Borrowing it
Nothing to install: this file belongs to fwornle/coding. 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/fwornle/coding/main/.claude/commands/kgbench.mdgit clone --depth 1 https://github.com/fwornle/codingWrote 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/commands/fwornle/coding/kgbench)<a href="https://agentmods.dev/commands/fwornle/coding/kgbench"><img src="https://agentmods.dev/badge/commands/fwornle/coding/kgbench/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/commands/fwornle/coding/kgbench"><img src="https://agentmods.dev/badge/commands/fwornle/coding/kgbench.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 | $0.00060 | $0.04573 |
| Opus 5.5 | $0.00024 | $0.01829 |
| Sonnet 5.5 | $0.00012 | $0.00915 |
| Haiku 4.5 | $0.00006 | $0.00457 |
Grade A, and why
kgbench scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s localhost:3032/api/kgbench/active-run # {"runId":null} when the coast is clear How it starts
The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kgbench (/kgbench) — run, resume, grade and diagnose the retrieval benchmark
Operator front-end for the coding-v1 code-retrieval benchmark: which retrieval strategy
answers questions about this repository best, at what token and latency cost.
This skill is a THIN WRAPPER. It shells to existing CLIs and reimplements no runner, grader, judge or report logic:
| Script | Role |
|---|---|
scripts/kgbench-supervise.sh |
detached, self-resuming matrix supervisor |
scripts/kgbench-run.mjs |
the matrix itself (--set --arms --only --reps --run-id) |
scripts/kgbench-regrade.mjs |
re-apply graders offline; --rejudge re-runs the judge |
scripts/kgbench-report.mjs |
render RESULTS.md + report.json (refuses to clobber hand-written files) |
scripts/kgbench-charts.mjs |
render the SVG figures |
scripts/kgbench-verify-questions.mjs |
validate questions and every evidence file:line |
scripts/kgbench-backfill-tokens.mjs |
re-resolve token fields offline; refuses a window narrower than the cell |
scripts/kgbench-repair-attempt-windows.mjs |
transitional: reconstruct per-attempt windows on runs recorded before the runner wrote them |
Read docs/benchmarks/measurement-lessons.md before changing a question, a matcher or an answer key. It records defects that cost a full investigation each, and one blind spot that makes the obvious diagnosis wrong.
Two front-ends, one benchmark
There is also a Performance → Benchmarks sub-tab at
localhost:3032/performance. It is a second front-end
over the same scripts, not a second implementation: its launcher shells to
kgbench-supervise.sh on the host, and its results view renders what
lib/kgbench/report.mjs produces — the function kgbench-report.mjs calls. A number shown
there and a number in the published report can differ only because the data changed.
CLI (/kgbench) |
Dashboard | |
|---|---|---|
| run / resume | ✅ | ✅ (Launch, and a resume offer when the id has cells) |
| watch a run | status |
✅ live monitor + supervisor log tail |
| cancel a run | Ctrl-C, or kill the group | ✅ Cancel |
| results | report → RESULTS.md |
✅ live aggregate, and the published artefacts |
| regrade / rejudge | ✅ | ❌ — CLI only, deliberately (Step 4) |
| publish | ✅ | ❌ — CLI only (Step 3) |
| doctor | ✅ | partial: a model probe, not the judge probe (Step 5) |
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 · 323 lines · 60 tokens per session scan A 87a00b3df7cd
kgbench is a command published in the GitHub repository fwornle/coding (2 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 4,573 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.
laravel-ai-sdk
Build AI features with the first-party Laravel AI SDK (Laravel 13+); use the laravel:ai-sdk skill exactly as written.
vlm-ocr-evaluation
Run the vlm-ocr skill in its evaluate phase: compare candidate OCR systems against a stratified human-transcribed ground-truth sample and pick a model on measured CER/WER before committing to a bulk run.
dare-llm-integration
Integração segura e eficiente com LLMs (Gemini, Claude, OpenAI, Ollama) em projetos DARE.