Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fmflurry/settings-opencodenpx agentmods add commands/fmflurry/settings-opencode/arena-new-promptWrote 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/fmflurry/settings-opencode/arena-new-prompt)<a href="https://agentmods.dev/commands/fmflurry/settings-opencode/arena-new-prompt"><img src="https://agentmods.dev/badge/commands/fmflurry/settings-opencode/arena-new-prompt/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/fmflurry/settings-opencode/arena-new-prompt"><img src="https://agentmods.dev/badge/commands/fmflurry/settings-opencode/arena-new-prompt.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 | $0.00017 | $0.02080 |
| Opus 5.5 | $0.00007 | $0.00832 |
| Sonnet 5.5 | $0.00003 | $0.00416 |
| Haiku 4.5 | $0.00002 | $0.00208 |
Grade A, and why
arena-new-prompt 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 26d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arena New Prompt
CC: Scaffold a new bench-able prompt following the real PromptAdapter<TInput,TOutput,TGroundTruth> contract and verified file layout. Read the task below carefully to understand the structure before generating code.
Generate a new prompt adapter for the LLM arena: $ARGUMENTS
Your Task
Scaffold a complete, working prompt adapter following the proven classify / draft pattern. Your job is to generate code (the coder role), then emit a wiring checklist for manual completion by the user.
1. Parse Arguments
From $ARGUMENTS, extract:
promptId: The new prompt's ID (e.g.,sentiment,summarize). Used as a stable machine-readable identifier in types, filenames, and exports.
2. Generate Code Artifacts
Create the following files (structure mirrors bench/cases-classify/ and bench/prompts/classify.adapter.ts):
A. Adapter Implementation: ai-sdk/bench/prompts/<promptId>.adapter.ts
A concrete implementation of PromptAdapter<TInput, TOutput, TGroundTruth> (see bench/prompts/prompt-adapter.ts for the contract). Must include:
id: PromptIdfield set to the new promptIdrunInstrumented(input: TInput, options?: AdapterRunOptions)— calls the production instrumented agent function for this promptloadCases()— returns the labeled bench cases arrayscorers(output: TOutput, groundTruth: TGroundTruth, meta)— returnsCriterionResult[]from deterministic scoring
Reference: bench/prompts/classify.adapter.ts (lines 1–49) — mirrors this exactly, swapping classifyThreadInstrumented for your prompt's production instrumented function and CLASSIFY_FALLBACK_CASES for your cases export.
B. Adapter Tests: ai-sdk/bench/prompts/<promptId>.adapter.test.ts
Unit tests verifying the adapter loads cases, calls the instrumented function, and applies scorers correctly. Use node:test's mock.module() to stub the production function without network calls.
Reference: bench/prompts/classify.adapter.test.ts (full file) — copy the mocking pattern and structure, replace classifyAdapter/Classification with your adapter/output type.
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.
- 26d ago First seen · 172 lines · 17 tokens per session scan A 414bc9c2ff57
arena-new-prompt is a command published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 2,080 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 2026-09-20.
Other commands, from other repositories
verify-math
Verify a self-authored mathematical result end to end by routing claims across adversarial review, numerical falsification, symbolic or CAS checks, and Lean, then aggregating one report. Use when a theorem, proposition, conjecture, or paper-wide mathematical argument needs the appropriate combination of verification…
diff
Quantitative volume comparison between a CadQuery model and a reference STEP file.
simulation-calibrator
Test and refine simulation accuracy with validation loops, bias detection, and continuous improvement frameworks.
arg-diagram
ARG academic-paper diagram mode — standalone structural & conceptual diagram generation.
plot
Publication Polish. Runs after results-analysis (Phase 7). Audits all tables and figures produced in Phases 4–7, upgrades them to top-journal standards by calling the table and figure skills.
graphite-morphology-classify
Classify graphite in a cast-iron micrograph per ASTM A247 / ISO 945-1, quantify nodularity, and read the matrix — the single most diagnostic observation in a cast-iron case.