Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add pariyar07/kybernetes --skill kybernetes-verify-rungit clone --depth 1 https://github.com/pariyar07/kybernetesWrote 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/pariyar07/kybernetes/kybernetes-verify-run)<a href="https://agentmods.dev/skills/pariyar07/kybernetes/kybernetes-verify-run"><img src="https://agentmods.dev/badge/skills/pariyar07/kybernetes/kybernetes-verify-run/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/pariyar07/kybernetes/kybernetes-verify-run"><img src="https://agentmods.dev/badge/skills/pariyar07/kybernetes/kybernetes-verify-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00033 | $0.00799 |
| Opus 5 | $0.00016 | $0.00400 |
| Sonnet 5 | $0.00007 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
kybernetes:verify-run 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 11d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kybernetes Verify Run
This helper is an independent sensor with rejection authority over a completion claim. It cannot mutate canonical lifecycle state, repair work silently, or convert advisory consensus into proof. The governor admits the evidence and owns completion.
Required Inputs
- Objective and enumerated DONE criteria.
- Canonical revision and artifacts under test.
- Proposed verifier, environment, commands/rubric, and expected outcomes.
- Evidence pointers with provenance and timestamps.
- Producer identity and available checker independence.
- Permission boundary for read-only checks or explicitly authorized probes.
- Accountable owner and acceptance boundary when the tested work affects a dependent system or owner-held external decision.
- Known brownfield constraints, operational evidence, dependent systems, and unobservable gaps when visible code and tests may not cover the real contract.
Verifier Types
deterministic: tests, schemas, static checks, reproducible calculations.external: observed runtime, deployment, API, source, or third-party state.subjective: explicit rubric, evaluator, examples, threshold, and residual judgment.human_acceptance: named decision boundary and exact accepted scope.
Human acceptance may serve as the verifier only when the human is explicitly named for that criterion. A technical or reviewer pass does not issue the acceptance verdict for a dependent system.
Advisory reviews, generated lenses, popularity, and “looks good” are comparator augmentation, not verification.
Maker/Checker Separation
Record the maker/checker relationship. Prefer a separate context, worker,
method, source, or human for consequential work. Producer self-approval is not
sufficient above simple work. When true independence is unavailable, disclose
the limitation and strengthen deterministic or external evidence; otherwise
return inconclusive.
Procedure
- Map each DONE criterion to one or more checks.
- Confirm artifact revision, environment, capability, and evidence freshness.
- Run checks without modifying the artifact under evaluation.
- Record exact outcome, coverage, provenance, gaps, and rerun instructions.
- Reject completion on any failed criterion, stale material evidence, incomplete required coverage, or hidden subjective judgment.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 96 lines · 33 tokens per session scan A 9248340d9a50
kybernetes:verify-run is a skill published in the GitHub repository pariyar07/kybernetes (13 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 799 once invoked, about $0.0002 per session on Opus 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
pptx-html-fidelity-audit
Audit a python-pptx export against its source HTML deck, identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing), and re-export with strict footer-rail + cursor-flow layout discipline. Use this skill whenever the user has a .pptx that was generated from an…
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
nemo-automodel-model-onboarding
Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.
amc-run-sample-calibration
Run end-to-end calibration on the shipped sample dataset (sdg082sampledata010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.
jetson-video-pipeline
Use when executing and verifying Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or acceptance workflows with exact artifact handoffs.
nemo-automodel-recipe-development
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.