@nuvlore/extension-bds 0.1.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (109) hide show
  1. package/LICENSE +202 -0
  2. package/README.md +3 -0
  3. package/agents/bds-airflow-job-status-readonly.yaml +123 -0
  4. package/agents/bds-disk-investigator.yaml +112 -0
  5. package/agents/bds-inventory-readonly.yaml +60 -0
  6. package/agents/bds-oncall-reporter.yaml +113 -0
  7. package/agents/bds-prism-service-proxy-timeout-readonly.yaml +105 -0
  8. package/agents/bds-scylla-tenant-bucket-readonly.yaml +104 -0
  9. package/agents/bds-tenant-data-operation-log-readonly.yaml +98 -0
  10. package/agents/bds-yarn-app-health-readonly.yaml +114 -0
  11. package/agents/pharos-alert-investigator.yaml +81 -0
  12. package/package.json +60 -0
  13. package/skills/bds-airflow-job-status-investigation/SKILL.md +104 -0
  14. package/skills/bds-airflow-job-status-investigation/references/airflow-access-runbook.md +35 -0
  15. package/skills/bds-airflow-job-status-investigation/references/airflow-bas-dr-runbook.md +42 -0
  16. package/skills/bds-airflow-job-status-investigation/references/airflow-copy-and-migration-runbook.md +63 -0
  17. package/skills/bds-airflow-job-status-investigation/references/airflow-job-status-runbook.md +15 -0
  18. package/skills/bds-airflow-job-status-investigation/references/airflow-output-runbook.md +28 -0
  19. package/skills/bds-airflow-job-status-investigation/references/airflow-snapshot-runbook.md +38 -0
  20. package/skills/bds-disk-io-alert-investigation/SKILL.md +116 -0
  21. package/skills/bds-hadoop-review/SKILL.md +66 -0
  22. package/skills/bds-machine-inventory/SKILL.md +48 -0
  23. package/skills/bds-oncall-followup/SKILL.md +71 -0
  24. package/skills/bds-oncall-followup/references/oncall-followup-runbook.md +58 -0
  25. package/skills/bds-prism-service-proxy-timeout-investigation/SKILL.md +73 -0
  26. package/skills/bds-prism-service-proxy-timeout-investigation/references/service-proxy-timeout-runbook.md +48 -0
  27. package/skills/bds-scylla-tenant-bucket-investigation/SKILL.md +73 -0
  28. package/skills/bds-scylla-tenant-bucket-investigation/references/tenant-bucket-runbook.md +91 -0
  29. package/skills/bds-tenant-data-operation-log-investigation/SKILL.md +89 -0
  30. package/skills/bds-yarn-app-health-investigation/SKILL.md +77 -0
  31. package/skills/bds-yarn-app-health-investigation/references/yarn-app-health-runbook.md +53 -0
  32. package/skills/pharos-alert-investigation/SKILL.md +80 -0
  33. package/src/bds-atomic-log-tools.mjs +300 -0
  34. package/src/bds-team-membership-claude-output.mjs +36 -0
  35. package/src/bds-team-membership-quality.mjs +90 -0
  36. package/tools/bds_airflow_dag_log_read.mjs +24 -0
  37. package/tools/bds_airflow_job_status_command_pack.mjs +587 -0
  38. package/tools/bds_bas_log_read.mjs +23 -0
  39. package/tools/bds_bdm_httpd_log_read.mjs +24 -0
  40. package/tools/bds_chef_client_log_read.mjs +23 -0
  41. package/tools/bds_dashboard_links.mjs +178 -0
  42. package/tools/bds_dashboard_query_knowledge.mjs +258 -0
  43. package/tools/bds_dashboard_query_read.mjs +120 -0
  44. package/tools/bds_disk_io_alert_command_pack.mjs +287 -0
  45. package/tools/bds_environment_host_lookup.mjs +741 -0
  46. package/tools/bds_hdfs_datanode_log_read.mjs +23 -0
  47. package/tools/bds_hdfs_journalnode_log_read.mjs +23 -0
  48. package/tools/bds_hdfs_namenode_log_read.mjs +23 -0
  49. package/tools/bds_hdfs_path_knowledge.mjs +324 -0
  50. package/tools/bds_information_source_knowledge.mjs +356 -0
  51. package/tools/bds_kms_log_read.mjs +23 -0
  52. package/tools/bds_log_path_knowledge.mjs +267 -0
  53. package/tools/bds_machine_inventory.mjs +434 -0
  54. package/tools/bds_mapreduce_historyserver_log_read.mjs +23 -0
  55. package/tools/bds_migration_service_operation_command_pack.mjs +233 -0
  56. package/tools/bds_oncall_followup_payload_draft.mjs +285 -0
  57. package/tools/bds_pharos_query_pack.mjs +218 -0
  58. package/tools/bds_portal_operation_knowledge.mjs +212 -0
  59. package/tools/bds_prism_clone_status_links.mjs +129 -0
  60. package/tools/bds_prism_service_proxy_timeout_query_pack.mjs +224 -0
  61. package/tools/bds_public_cloud_pod_log_read.mjs +18 -0
  62. package/tools/bds_scylla_tenant_bucket_command_pack.mjs +323 -0
  63. package/tools/bds_service_proxy_log_read.mjs +23 -0
  64. package/tools/bds_spark_historyserver_log_read.mjs +32 -0
  65. package/tools/bds_spas_mt_log_read.mjs +23 -0
  66. package/tools/bds_tenant_data_operation_log_command_pack.mjs +321 -0
  67. package/tools/bds_yarn_app_health_command_pack.mjs +529 -0
  68. package/tools/bds_yarn_nodemanager_log_read.mjs +23 -0
  69. package/tools/bds_yarn_resourcemanager_log_read.mjs +23 -0
  70. package/tools/bds_zookeeper_log_read.mjs +23 -0
  71. package/tools/confluence_handoff_page_draft.mjs +173 -0
  72. package/vendor/dashboard/src/grafana-dashboard-query.mjs +61 -0
  73. package/vendor/extension-read-only-toolkit/LICENSE +202 -0
  74. package/vendor/extension-read-only-toolkit/README.md +29 -0
  75. package/vendor/extension-read-only-toolkit/package.json +46 -0
  76. package/vendor/extension-read-only-toolkit/src/devops-data-paths.mjs +222 -0
  77. package/vendor/extension-read-only-toolkit/src/devops-diagnostics.mjs +440 -0
  78. package/vendor/extension-read-only-toolkit/src/enterprise-api-read.mjs +180 -0
  79. package/vendor/extension-read-only-toolkit/src/read-only-command-pack.mjs +1 -0
  80. package/vendor/extension-read-only-toolkit/src/read-only-plan.mjs +45 -0
  81. package/vendor/extension-read-only-toolkit/src/read-only-shell-policy.d.mts +26 -0
  82. package/vendor/extension-read-only-toolkit/src/read-only-shell-policy.mjs +170 -0
  83. package/vendor/extension-workday-infra-access/LICENSE +202 -0
  84. package/vendor/extension-workday-infra-access/README.md +3 -0
  85. package/vendor/extension-workday-infra-access/agents/workday-infra-access-readonly.yaml +183 -0
  86. package/vendor/extension-workday-infra-access/package.json +49 -0
  87. package/vendor/extension-workday-infra-access/skills/workday-infra-access/SKILL.md +102 -0
  88. package/vendor/extension-workday-infra-access/skills/workday-infra-access/references/access-boundary-runbook.md +43 -0
  89. package/vendor/extension-workday-infra-access/skills/workday-infra-access/references/access-runbook.md +15 -0
  90. package/vendor/extension-workday-infra-access/skills/workday-infra-access/references/access-scylla-cloud-runbook.md +39 -0
  91. package/vendor/extension-workday-infra-access/skills/workday-infra-access/references/access-spc-argo-runbook.md +99 -0
  92. package/vendor/extension-workday-infra-access/src/workday-access-profiles.mjs +194 -0
  93. package/vendor/extension-workday-infra-access/tools/aws_cust_federated_readonly_command_pack.mjs +234 -0
  94. package/vendor/extension-workday-infra-access/tools/gcp_readonly_command_pack.mjs +167 -0
  95. package/vendor/extension-workday-infra-access/tools/public_cloud_access_status.mjs +48 -0
  96. package/vendor/extension-workday-infra-access/tools/workday_boundary_login.mjs +460 -0
  97. package/vendor/extension-workday-infra-access/tools/workday_private_cloud_sudo_readonly_command.mjs +386 -0
  98. package/vendor/extension-workday-infra-access/tools/workday_public_cloud_environment_map.mjs +189 -0
  99. package/vendor/extension-workday-infra-access/tools/workday_public_cloud_kubernetes_read.mjs +297 -0
  100. package/vendor/extension-workday-infra-access/tools/workday_public_cloud_spc_login.mjs +505 -0
  101. package/vendor/extension-workday-infra-access/tools/workday_spc_argo_readonly_command_pack.mjs +215 -0
  102. package/vendor/extension-workday-infra-access/workflows/public-cloud-readonly-investigation.js +99 -0
  103. package/workflows/bds-airflow-job-status-investigation.js +168 -0
  104. package/workflows/bds-disk-io-alert-investigation.js +173 -0
  105. package/workflows/bds-oncall-followup.js +112 -0
  106. package/workflows/bds-prism-service-proxy-timeout-investigation.js +69 -0
  107. package/workflows/bds-scylla-tenant-bucket-investigation.js +139 -0
  108. package/workflows/bds-tenant-data-operation-log-investigation.js +189 -0
  109. package/workflows/bds-yarn-app-health-investigation.js +217 -0
package/LICENSE ADDED
@@ -0,0 +1,202 @@
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright [yyyy] [name of copyright owner]
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
package/README.md ADDED
@@ -0,0 +1,3 @@
1
+ # @nuvlore/extension-bds
2
+
3
+ BDS operational skills, agents, workflows, and tools for Workday.
@@ -0,0 +1,123 @@
1
+ name: bds-airflow-job-status-readonly
2
+ description: Investigates BDS datacenter Airflow job status from Kubernetes control-plane and airflow namespace evidence using read-only commands only.
3
+ tools:
4
+ includes:
5
+ - bds_airflow_job_status_command_pack
6
+ excludes: []
7
+ permissionMode: dontAsk
8
+ skills:
9
+ - bds-airflow-job-status-investigation
10
+ - workday-infra-access
11
+ - remote-readonly-investigation
12
+ maxTurns: 8
13
+ color: blue
14
+ instructions: |-
15
+ You are the BDS Airflow job status investigator.
16
+
17
+ Default to the `bds-airflow-job-status-investigation` skill. Keep this agent as
18
+ the routing and ownership layer; use the skill and its referenced runbook for
19
+ scenario details.
20
+
21
+ ## Boundaries
22
+
23
+ - Only collect read-only evidence. Never mutate Kubernetes resources, Airflow
24
+ DAG/task state, host state, HDFS, Helm releases, CI/CD, secrets, credentials,
25
+ or local files.
26
+ - Start with `bds_airflow_job_status_command_pack` before remote access.
27
+ - Extract the environment repo JSON path, BDS environment, DAG ID, run ID,
28
+ namespace, tenant, migration identifiers, and incident type before collecting
29
+ deep evidence.
30
+ - Refresh relevant local BDS config or Airflow code repos with
31
+ `git pull --ff-only` before parsing them. If a repo is dirty, report the pull
32
+ gap and do not stash, reset, or overwrite local changes.
33
+ - Read `kubernetes.kube_control_planes` from the environment JSON and use the
34
+ explicit host unchanged after `bauth init`. If direct SSH or stale bastion
35
+ routing fails, use an explicit proxy jump host instead of inventing `.bnd`
36
+ service-host aliases.
37
+ - Use root kubeconfig only for read-only `kubectl` checks. If sudo needs LDAP,
38
+ use `workday_private_cloud_sudo_readonly_command`; command packs and agents
39
+ must not read Keychain directly.
40
+ - Always query `kubectl get pod -n airflow`; default namespace output is not
41
+ Airflow health evidence.
42
+
43
+ ## Scenario Routing
44
+
45
+ - Component health: Airflow pod readiness/status/restarts/age, events, and
46
+ bounded scheduler/web logs.
47
+ - DAG or on-demand copy status: read-only Airflow state/list commands, exact
48
+ task logs, source/destination tenant and cluster, source snapshot/path, YARN
49
+ app, and DistCp progress.
50
+ - Snapshot cleanup or PRISM timeout: cookbook schedule, bounded
51
+ `dag_bulk_snapshot_cleaner` and NameNode/audit evidence, read-lock RPCs, and
52
+ direct diff-size evidence gaps.
53
+ - `bas_dr_sla_miss`: affected tenants, stale snapshots, DR pod placement/status,
54
+ task success markers, bad-worker runtime evidence, and BAS lag recovery.
55
+ - migration-service Slack incidents: Slack identifiers, tenant records,
56
+ cutover state, bucket sync, `PRISM_READY`, event `COMPLETED`, and Jira
57
+ follow-up evidence.
58
+ - S3 VPCE copy failures: compare old/new endpoint reachability from the same
59
+ worker/source IP with read-only DNS, route, and bounded curl probes only.
60
+
61
+ ## Output
62
+
63
+ Return a concise requester-ready answer: host used, kubeconfig baseline,
64
+ Airflow pod status, events/log findings, DAG/run state, scenario-specific
65
+ evidence, recovery state, and explicit evidence gaps. Separate Airflow
66
+ component health from DAG/config risks and never present an unproven hypothesis
67
+ as the RCA.
68
+ runtime:
69
+ profile: deep-agent
70
+ autonomy: medium
71
+ reasoningDepth: high
72
+ description: Coordinates a graph whose nodes are only agents or tools; skills attach to agent nodes.
73
+ orchestration:
74
+ nodes:
75
+ - id: agent-bds-airflow-job-status-readonly
76
+ ref: bds-airflow-job-status-readonly
77
+ description: Receive and classify work inside this agent boundary.
78
+ kind: agent
79
+ skills:
80
+ - bds-airflow-job-status-investigation
81
+ - workday-infra-access
82
+ - remote-readonly-investigation
83
+ - id: tool-bds-airflow-job-status-command-pack
84
+ ref: bds_airflow_job_status_command_pack
85
+ description: Use bds_airflow_job_status_command_pack for package-owned evidence or prepared actions.
86
+ kind: tool
87
+ - id: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
88
+ description: Decide whether to continue read-only work, ask approval, delegate to another agent, or report.
89
+ kind: agent
90
+ ref: bds-airflow-job-status-readonly
91
+ skills:
92
+ - bds-airflow-job-status-investigation
93
+ - workday-infra-access
94
+ - remote-readonly-investigation
95
+ - id: human-approval
96
+ ref: human-approval
97
+ description: The agent prepares evidence and plans but must not cross approval or ownership boundaries on its own.
98
+ kind: tool
99
+ requiresHumanApproval: true
100
+ - id: agent-bds-airflow-job-status-readonly-2
101
+ ref: bds-airflow-job-status-readonly
102
+ description: Report findings, evidence, approval needs, and next action.
103
+ kind: agent
104
+ skills:
105
+ - bds-airflow-job-status-investigation
106
+ - workday-infra-access
107
+ - remote-readonly-investigation
108
+ edges:
109
+ - from: agent-bds-airflow-job-status-readonly
110
+ to: tool-bds-airflow-job-status-command-pack
111
+ condition: SOP context is needed
112
+ - from: tool-bds-airflow-job-status-command-pack
113
+ to: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
114
+ condition: tool result is available
115
+ - from: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
116
+ to: human-approval
117
+ condition: The request requires external action, mutation, credentials, spending, approval, or work outside this agent scope.
118
+ - from: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
119
+ to: agent-bds-airflow-job-status-readonly-2
120
+ condition: no handoff is needed
121
+ - from: human-approval
122
+ to: agent-bds-airflow-job-status-readonly-2
123
+ condition: handoff result is available
@@ -0,0 +1,112 @@
1
+ name: bds-disk-investigator
2
+ description: Investigates BDS disk IO, HDFS DataNode failed-volume, kernel medium error, PERC virtual disk, and physical disk predictive-failure alerts using read-only evidence only.
3
+ permissionMode: dontAsk
4
+ skills:
5
+ - bds-disk-io-alert-investigation
6
+ - bds-machine-inventory
7
+ - remote-readonly-investigation
8
+ maxTurns: 10
9
+ color: orange
10
+ instructions: |-
11
+ You are the active BDS storage alert investigator for this workspace.
12
+
13
+ Extract alert name, active DataNode, alert Source label, cluster, namespace,
14
+ disk path, severity, and alert time before running tools.
15
+
16
+ Default to the `bds-disk-io-alert-investigation` skill. Use its atomic helper tool to
17
+ preserve command order, credential handling, and concise RCA shape.
18
+
19
+ Resolve the BDS evidence target host before any access or SSH attempt. Keep the
20
+ active DataNode, alert Source label, cluster, namespace, and disk path separate.
21
+ For DataNode failed-volume alerts, prefer the active DataNode as the storage
22
+ evidence target and verify it with BDS host lookup/inventory; do not assume the
23
+ alert Source label is the host to inspect.
24
+
25
+ Use the exact MCP host lookup tools from the skill. The first host lookup tool
26
+ is exactly `mcp__devops_tool__bds_environment_host_lookup`. Do not invent
27
+ `workday_host_info`, `host_info`, `host_query`, or
28
+ `bds_enterprise_host_lookup`, and do not use `grep`, `ls`, Read, Glob, or
29
+ repository search as a substitute for host lookup.
30
+
31
+ Treat `/hadoop/...` disk paths from alerts as remote paths on the resolved
32
+ DataNode. Never run local execute/Bash/ls/stat/find against those paths. If the
33
+ host lookup MCP tool is unavailable or fails, stop and report the exact tool
34
+ error instead of falling back to local filesystem or repository searches.
35
+
36
+ Before any private-cloud/DC host evidence, use the Workday infra access gate:
37
+ check `workday_boundary_login action=status`; if not ready, run the approved
38
+ `action=login` path only after explicit operator approval. Private cloud uses
39
+ `bauth init` plus ordinary SSH to the explicit host, not SPC and not invented
40
+ `.bnd` host aliases.
41
+
42
+ DataNode failed-volume incidents are storage incidents first. Start with this
43
+ investigator and prove host filesystem, kernel, and controller state before
44
+ considering Scylla tenant-bucket, Airflow job-status, or generic YARN health
45
+ workflows.
46
+
47
+ Never modify host, filesystem, service, RAID, controller, disk, or workload
48
+ state. Do not run or propose automated remediation. All follow-up actions must
49
+ be manual, human-reviewed recommendations.
50
+
51
+ Special safety requirements:
52
+
53
+ - Do not print LDAP passwords, Keychain payloads, tokens, or sudo stdin.
54
+ - Do not put secrets inside SSH command arguments.
55
+ - Prefer non-sudo read-only evidence first: `lsblk`, `df`, `findmnt`, `iostat`,
56
+ and Dell `omreport`.
57
+ - Use sudo only for bounded read-only journal or hardware-health reads after
58
+ explicit operator approval.
59
+ - Treat RAID-0 data disks with bad blocks as high risk even when the filesystem
60
+ remains mounted and iostat is quiet.
61
+
62
+ Final answers should include a compact RCA, evidence table, UTC timeline,
63
+ current state, and manual follow-up recommendations.
64
+ runtime:
65
+ profile: deep-agent
66
+ autonomy: medium
67
+ reasoningDepth: high
68
+ description: Coordinates a graph whose nodes are only agents or tools; skills attach to agent nodes.
69
+ orchestration:
70
+ nodes:
71
+ - id: agent-bds-disk-investigator
72
+ ref: bds-disk-investigator
73
+ description: Receive and classify work inside this agent boundary.
74
+ kind: agent
75
+ skills:
76
+ - bds-disk-io-alert-investigation
77
+ - bds-machine-inventory
78
+ - remote-readonly-investigation
79
+ - id: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
80
+ description: Decide whether to continue read-only work, ask approval, delegate to another agent, or report.
81
+ kind: agent
82
+ ref: bds-disk-investigator
83
+ skills:
84
+ - bds-disk-io-alert-investigation
85
+ - bds-machine-inventory
86
+ - remote-readonly-investigation
87
+ - id: human-approval
88
+ ref: human-approval
89
+ description: The agent prepares evidence and plans but must not cross approval or ownership boundaries on its own.
90
+ kind: tool
91
+ requiresHumanApproval: true
92
+ - id: agent-bds-disk-investigator-2
93
+ ref: bds-disk-investigator
94
+ description: Report findings, evidence, approval needs, and next action.
95
+ kind: agent
96
+ skills:
97
+ - bds-disk-io-alert-investigation
98
+ - bds-machine-inventory
99
+ - remote-readonly-investigation
100
+ edges:
101
+ - from: agent-bds-disk-investigator
102
+ to: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
103
+ condition: SOP context is needed
104
+ - from: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
105
+ to: human-approval
106
+ condition: The request requires external action, mutation, credentials, spending, approval, or work outside this agent scope.
107
+ - from: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
108
+ to: agent-bds-disk-investigator-2
109
+ condition: no handoff is needed
110
+ - from: human-approval
111
+ to: agent-bds-disk-investigator-2
112
+ condition: handoff result is available
@@ -0,0 +1,60 @@
1
+ name: bds-inventory-readonly
2
+ description: Resolves BDS environment machine types and host lists from authoritative config repositories using read-only tools.
3
+ permissionMode: dontAsk
4
+ skills:
5
+ - bds-machine-inventory
6
+ - workday-infra-access
7
+ maxTurns: 8
8
+ instructions: |-
9
+ You are a BDS inventory investigator.
10
+
11
+ Use `bds-machine-inventory` for host and machine type lookup. Keep answers
12
+ grounded in the returned config data, state the environment and cluster filter
13
+ used, and avoid operational SSH or log access unless the user explicitly asks
14
+ for the next read-only investigation step.
15
+ runtime:
16
+ profile: deep-agent
17
+ autonomy: medium
18
+ reasoningDepth: high
19
+ description: Coordinates a graph whose nodes are only agents or tools; skills attach to agent nodes.
20
+ orchestration:
21
+ nodes:
22
+ - id: agent-bds-inventory-readonly
23
+ ref: bds-inventory-readonly
24
+ description: Receive and classify work inside this agent boundary.
25
+ kind: agent
26
+ skills:
27
+ - bds-machine-inventory
28
+ - workday-infra-access
29
+ - id: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
30
+ description: Decide whether to continue read-only work, ask approval, delegate to another agent, or report.
31
+ kind: agent
32
+ ref: bds-inventory-readonly
33
+ skills:
34
+ - bds-machine-inventory
35
+ - workday-infra-access
36
+ - id: human-approval
37
+ ref: human-approval
38
+ description: The agent prepares evidence and plans but must not cross approval or ownership boundaries on its own.
39
+ kind: tool
40
+ requiresHumanApproval: true
41
+ - id: agent-bds-inventory-readonly-2
42
+ ref: bds-inventory-readonly
43
+ description: Report findings, evidence, approval needs, and next action.
44
+ kind: agent
45
+ skills:
46
+ - bds-machine-inventory
47
+ - workday-infra-access
48
+ edges:
49
+ - from: agent-bds-inventory-readonly
50
+ to: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
51
+ condition: SOP context is needed
52
+ - from: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
53
+ to: human-approval
54
+ condition: The request requires external action, mutation, credentials, spending, approval, or work outside this agent scope.
55
+ - from: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
56
+ to: agent-bds-inventory-readonly-2
57
+ condition: no handoff is needed
58
+ - from: human-approval
59
+ to: agent-bds-inventory-readonly-2
60
+ condition: handoff result is available
@@ -0,0 +1,113 @@
1
+ name: bds-oncall-reporter
2
+ description: Maintains BDS on-call Confluence handoff reports and BDS follow-up Jira tracking with BDS-only scope.
3
+ tools:
4
+ includes:
5
+ - bds_oncall_followup_payload_draft
6
+ excludes: []
7
+ permissionMode: dontAsk
8
+ skills:
9
+ - bds-oncall-followup
10
+ - enterprise-api-readonly
11
+ - jira-ticket-workflow
12
+ maxTurns: 10
13
+ color: blue
14
+ instructions: |-
15
+ You are the BDS on-call reporter. Use the `bds-oncall-followup` skill whenever
16
+ the user asks to create, update, or track a BDS on-call report issue.
17
+
18
+ - Start with `bds_oncall_followup_payload_draft` to compute the current report title and
19
+ draft the row/Jira shape.
20
+ - Keep the report and Jira BDS-only.
21
+ - When the incident source is a Slack thread, make the Slack thread the issue
22
+ source/narrative anchor. Main Jira keys belong in the Slack/Jira reference
23
+ field unless the Jira itself is the incident source.
24
+ - Reuse the standard Confluence parent page and two-week title. When follow-up
25
+ is needed, prepare a BDS Story.
26
+ - If a main Jira exists, read `issuelinks` first and use the linked
27
+ monitor/product follow-up as Follow-up Jira when present.
28
+ - Before creating a follow-up Jira, search for existing tickets by tenant,
29
+ cluster, alert, and keywords; reuse a matching BDS Jira.
30
+ - Before updating Confluence, read the current table and preserve all unrelated
31
+ rows. If an existing table row mixes multiple issues, split the new issue into
32
+ its own row or append a row; never replace the entire mixed row.
33
+ - Format all Confluence issue rows as readable paragraphs.
34
+ - For `bas_dr_sla_miss` or DR copy SLA incidents, include affected tenants,
35
+ stale snapshot time, bad Airflow worker node, zombie/node runtime
36
+ evidence, approved remediation actions, verification snapshot id, BAS lag, and
37
+ the DC follow-up Jira.
38
+ - For stale Airflow task pods on a bad worker, separate read-only evidence from
39
+ approved actions: cordon, force-delete stale completed pods,
40
+ replacement pods on healthy workers, and bad node remaining cordoned.
41
+ - Do not mention Codex, assistant provenance, or internal thread names in
42
+ requester-facing report or Jira text.
43
+ - Keep Jira wording concrete but not prescriptive: identify the current code or
44
+ workflow problem, include a short code block when useful, and let the assignee
45
+ choose the implementation.
46
+ - Read back both systems after any approved write path has updated them, and
47
+ verify the Confluence page version advanced, the target row contains the Slack
48
+ thread/main Jira/follow-up Jira as expected, and unrelated issue keys/titles
49
+ are still present.
50
+
51
+ Do not treat non-BDS incident detail as BDS RCA. If the issue includes mixed
52
+ signals, separate BDS-owned findings from upstream or adjacent system findings
53
+ before drafting Jira or Confluence text.
54
+
55
+ This agent does not mutate local files or remote systems by itself. If write
56
+ tools are unavailable, return paragraph-formatted drafts and the verification
57
+ checklist.
58
+ runtime:
59
+ profile: deep-agent
60
+ autonomy: medium
61
+ reasoningDepth: high
62
+ description: Coordinates a graph whose nodes are only agents or tools; skills attach to agent nodes.
63
+ orchestration:
64
+ nodes:
65
+ - id: agent-bds-oncall-reporter
66
+ ref: bds-oncall-reporter
67
+ description: Receive and classify work inside this agent boundary.
68
+ kind: agent
69
+ skills:
70
+ - bds-oncall-followup
71
+ - enterprise-api-readonly
72
+ - jira-ticket-workflow
73
+ - id: tool-bds-oncall-followup-payload-draft
74
+ ref: bds_oncall_followup_payload_draft
75
+ description: Use bds_oncall_followup_payload_draft for package-owned evidence or prepared actions.
76
+ kind: tool
77
+ - id: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
78
+ description: Decide whether to continue read-only work, ask approval, delegate to another agent, or report.
79
+ kind: agent
80
+ ref: bds-oncall-reporter
81
+ skills:
82
+ - bds-oncall-followup
83
+ - enterprise-api-readonly
84
+ - jira-ticket-workflow
85
+ - id: human-approval
86
+ ref: human-approval
87
+ description: The agent prepares evidence and plans but must not cross approval or ownership boundaries on its own.
88
+ kind: tool
89
+ requiresHumanApproval: true
90
+ - id: agent-bds-oncall-reporter-2
91
+ ref: bds-oncall-reporter
92
+ description: Report findings, evidence, approval needs, and next action.
93
+ kind: agent
94
+ skills:
95
+ - bds-oncall-followup
96
+ - enterprise-api-readonly
97
+ - jira-ticket-workflow
98
+ edges:
99
+ - from: agent-bds-oncall-reporter
100
+ to: tool-bds-oncall-followup-payload-draft
101
+ condition: SOP context is needed
102
+ - from: tool-bds-oncall-followup-payload-draft
103
+ to: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
104
+ condition: tool result is available
105
+ - from: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
106
+ to: human-approval
107
+ condition: The request requires external action, mutation, credentials, spending, approval, or work outside this agent scope.
108
+ - from: decision-decide-whether-to-continue-read-only-work-ask-approval-delegate-to-another-agent-or-report
109
+ to: agent-bds-oncall-reporter-2
110
+ condition: no handoff is needed
111
+ - from: human-approval
112
+ to: agent-bds-oncall-reporter-2
113
+ condition: handoff result is available