bench-reporter

bench-reporter is an agent for Claude Code from zivtech/accessibility-skills. It costs 40 tokens per session (667 once invoked), scanned A, original, GPL-3.0.

A documentation agent that records benchmark results in project documents. Benchmarks are repeatable tests used to measure a system's performance.

In plain words
What is it for?
Use it to update BENCHMARK.md, README.md, and EVAL-GAPS-PLAN.md after benchmark runs and produce summary tables with analysis.
Why use it?
It keeps benchmark findings, gaps, tables, and interpretation in the project's main documentation instead of leaving results scattered across runs or notes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/zivtech/accessibility-skills/bench-reporter
Clone the repo
git clone --depth 1 https://github.com/zivtech/accessibility-skills

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-reporter

README.md
[![agentmods](https://agentmods.dev/badge/agents/zivtech/accessibility-skills/bench-reporter.svg)](https://agentmods.dev/agents/zivtech/accessibility-skills/bench-reporter)
Your own site
<a href="https://agentmods.dev/agents/zivtech/accessibility-skills/bench-reporter"><img src="https://agentmods.dev/badge/agents/zivtech/accessibility-skills/bench-reporter.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 667 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 5.1 $0.00040 $0.00667
Opus 5 $0.00020 $0.00333
Sonnet 5 $0.00008 $0.00133
Haiku 4.5 $0.00004 $0.00067

Measured 6d ago against content hash 4a4873a666b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

bench-reporter 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 6d 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-reporter.md · 59 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 6d ago First seen · 59 lines · 40 tokens per session scan A 4a4873a666b8

Subscribe to this mod's changes

bench-reporter is an agent published in the GitHub repository zivtech/accessibility-skills (6 stars, last pushed yesterday), licensed GPL-3.0. It adds 40 tokens to every session and 667 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 2026-08-31.

Related

Other agents, from other repositories

web-accessibility-wizard

Interactive web accessibility review wizard. Runs a guided, step-by-step WCAG audit of your web application. Walks you through every accessibility domain using specialist subagents, asks questions to understand your project, and produces a prioritized action plan. Includes severity scoring, framework-specific…

Community-Access/accessibility-agents · 91 tokens

document-accessibility-wizard

Interactive document accessibility audit wizard. Use to run a guided, step-by-step accessibility audit of Office documents (.docx, .xlsx, .pptx) and PDFs. Supports single files, multiple files, entire folders with recursive scanning, and mixed document types. Orchestrates specialist sub-agents (word-accessibility…

Community-Access/accessibility-agents · 89 tokens

Issue Tracker

Your GitHub issue command center -- find, triage, review, and respond to issues with full markdown + HTML reports saved to your workspace. Includes reactions, release context, and discussion awareness.

Community-Access/accessibility-agents · 42 tokens

Alt Text & Headings

Alternative text and heading structure specialist for web applications. Use when building or reviewing any page with images, icons, SVGs, videos, figures, charts, or heading hierarchies. Covers meaningful vs decorative images, complex image descriptions, heading levels, document outline, and landmark structure. Can…

Community-Access/accessibility-agents · 96 tokens

Forms Specialist

Form accessibility specialist for web applications. Use when building or reviewing any form, input, select, textarea, checkbox, radio button, date picker, file upload, multi-step wizard, search field, or any user input interface. Covers labeling, error handling, validation, grouping, autocomplete, and assistive…

Community-Access/accessibility-agents · 79 tokens

Accessibility Tool Builder

Expert in building accessibility scanning tools, rule engines, document parsers, report generators, and audit automation. Designs WCAG criterion mapping, severity scoring algorithms, CLI/GUI scanner architecture, and CI/CD integration for accessibility tooling.

Community-Access/accessibility-agents · 49 tokens