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 levnikolaevich/claude-code-skills --skill ln-45-benchmark-comparatorgit clone --depth 1 https://github.com/levnikolaevich/claude-code-skillsWrote 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/levnikolaevich/claude-code-skills/ln-45-benchmark-comparator)<a href="https://agentmods.dev/skills/levnikolaevich/claude-code-skills/ln-45-benchmark-comparator"><img src="https://agentmods.dev/badge/skills/levnikolaevich/claude-code-skills/ln-45-benchmark-comparator/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/levnikolaevich/claude-code-skills/ln-45-benchmark-comparator"><img src="https://agentmods.dev/badge/skills/levnikolaevich/claude-code-skills/ln-45-benchmark-comparator.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 | $0.00021 | $0.02713 |
| Opus 5.5 | $0.00008 | $0.01085 |
| Sonnet 5.5 | $0.00004 | $0.00543 |
| Haiku 4.5 | $0.00002 | $0.00271 |
Grade A, and why
ln-45-benchmark-comparator 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 7d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Benchmark Comparator
Goal: Compare alternatives under controlled, reproducible conditions. Correctness comes before speed, and measured data must remain separate from estimates, setup cost, and interpretation.
Execution contract: The checklist defines completion. Track each item internally as PENDING, PROVEN with evidence, CLEARED with evidence its condition is absent, or UNPROVEN with a gap; reading, delegation, tool failure, a zero exit status, or a self-reported success is not proof; only the observed outcome is. Reconcile after each section. Before returning, resolve all PENDING, count only PROVEN and CLEARED, and apply verdict and approval rules to every gap.
Preserve intent, scope, and existing authorization. Continue authorized work; ask only for consequential unresolved choices or required external approval. When no one can answer during the run, state the exact question and apply the skill's verdict for the remaining gap instead of waiting or guessing. Scale depth to material risk without skipping checks. Preserve dependency and safety order; otherwise choose an appropriate verification method.
Accept equivalent user or repository evidence; no other skill, named artifact, or complete lifecycle is required. Preserve source requirement and decision IDs. Bind reused evidence to relevant source versions, dirty changes, configuration, and environment; invalidate only affected claims.
On continuation, reconcile task, authorization, current state, and unresolved evidence. For long work, return a compact continuation record or update an already authorized artifact; read-only skills do not persist it. Distinguish artifact readiness, verified behavior, and external-action authority.
Prepare authorized work before required approval. If blocked by an instruction, cite its exact source and unresolved boundary; do not invent approval gates from caution.
Tool Routing
| Need | Preferred tool | Use it when | Fallback |
|---|---|---|---|
| Canonical workload and oracle | Repository fixtures, tests, expected diffs, schemas, or independently specified outcomes | Defining what success means before either candidate runs | Create the smallest deterministic fixture that represents the decision |
| Isolation | Clean Git worktrees, temporary directories, controlled environment, fixed seeds, and resettable caches | Preventing one candidate or run from contaminating another | Sequential clean-room setup with verified cleanup |
| Execution | The same shell runner and wrapper for every candidate | Capturing commands, exit status, stdout, stderr, timing, and artifacts consistently | Manual execution with an explicit reproducibility limitation |
| Activation proof | Logs, traces, command records, process metadata, or candidate-specific artifacts | Verifying the intended alternative actually ran and did not fall back | Treat the run as invalid when activation cannot be proven |
| Correctness grading | Tests, output parser, diff, schema validation, or independent oracle | Every scenario before cost comparison | Manual blind grading against written expectations |
| Performance and cost | Monotonic timer, resource metrics, token or usage telemetry, tool-call logs, and failure counts | Metrics are observable through the same method for all candidates | Label derived or estimated values and keep them out of measured aggregates |
| External semantics | Official documentation and specifications | Candidate configuration or claimed behavior needs current verification | Primary-source web research; otherwise mark the claim UNVERIFIED |
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.
- 7d ago Changed a88f4b740075
- 23d ago Changed · -1 lines 3000cab4666f
- 27d ago First seen · 121 lines · 21 tokens per session scan A a9ef28a307b1
ln-45-benchmark-comparator is a skill published in the GitHub repository levnikolaevich/claude-code-skills (573 stars, last pushed 4d ago), licensed MIT. It adds 21 tokens to every session and 2,713 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 2026-09-13.
Other skills, from other repositories
triage-report
Drain the .review/ report queue. Resolves un-triaged scan/audit reports (producer-agnostic — check-docs-consistency and any other scanner), dispatches the triage-report subagent (Sonnet) one report at a time for per-finding dispositions (promote / patch / dup / needs-investigation / dismiss), then the gateway absorbs…
dev-rc
The last gate before merge — QA, security audit, review and changelog, with objective pass conditions.
blast-radius
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', reviewing a small diff you don't trust, or a brief that asserts something about existing code…
no-comments
Spawn the comment-sicko subagent, fix accepted findings, and offer encodings for claimed constraints.
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.
huggingface-paper-publisher
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.