bench

bench is a skill for Claude Code, Codex from zapgun-ai/clawback. It costs 94 tokens per session (886 once invoked), scanned A, original, no licence file.

A tool that analyses NDJSON turn logs, where each line is a JSON record, to compare treatment and passthrough test groups.

In plain words
What is it for?
It is for creating Markdown, CSV, JSON summary, and manifest reports from clawback logs, including a bootstrap 95% confidence interval and supporting cost details.
Why use it?
It produces a structured comparison of reclaimed billable input tokens and includes statistical uncertainty, making log results easier to inspect.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

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 skills/zapgun-ai/clawback/bench
Any agent
npx skills add zapgun-ai/clawback --skill bench
Clone the repo
git clone --depth 1 https://github.com/zapgun-ai/clawback

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/zapgun-ai/clawback/bench.svg)](https://agentmods.dev/skills/zapgun-ai/clawback/bench)
Your own site
<a href="https://agentmods.dev/skills/zapgun-ai/clawback/bench"><img src="https://agentmods.dev/badge/skills/zapgun-ai/clawback/bench.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 886 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 $0.00094 $0.00886
Opus 5 $0.00047 $0.00443
Sonnet 5 $0.00019 $0.00177
Haiku 4.5 $0.00009 $0.00089

Measured 6d ago against content hash 329a4e88e2dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

bench 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.

.skills/bench/SKILL.md · 79 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

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 · 79 lines · 94 tokens per session scan A 329a4e88e2dd

Subscribe to this mod's changes

bench is a skill published in the GitHub repository zapgun-ai/clawback (5 stars, last pushed 2mo ago), with no licence file. It adds 94 tokens to every session and 886 once invoked, about $0.0005 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 skills, from other repositories

remove-ai-marks

Strip multi-vendor AI provenance from owned files: hidden Unicode (Layer A), statistical sampling watermarks via rewrite (Layer B — always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Covers Claude, Gemini/SynthID-class, OpenAI provenance surfaces, and open-LLM sampling…

ShadowAqueduct/watermark-remover · 135 tokens

clean-user-facing-text

Audit and finalize authorized natural-language text meant for readers: strip suspicious invisible Unicode, then rewrite prose while keeping facts, meaning, and the writer's voice. Use when the user asks to clean, humanize, polish, or finalize articles, manuscripts, reports, documentation, emails, product copy, UI…

ShadowAqueduct/watermark-remover · 121 tokens

repo-visuals

Create hero visuals — animated GIF, static PNG, or animated SVG — for GitHub repositories. Runs a structured discovery conversation (scan repo → recommend format → propose creative scenarios → agree on a brief), then designs bespoke HTML/SVG, previews it in the browser, and exports. Use when the user asks for a README…

livlign/claude-skills · 112 tokens

repo-visuals-retro

Retrospective meta-skill for the repo-visuals skill. Reads accumulated evaluation logs from past runs, spots patterns (recurring low-score criteria, repeated iteration failures, unsatisfied requests), consults other expert skills (skill-creator, frontend-design, etc.) where relevant, and proposes concrete edits to…

livlign/claude-skills · 95 tokens

hyper-plan

Use when about to start a non-trivial implementation that needs decomposition before coding. Also when the user invokes /hyperclaude:hyper-plan. Produces an ordered, bite-sized plan in .hyperclaude/plans/ — the input for /hyperclaude:hyper-plan-review and /hyperclaude:hyper-implement.

zeikar/hyperclaude · 70 tokens

hyper-interview

Use when starting from a vague or under-specified idea and want requirements clarified before planning — "interview me", "ask me what you need", "clarify requirements first", "I'm not sure exactly what I want", "make sure you understand before building". Also when the user invokes /hyperclaude:hyper-interview. Runs a…

zeikar/hyperclaude · 138 tokens