Ops Observability Card
This is a Hermes-native ops-observability-card workflow skill.
Why This Exists
ops-observability-card exists so Hermes users can ask for this workflow in chat and receive a structured, evidence-bounded OMH operating surface instead of ad hoc narration.
Do Not Use When
- The request is already handled by a narrower explicit skill with stronger evidence.
- The user asks OMH to secretly run external platforms, connectors, schedulers, file exports, or runtime agents.
- The only safe answer is to ask for missing authority, credentials, target, or observed evidence first.
Examples
Good example:
- Prompt: ops-observability-card show token, cost, latency, supplied Prometheus/Grafana metrics, and missing service-quality evidence for this loop.
- Expected behavior: Produce
prepare_ops_observability_card with required context, wrapper actions, and not-evidence boundaries.
- Why: The prompt names a real workflow surface that Hermes can orchestrate without hiding execution.
Bad example:
- Prompt: ops-observability-card claim exact provider billing, healthy SLO, incident closure, or remediation completion from local estimates.
- Expected behavior: Report the missing observed evidence or authority instead of claiming the external step happened.
- Why: Prepared OMH guidance is not platform, runtime, connector, file, memory, or delivery evidence.
Completion Checklist
- The run or workflow scope, metric window, failure modes, and cost/latency boundary are named.
- Local telemetry, provider truth, billing truth, and completion evidence are separate states.
- Warnings name the next measurement or operator review action.
Recovery Notes
- If provider metrics are unavailable, report only local metadata and mark provider truth not_observed.
- If cost or latency looks risky, surface a warning plus the next measurement rather than a completion claim.
Workflow Lane
- Current lane: Automation and status (
achievements, workspace-audit, production-audit, automation-blueprint, github-event-ops, github-issue-intake, buzz, agent-board, +35 more) - schedules, status, health, and ops review.
- If intent belongs to another lane, hand back to
oh-my-hermes or name the adjacent workflow.
- Shared product, routing, compatibility, and evidence rules:
omh-routing/references/skill-common-rail.md.
Use When
Use when automation, loops, gateway work, executor handoffs, or service operations need a safe command-board for cost, latency, token, history, failure-mode, supplied metric-provider, and service-quality visibility.
Strong routing signals: `ops-observability-card`, `observability card`, `operations command board`, `ops command board`, `service quality board`, `service quality`, `external metric provider`, `metric provider`, `prometheus metrics`, `grafana metrics`, `cost telemetry`, `latency telemetry`, `token telemetry`, `run history`, `loop telemetry`, `failure mode`, `monitor tokens`, `service health`, `slo dashboard`, `비용`, `토큰`, `지연시간`, `관측성`, `운영 지휘판`, `서비스 품질`, `메트릭`, `프로메테우스`, `그라파나`
Catalog Metadata
Category: observability
Phase: telemetry-card
Hermes role: tracker
Quality tier: workflow-surface-gated
Reasoning demand: standard
Quality bar:
- Name the user-facing workflow objective, required context, next action, and stop condition.
- Separate prepared guidance from observed platform, runtime, connector, file, memory, or delivery evidence.
- Expose missing tools, credentials, targets, or observations as user-visible gaps.
- When advising what to record per model call, require the five answers - which model, how long, how many tokens in and out, whether it succeeded, and why it failed - with streaming calls adding time-to-first-token; the attribute tiers live in
omh-agent-ops-review/references/instrumentation-ladder.md.
- Aggregate cost at the four levels - per call, per agent run, per session, per user - and name the budget threshold each level checks against before recommending any optimization signal.
- Never recommend logging raw prompts, responses, or secret values into telemetry; counts, lengths, hashes, and key-set booleans carry the signal without the leak.
Handoff policy:
Keep this as Hermes-facing orchestration guidance first. Prepare executor, connector, gateway, or host-runtime handoff only when the user accepts that next step and observed evidence can be recorded.
Required inputs:
- user request
- target context
- delivery or status expectation
- known missing evidence
Expected outputs:
- ops-observability-card/v1 card or guidance
- external_metric_provider/v1 payload contract
- external_metric_provider_adapter/v1 adapter contract
- ops_service_quality_board/v1 service-quality board
- typed service-quality downgrade gaps
- next action
- prepared-vs-observed boundary
Artifact expectations:
- ops-observability-card/v1 metadata-only runtime or wrapper card when recorded
- external_metric_provider/v1 supplied metric payload when available
- external_metric_provider_adapter/v1 connector-ready adapter metadata when available
- ops_service_quality_board/v1 evidence-gated service-quality board
Artifact contracts:
This label denotes the machine-enforcement level, not a skill quality score and not an observed evidence state.
- contract_id:
ops_service_quality_board/v1; enforcement_level: executable_validated; consumer_id: validate_ops_service_quality_board
Safety rules:
- An ops observability card is not billing truth, provider quota truth, live metric-provider access, complete tracing, SLO pass, incident closure, root-cause proof, remediation completion, performance proof, or successful workflow completion evidence.
- Do not claim connector, gateway, runtime, file generation, memory mutation, or host automation evidence from prepared guidance.
Runtime Evidence
Preferred harness for this skill: ops-observability-card.
omh runtime record --skill ops-observability-card --harness ops-observability-card --status started
Record observed delegation results; otherwise return not_available or not_observed.
Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.
- Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes.
Preserve workflow intent and stop conditions; verify before claiming completion.
Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.
Shared product, compatibility, topology, memory, harness, and execution rules: omh-routing/references/skill-common-rail.md. Load it when applicable; otherwise name an unavailable capability.
1---
2name: "omh-ops-observability-card"
3description: "[omh] Hermes ops observability workflow: prepare an operations command-board for wrapper-safe token, cost, latency, run history, queue, failure-mode, external metric-provider, and service-quality evidence boundaries. Use when the user says: ops-observability-card, observability card, operations command board, ops command board, service quality board, service quality, external metric provider, metric provider."
4metadata:
5 hermes:
6 tags: [workflow, oh-my-hermes, observability]
7 category: observability
8 phase: telemetry-card
9 role: tracker
10 quality_tier: workflow-surface-gated
11---
12
13# Ops Observability Card
14
15This is a Hermes-native `ops-observability-card` workflow skill.
16
17## Why This Exists
18
19`ops-observability-card` exists so Hermes users can ask for this workflow in chat and receive a structured, evidence-bounded OMH operating surface instead of ad hoc narration.
20
21## Do Not Use When
22
23- The request is already handled by a narrower explicit skill with stronger evidence.
24- The user asks OMH to secretly run external platforms, connectors, schedulers, file exports, or runtime agents.
25- The only safe answer is to ask for missing authority, credentials, target, or observed evidence first.
26
27## Examples
28
29Good example:
30
31- Prompt: ops-observability-card show token, cost, latency, supplied Prometheus/Grafana metrics, and missing service-quality evidence for this loop.
32- Expected behavior: Produce `prepare_ops_observability_card` with required context, wrapper actions, and not-evidence boundaries.
33- Why: The prompt names a real workflow surface that Hermes can orchestrate without hiding execution.
34
35Bad example:
36
37- Prompt: ops-observability-card claim exact provider billing, healthy SLO, incident closure, or remediation completion from local estimates.
38- Expected behavior: Report the missing observed evidence or authority instead of claiming the external step happened.
39- Why: Prepared OMH guidance is not platform, runtime, connector, file, memory, or delivery evidence.
40
41## Completion Checklist
42
43- The run or workflow scope, metric window, failure modes, and cost/latency boundary are named.
44- Local telemetry, provider truth, billing truth, and completion evidence are separate states.
45- Warnings name the next measurement or operator review action.
46
47## Recovery Notes
48
49- If provider metrics are unavailable, report only local metadata and mark provider truth not_observed.
50- If cost or latency looks risky, surface a warning plus the next measurement rather than a completion claim.
51
52## Workflow Lane
53
54- Current lane: **Automation and status** (`achievements`, `workspace-audit`, `production-audit`, `automation-blueprint`, `github-event-ops`, `github-issue-intake`, `buzz`, `agent-board`, `+35 more`) - schedules, status, health, and ops review.
55- If intent belongs to another lane, hand back to `oh-my-hermes` or name the adjacent workflow.
56- Shared product, routing, compatibility, and evidence rules: `omh-routing/references/skill-common-rail.md`.
57
58## Use When
59
60Use when automation, loops, gateway work, executor handoffs, or service operations need a safe command-board for cost, latency, token, history, failure-mode, supplied metric-provider, and service-quality visibility.
61
62 Strong routing signals: `ops-observability-card`, `observability card`, `operations command board`, `ops command board`, `service quality board`, `service quality`, `external metric provider`, `metric provider`, `prometheus metrics`, `grafana metrics`, `cost telemetry`, `latency telemetry`, `token telemetry`, `run history`, `loop telemetry`, `failure mode`, `monitor tokens`, `service health`, `slo dashboard`, `비용`, `토큰`, `지연시간`, `관측성`, `운영 지휘판`, `서비스 품질`, `메트릭`, `프로메테우스`, `그라파나`
63
64## Catalog Metadata
65
66Category: `observability`
67Phase: `telemetry-card`
68Hermes role: `tracker`
69Quality tier: `workflow-surface-gated`
70Reasoning demand: `standard`
71
72Quality bar:
73
74- Name the user-facing workflow objective, required context, next action, and stop condition.
75- Separate prepared guidance from observed platform, runtime, connector, file, memory, or delivery evidence.
76- Expose missing tools, credentials, targets, or observations as user-visible gaps.
77- When advising what to record per model call, require the five answers - which model, how long, how many tokens in and out, whether it succeeded, and why it failed - with streaming calls adding time-to-first-token; the attribute tiers live in `omh-agent-ops-review/references/instrumentation-ladder.md`.
78- Aggregate cost at the four levels - per call, per agent run, per session, per user - and name the budget threshold each level checks against before recommending any optimization signal.
79- Never recommend logging raw prompts, responses, or secret values into telemetry; counts, lengths, hashes, and key-set booleans carry the signal without the leak.
80
81Handoff policy:
82
83Keep this as Hermes-facing orchestration guidance first. Prepare executor, connector, gateway, or host-runtime handoff only when the user accepts that next step and observed evidence can be recorded.
84
85Required inputs:
86
87- user request
88- target context
89- delivery or status expectation
90- known missing evidence
91
92Expected outputs:
93
94- ops-observability-card/v1 card or guidance
95- external_metric_provider/v1 payload contract
96- external_metric_provider_adapter/v1 adapter contract
97- ops_service_quality_board/v1 service-quality board
98- typed service-quality downgrade gaps
99- next action
100- prepared-vs-observed boundary
101
102Artifact expectations:
103
104- ops-observability-card/v1 metadata-only runtime or wrapper card when recorded
105- external_metric_provider/v1 supplied metric payload when available
106- external_metric_provider_adapter/v1 connector-ready adapter metadata when available
107- ops_service_quality_board/v1 evidence-gated service-quality board
108
109Artifact contracts:
110
111This label denotes the machine-enforcement level, not a skill quality score and not an observed evidence state.
112
113- contract_id: `ops_service_quality_board/v1`; enforcement_level: `executable_validated`; consumer_id: `validate_ops_service_quality_board`
114
115Safety rules:
116
117- An ops observability card is not billing truth, provider quota truth, live metric-provider access, complete tracing, SLO pass, incident closure, root-cause proof, remediation completion, performance proof, or successful workflow completion evidence.
118- Do not claim connector, gateway, runtime, file generation, memory mutation, or host automation evidence from prepared guidance.
119
120## Runtime Evidence
121
122Preferred harness for this skill: `ops-observability-card`.
123
124```sh
125omh runtime record --skill ops-observability-card --harness ops-observability-card --status started
126```
127
128Record observed delegation results; otherwise return `not_available` or `not_observed`.
129Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.
130- Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes.
131Preserve workflow intent and stop conditions; verify before claiming completion.
132
133Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.
134
135Shared product, compatibility, topology, memory, harness, and execution rules: `omh-routing/references/skill-common-rail.md`. Load it when applicable; otherwise name an unavailable capability.
rlaope