Borrowing it
Nothing to install: this file belongs to Smana/cloud-native-ref. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Smana/cloud-native-ref/main/.agents/skills/verify-spec/SKILL.mdgit clone --depth 1 https://github.com/Smana/cloud-native-refWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/smana/cloud-native-ref/verify-spec)<a href="https://agentmods.dev/skills/smana/cloud-native-ref/verify-spec"><img src="https://agentmods.dev/badge/skills/smana/cloud-native-ref/verify-spec/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/smana/cloud-native-ref/verify-spec"><img src="https://agentmods.dev/badge/skills/smana/cloud-native-ref/verify-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.01479 |
| Opus 5.5 | $0.00021 | $0.00592 |
| Sonnet 5.5 | $0.00010 | $0.00296 |
| Haiku 4.5 | $0.00005 | $0.00148 |
Grade A, and why
verify-spec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Spec Skill
Close the acceptance loop. Merged work is not "done" until the design's success criteria are observably met in the target cluster.
Workflow
1. Locate inputs
Resolve $ARGUMENTS to a design document under docs/superpowers/specs/. Accept a bare topic
slug and glob for it. Abort with guidance if not found.
Read:
- the design doc — its goals, its Testing table, and any explicit success criteria
- the matching plan at
docs/superpowers/plans/<same-date>-<same-topic>-plan.md, if present — its per-task verification commands are usually the best evidence source - any example manifests the design names
Archived specs under docs/specs/done/ are also accepted, for re-verifying older work. Those use
the retired SC-XXX format; parse **SC-XXX**: <text> lines when you see them.
2. Enumerate success criteria
Superpowers designs state criteria in prose and in a Testing table rather than as numbered
SC-XXX items. Extract one checkable claim per row or per bullet, and give each a stable local
id (C-1, C-2, …) for the report. For each, infer a verification method:
| Criterion pattern | Verification method |
|---|---|
| "pods can call AWS APIs …" | kubectl run a test pod; try the API; check result |
| "reconciliation succeeds within Xs" | flux get + time window check |
| "metrics emit" | VictoriaMetrics query for the metric name |
| "logs appear" | VictoriaLogs query for the log stream |
| "latency p95 < Y" | VictoriaMetrics histogram_quantile(0.95, ...) |
| "eviction deterministic" | deploy, fill, observe eviction counter |
| "resource X created" | kubectl get X -l <label> |
| a literal shell command in the Testing table | run it verbatim; compare to the stated expected output |
If the method is unclear, list the criterion as MANUAL and ask the user how they want to verify.
3. Deploy the example (idempotent)
Prefer kubectl apply -k <dir>/examples/ or kubectl apply -f <dir>/examples/<name>.yaml. If the resource is a Flux HelmRelease / Kustomization, just wait for reconciliation — Flux owns deployment.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 144 lines · 52 tokens per session scan A 40b46b0787e2
verify-spec is a skill published in the GitHub repository Smana/cloud-native-ref (104 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 1,479 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
troubleshoot-sandbox
Troubleshoot OpenSandbox issues by running diagnostics (logs, inspect, events, summary) via CLI or HTTP API to diagnose sandbox failures like OOM, crash, image pull errors, network problems, etc.
network-rca
Kubernetes network root cause analysis skill powered by Kubeshark MCP. Use this skill whenever the user wants to investigate past incidents, perform retrospective traffic analysis, take or manage traffic snapshots, extract PCAPs, dissect L7 API calls from historical captures, compare traffic patterns over time, detect…
mirrord-prev-env
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer…
mirrord-kafka
Helps DevOps engineers configure mirrord Operator's Kafka queue splitting feature end-to-end. Generates the MirrordSplitConfig and MirrordPropertyList Kubernetes CRD YAMLs (the current resources; MirrordKafkaTopicsConsumer + MirrordKafkaClientConfig are deprecated but still supported), the matching mirrord.json…
mirrord-operator
Help users install and configure the mirrord Operator for team/enterprise environments. Use when users ask about operator setup, Helm installation, cloud API key or license configuration, air-gapped/offline licensing, enabling features (queue splitting, DB branching, preview environments, multi-cluster), internal…
mirrord-header-propagation
Makes a codebase propagate W3C baggage (the baggage header carrying mirrord-session= ) end to end, so mirrord HTTP filters, preview environments, and queue splitting can route a whole request chain to one developer's session. Detects existing OpenTelemetry, Datadog, or other tracing that can already propagate baggage…