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 GongShichen/LuminaCode --skill benchmark-runner-plangit clone --depth 1 https://github.com/GongShichen/LuminaCodeWrote 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/gongshichen/luminacode/benchmark-runner-plan)<a href="https://agentmods.dev/skills/gongshichen/luminacode/benchmark-runner-plan"><img src="https://agentmods.dev/badge/skills/gongshichen/luminacode/benchmark-runner-plan/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/gongshichen/luminacode/benchmark-runner-plan"><img src="https://agentmods.dev/badge/skills/gongshichen/luminacode/benchmark-runner-plan.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 | $0.00019 | $0.00192 |
| Opus 5.5 | $0.00008 | $0.00077 |
| Sonnet 5.5 | $0.00004 | $0.00038 |
| Haiku 4.5 | $0.00002 | $0.00019 |
Grade A, and why
Benchmark Runner Plan 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 2mo 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.
What it actually says
Specify:
- Benchmark purpose: model quality, agent harness, product performance, reliability, cost, latency, or regression detection.
- Upstream or official harness boundaries, including what must not be modified.
- Required datasets, containers, services, credentials, hardware, network access, seeds, and versions.
- Working directories, mounted resources, generated output paths, report formats, and artifact retention.
- Debug versus official run markers, limits, sampling, and how those affect score interpretation.
- Metrics to capture, including pass/fail, latency percentiles, resource use, cost, logs, and failure categories when relevant.
- Cleanup, reproducibility, and resume behavior.
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.
- 2mo ago First seen · 18 lines · 19 tokens per session scan A 1be4a8072577
Benchmark Runner Plan is a skill published in the GitHub repository GongShichen/LuminaCode (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 19 tokens to every session and 192 once invoked, about $0.0001 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.