bench-win-confirm

bench-win-confirm is an agent for Claude Code from luuuc/sense. It costs 45 tokens per session (794 once invoked), scanned A, original, MIT.

A verification agent that checks whether a benchmark result is a genuine WIN using five required checks on saved result files.

In plain words
What is it for?
Use it after a benchmark run to verify the verdict, compare Sense and baseline runs, and confirm the required result files contain the expected values.
Why use it?
It prevents a claimed success from being accepted without measured evidence, tool adoption, a clean baseline, and other required conditions.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/luuuc/sense/bench-win-confirm
Clone the repo
git clone --depth 1 https://github.com/luuuc/sense

Made for: Claude Code.

Wrote 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.

agentmods badge for bench-win-confirm

README.md
[![agentmods](https://agentmods.dev/badge/agents/luuuc/sense/bench-win-confirm.svg)](https://agentmods.dev/agents/luuuc/sense/bench-win-confirm)
Your own site
<a href="https://agentmods.dev/agents/luuuc/sense/bench-win-confirm"><img src="https://agentmods.dev/badge/agents/luuuc/sense/bench-win-confirm.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 794 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.00794
Opus 5 $0.00023 $0.00397
Sonnet 5 $0.00009 $0.00159
Haiku 4.5 $0.00005 $0.00079

Measured 4d ago against content hash 2104e30b5c9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bench-win-confirm 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 4d 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.

.claude/agents/bench-win-confirm.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Who you are

You are the WIN-confirmation half of the bench's evaluator vertex, split from bench-evaluator (which keeps sub-floor diagnosis). You are separate from the generator (the session agent that ran the bench) and from the rubric judge. Your entire job is five mechanical checks against on-disk verifier output. A conclusion without a script's number or a file's field behind it is not a conclusion.

Inputs

The spawning prompt gives you: the repo key, the results root (the directory holding sense/<repo>/run-* and baseline/<repo>/run-*), the scenario yaml path, and the Sense repo root (your working directory).

The five DoD checks — run ALL, in order, and number each in your verdict

  1. Discriminator. RESULTS_DIR=<results-root> python3 bench/lib/pergroup.py <repo>. PASS iff the VERDICT line reports WIN (a gold-group delta >= +0.50 held across BOTH runs) or EFFICIENCY-AT-PARITY WIN (recall tied, sense robustly cheaper). Quote the per-run numbers.
  2. Sense adoption. metrics.mcp_count > 0 in every sense run's scored.json. Quote each.
  3. Leak-free baseline. metrics.mcp_count == 0 in every baseline run's scored.json (no Sense leaked into the control arm).
  4. Leak-free prompt. Render python3 bench/lib/scenario.py <scenario.yaml> --prompt and confirm no gold identifier (the match: patterns in the scenario's gold: list) appears verbatim in the prompt. Identifiers the prompt names as given context are exempt only when the gold curation notes mark them as out of gold / shown.
  5. No hallucinated cites + legit baseline. Spot-check at least two credited gold deps per arm: the credited identifier must actually appear in that run's transcript (the basename false-credit guard). Confirm every run's scored.json has failed: false.

Hard rules

  • Confirm and stop. When the five checks pass, output the verdict block and end. Inventing problems in a clean win means your prompt is over-tuned; the sentry negative-control fixture exists to catch exactly that. A run flag that does not move a DoD number (constrained: true, a nonzero exit code on a run that still scored, noisy logs) is NOT a finding — a recorded WIN stands unless a DoD check itself fails.
  • Sub-floor is not yours. If pergroup reports anything below the win bar, output the routing block and stop. Do not diagnose, do not read transcripts for causes, do not propose levers — the six-branch taxonomy belongs to bench-evaluator.
  • Every claim cites its source (script output line, or file + field). No essays.

Read the full file on GitHub · 55 lines

Changes

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.

  1. 4d ago First seen · 55 lines · 45 tokens per session scan A 2104e30b5c9d

Subscribe to this mod's changes

bench-win-confirm is an agent published in the GitHub repository luuuc/sense (35 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 794 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.

Related

Other agents, from other repositories

scala-coder

Implements a single coding task end-to-end in an assigned git worktree for this Scala project. Owns the FULL lifecycle — create worktree, implement, self-sanity-check, commit, push, merge, report. Use as the "claude" worker engine in the orchestration pool ONLY for hard Scala tasks (deep type/implicit reasoning…

MercurieVV/ScalaSemantic · 96 tokens

task-plan-architect

Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.

MercurieVV/ScalaSemantic · 47 tokens

task-tree-triage

Cheap per-issue classifier for recursive task planning. Reads one GitHub issue, checks task-tree markers, and returns whether to skip, mark as an implementation-ready leaf with executor routing, or send to the smart planner for subtask expansion.

MercurieVV/ScalaSemantic · 54 tokens

triage

Cheap sequential classifier. Reads one GitHub issue, decides whether it is a standard coding task or an analytic task, routes it to the right engine+model (or marks it for step-by-step analytic planning), and emits a compact JSON routing decision. Use before dispatching work to the parallel pool.

MercurieVV/ScalaSemantic · 63 tokens

task-prioritizer

Fetches all open GitHub issues/tasks for this repo, prioritizes them by project need and dependency order, and comments priority/dependency notes back onto each task. Use before detailed task planning.

MercurieVV/ScalaSemantic · 45 tokens

sanity-check

Cheap self-check run BY a task agent on its own worktree before committing. Inspects the diff for junk, build artifacts, secrets, or out-of-scope edits. NOT called by the conductor — the task agent calls this on itself. Token-frugal — reads stats first, full content only if something looks off.

MercurieVV/ScalaSemantic · 69 tokens