Hermes operations as... L: `blueprint_scope_recorded` -> `schedule_policy_prepared` -> `delivery_policy_prepared` -> `+3 more`. A: `show_blueprint`, `revise_schedule`, `confirm_delivery_policy`, `+3 more`.
- `research-department`: Prepare Scout, Analyst, and Briefer research... L: `research_plan_scope_recorded` -> `source_inbox_prepared` -> `briefing_status_prepared` -> `+2 more`. A: `show_research_department_plan`, `revise_research_sources`, `confirm_cadence_delivery_tooling`, `+2 more`.
- `reliability-review`: Review incidents, SLOs, error budgets, and... L: `reliability_scope_recorded` -> `evidence_boundary_recorded` -> `review_prepared_or_observed` -> `+1 more`. A: `show_evidence`, `record_gap`, `prepare_handoff`, `+2 more`.
- `app-delivery-loop`: Run complete app operation loops from idea through... L: `loop_scope_recorded` -> `decision_gate_recorded` -> `plan_or_release_gate_accepted` -> `+3 more`. A: `show_delivery_loop`, `accept_plan`, `choose_executor`, `+4 more`.
- `goal-loop`: Run explicit loop invocations through agentic... L: `loop_triggered` -> `loopability_assessed` -> `goal_reframed` -> `+7 more`. A: `assess_loopability`, `convert_to_loop_goal`, `route_direct_task`, `+12 more`.
- `deep-interview`: Clarify intent and boundaries one question at a... L: `ambiguity_identified` -> `blocking_question_asked` -> `answer_recorded` -> `+2 more`. A: `answer:clarify`, `cancel`, `rerun_plan`.
- `decision-frontier`: Resolve repository terminology through one... L: `frontier_entry_confirmed` -> `ready_batch_presented` -> `answers_applied_by_id` -> `+2 more`. A: `prepare_project_terms_context`, `answer:clarify`, `cancel`, `+1 more`.
- `jit-learn`: Confirm the highest-leverage immediate learning... L: `context_reviewed` -> `confirmation_asked` -> `target_confirmed` -> `+2 more`. A: `answer:clarify`, `prepare_learning_brief`, `show_sources`, `+3 more`.
- `architect`: Evaluate system boundaries, integration choices... L: `architecture_context_loaded` -> `tradeoffs_recorded` -> `boundary_verdict_recorded`. A: `show_review`, `revise_plan`, `approve_plan`.
- `critic`: Challenge plan consistency, quality criteria, and... L: `review_scope_loaded` -> `findings_recorded` -> `verdict_recorded` -> `+1 more`. A: `show_findings`, `request_changes`, `approve_plan`.
- `qa-specialist`: Design adversarial scenarios and verify... L: `scenario_matrix_defined` -> `checks_run` -> `pass_fail_recorded` -> `+1 more`. A: `show_status`, `record_check`, `record_blocker`.
- `docs-specialist`: Keep public docs accurate, installable, and aligned... L: `claims_scoped` -> `docs_updated` -> `generated_docs_checked` -> `+1 more`. A: `show_docs`, `record_claim_check`, `show_status`.
- `apple-design`: Apple platform-aware design/review/improvement direction. L: `target_scoped` -> `source_applicability_prepared` -> `findings_prepared` -> `+1 more`. A: `prepare_design_orchestration`, `choose_executor`, `prepare_accessibility_audit`, `prepare_visual_qa`.
- `design-orchestration`: Direction. L: `intent` -> `direction` -> `visual_when_available`. A: `prepare_design_orchestration`, `choose_executor`, `prepare_visual_qa`.
- `github-event-ops`: Route GitHub PR, issue, CI, and review events into... L: `event_received` -> `event_classified` -> `route_card_prepared` -> `+1 more`. A: `show_event_card`, `prepare_review`, `prepare_label`, `+2 more`.
- `agent-board`: Coordinate multi-Hermes-agent or profile work as... L: `board_scoped` -> `cards_prepared` -> `heartbeat_recorded_when_available` -> `+1 more`. A: `show_board`, `move_card`, `record_heartbeat`, `+2 more`.
- `memory-new`: Capture one bounded durable project or product... L: `candidate_captured` -> `candidate_reviewed` -> `candidate_approved` -> `+1 more`. A: `show_memory_candidate`, `approve_memory_candidate`, `reject_memory_candidate`, `+2 more`.
- `memory-sync`: English-canonical Hermes memory-review guidance... L: `memory_candidates_scoped` -> `conflicts_ranked` -> `review_actions_prepared` -> `+2 more`. A: `show_memory_review`, `prepare_memory_diff`, `approve_diff_application`, `+1 more`.
- `gateway-intent-card`: Normalize gateway session policy for origin... L: `origin_scoped` -> `thread_policy_prepared` -> `delivery_policy_prepared` -> `+1 more`. A: `show_gateway_card`, `confirm_delivery`, `record_delivery`, `+2 more`.
- `executor-runtime-readiness`: Compare executor/runtime options by available... L: `task_runtime_scoped` -> `tool_matrix_prepared` -> `handoff_mode_selected` -> `+1 more`. A: `show_runtime_matrix`, `choose_executor`, `prepare_handoff`, `+2 more`.
- `deliverable-package`: Track file deliverables through prepared... L: `deliverable_scoped` -> `format_plan_prepared` -> `generation_handoff_prepared` -> `+2 more`. A: `show_deliverable_card`, `choose_format`, `prepare_generation_handoff`, `+2 more`.
- `voice-operator`: Convert terse voice/mobile requests into safe... L: `voice_request_received` -> `ambiguity_checked` -> `safe_action_prepared` -> `+1 more`. A: `ask_clarification`, `confirm_action`, `show_status`, `+1 more`.
- `browser-operator`: Scope browser/page interaction requests as safe... L: `scope_recorded` -> `auth_boundary_recorded` -> `allowed_actions_recorded` -> `+2 more`. A: `prepare_browser_operator_card`, `show_browser_operator_card`, `confirm_browser_action`, `+3 more`.
- `workspace-file-operator`: Scope local file and folder operations as safe task... L: `path_scope_recorded` -> `allowed_operations_recorded` -> `excluded_paths_recorded` -> `+3 more`. A: `prepare_workspace_file_operator_card`, `show_workspace_file_operator_card`, `confirm_file_operation`, `+3 more`.
- `command-operator`: Scope terminal, shell, CLI, package-manager, and... L: `command_text_recorded` -> `working_directory_recorded` -> `environment_boundary_recorded` -> `+2 more`. A: `prepare_command_operator_card`, `show_command_operator_card`, `confirm_command_execution`, `+3 more`.
- `connector-operator`: Scope external app and SaaS connector actions as... L: `provider_boundary_recorded` -> `connector_action_recorded` -> `target_and_payload_recorded` -> `+3 more`. A: `prepare_connector_operator_card`, `show_connector_operator_card`, `confirm_connector_action`, `+3 more`.
- `live-info-operator`: Scope live info provider/freshness gates. L: `provider_boundary_recorded` -> `scope_recorded` -> `freshness_boundary_recorded` -> `+2 more`. A: `prepare_live_info_operator_card`, `show_live_info_operator_card`, `record_live_info_observation`, `+2 more`.
- `external-connector-readiness`: Score external plugin, connector, API, live-data... L: `candidate_connector_recorded` -> `connector_route_selected` -> `capability_matrix_recorded` -> `+5 more`. A: `prepare_external_connector_readiness`, `show_external_connector_readiness_card`, `record_connector_capability_matrix`, `+4 more`.
- `prompt-import-readiness`: Audit explicitly named CLI-agent prompt files... L: `prompt_sources_recorded` -> `prompt_compatibility_audit_observed_for_explicit_paths` -> `prompt_format_matrix_recorded` -> `+4 more`. A: `prepare_prompt_import_readiness`, `audit_prompt_compatibility`, `show_prompt_import_readiness_card`, `+5 more`.
- `physical-device-readiness`: Score physical-device workflows before any... L: `device_scope_selected` -> `hazard_inventory_recorded` -> `physical_safety_boundary_recorded` -> `+4 more`. A: `prepare_physical_device_readiness`, `show_physical_device_readiness_card`, `record_device_safety_envelope`, `+4 more`.
- `content-operator`: Scope publish-ready content with audience, source... L: `source_scope_recorded` -> `audience_recorded` -> `tone_style_recorded` -> `+3 more`. A: `prepare_content_operator_card`, `show_content_operator_card`, `record_content_draft`, `+3 more`.
- `media-input-operator`: Scope audio, video, YouTube, OCR, screenshot text... L: `media_source_scope_recorded` -> `permission_boundary_recorded` -> `transcript_boundary_recorded` -> `+2 more`. A: `prepare_media_input_card`, `show_media_input_card`, `record_media_source_scope`, `+3 more`.
- `data-analysis`: Scope supplied data analysis with provenance and... L: `dataset_scope_recorded` -> `schema_or_columns_recorded` -> `analysis_question_recorded` -> `+4 more`. A: `prepare_data_analysis_card`, `show_data_analysis_card`, `record_dataset_scope`, `+2 more`.
- `toolbelt-readiness`: Check required MCP servers, CLIs, APIs... L: `workflow_tools_scoped` -> `tool_requirements_listed` -> `installed_state_recorded_when_available` -> `+1 more`. A: `show_toolbelt`, `open_setup`, `record_tool_check`, `+2 more`.
- `harness-session-inventory`: Normalize cross-harness session, wrapper, MCP... L: `inventory_scope_recorded` -> `session_adapter_matrix_prepared` -> `mcp_inventory_redacted` -> `+4 more`. A: `prepare_harness_session_inventory`, `record_harness_session`, `record_mcp_inventory`, `+2 more`.
- `ops-observability-card`: Report wrapper-safe token, cost, latency, run... L: `telemetry_scope_recorded` -> `external_metric_provider_payload_recorded_when_available` -> `local_metrics_summarized` -> `+3 more`. A: `show_observability`, `record_metric`, `record_metric_provider`, `+2 more`.
- `agent-ops-review`: Prepare a manager-facing quality and throughput... L: `manager_scope_recorded` -> `quality_lanes_prepared` -> `evidence_gaps_named` -> `+2 more`. A: `show_agent_ops_review`, `choose_ops_lane`, `prepare_research_lane`, `+4 more`.
- `agent-debug`: Prepare an evidence-bounded debugging report for a... L: `failure_state_captured` -> `tool_sequence_recorded_when_available` -> `context_pressure_checked` -> `+4 more`. A: `prepare_agent_debug`, `show_agent_debug_report`, `record_agent_failure_capture`, `+2 more`.
- `failure-signal-audit`: Prepare an evidence-bounded audit of swallowed... L: `audit_scope_recorded` -> `source_surfaces_recorded` -> `observed_failure_signals_recorded_when_available` -> `remediation_handoff_prepared_when_needed` -> `+3 more`. A: `prepare_failure_signal_audit`, `show_failure_signal_audit`, `record_failure_signal`, `route_to_remediation_or_visual_qa`, `+1 more`.
- `instinct-ledger`: Prepare an evidence-bounded ledger of atomic... L: `instinct_scope_recorded` -> `source_observations_redacted` -> `atomic_instinct_candidates_prepared` -> `+4 more`. A: `prepare_instinct_ledger`, `show_instinct_ledger`, `record_instinct_candidate`, `+5 more`.
- `skill-scout`: Prepare a metadata-only scout report for existing... L: `skill_scout_scope_recorded` -> `search_keywords_prepared` -> `local_candidates_inventory_prepared_when_observed` -> `external_candidates_reviewed_when_observed` -> `+1 more`. A: `prepare_skill_scout`, `show_skill_scout`, `record_skill_candidate`, `+2 more`.
- `skill-health`: Prepare a metadata-only health dashboard for OMH... L: `skill_health_scope_recorded` -> `catalog_surface_inventory_prepared` -> `failure_signals_clustered_when_observed` -> `+2 more`. A: `prepare_skill_health`, `show_skill_health`, `record_skill_health_signal`, `+2 more`.
- `workflow-learning`: Route self-improvement signals to memory, skill... L: `store_destination_classified` -> `store_destination_recorded` -> `store_destination_reviewed` -> `+8 more`. A: `route_self_improvement_signal`, `review_self_improvement_store_route`, `approve_store_route`, `+21 more`.
- `github-issue-intake`: Turn a public support-chat report into a confirmed... L: `report_received` -> `report_classified` -> `repo_inspected_read_only` -> `+4 more`. A: `show_direction_check`, `confirm_issue_creation`, `record_connector_result`, `+2 more`.
- `decision-recall`: Prepare a scope-limited recall of reviewed rejected... L: `query_scoped` -> `rejected_candidates_matched` -> `recall_rendered`. A: `show_rejected_decision_recall`.
- `run-efficiency`: Render a deterministic report from supplied local... L: `input_validated` -> `local_report_prepared` -> `not_observed_gaps_rendered`. A: `show_run_efficiency_report`.
- `provider-profile-posture`: Prepare a provider/profile posture card without... L: `profile_scoped` -> `secret_presence_declared` -> `posture_prepared`. A: `prepare_provider_profile_posture`.
## Harness Priority
1. Coding requests start with `coding-handling`.
2. Multi-step durable work adds `goal-execution`.
3. Current-source or best-practice questions use the `research` harness and stay in Hermes-side evidence gathering before any coding handoff.
4. Unclear work uses `deep-interview` before `planning`.
5. Risky architecture uses `architect`, then `critic`.
6. User-visible behavior changes add `qa-specialist`.
7. Public commands, examples, or limitations add `docs-specialist`.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |