agent-compare

agent-compare is a skill for Claude Code, Codex from leviuszen/meaning-assurance. It costs 18 tokens per session (149 once invoked), scanned A, original, Apache-2.0.

A decision-making guide for comparing results from two or more outside coding agents when their answers differ.

In plain words
What is it for?
Sort accepted and rejected parts of each result, identify pieces that can be combined, record the final decision, and list tests and remaining risks.
Why use it?
It helps choose what to trust using the original request, project limits, tests, code changes, and file evidence instead of confidence alone.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Sort accepted and rejected parts of each result, identify pieces that can be combined, record the final decision, and list tests and remaining risks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/leviuszen/meaning-assurance/agent-compare
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.

Any agent
npx skills add leviuszen/meaning-assurance --skill agent-compare
Clone the repo
git clone --depth 1 https://github.com/leviuszen/meaning-assurance

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 agent-compare

README.md
[![agentmods](https://agentmods.dev/badge/skills/leviuszen/meaning-assurance/agent-compare/github.svg)](https://agentmods.dev/skills/leviuszen/meaning-assurance/agent-compare)
Your own site
<a href="https://agentmods.dev/skills/leviuszen/meaning-assurance/agent-compare"><img src="https://agentmods.dev/badge/skills/leviuszen/meaning-assurance/agent-compare/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.

agentmods 80×15 button for agent-compare

Your own site · 80×15
<a href="https://agentmods.dev/skills/leviuszen/meaning-assurance/agent-compare"><img src="https://agentmods.dev/badge/skills/leviuszen/meaning-assurance/agent-compare.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 149 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00018 $0.00149
Opus 5 $0.00009 $0.00075
Sonnet 5 $0.00004 $0.00030
Haiku 4.5 $0.00002 $0.00015

Measured 9d ago against content hash 70267d7ed9ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-compare 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 9d 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/agent-compare/SKILL.md · 28 lines

What it actually says

Agent Compare

Use this skill when two or more agent outputs disagree or when Codex needs to decide which result to trust.

Rules

  • Compare against the user's original request and local project constraints.
  • Prefer tests, diffs, and file evidence over confident prose.
  • Identify partial reuse opportunities instead of picking only one winner.
  • Write the final decision to codex-final.md when working inside a task folder.

Decision Format

Use this structure:

  • Decision
  • Why
  • Accepted parts
  • Rejected parts
  • Files or patches to apply
  • Tests to run
  • Remaining risks
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. 9d ago First seen · 28 lines · 18 tokens per session scan A 70267d7ed9ab

Subscribe to this mod's changes

agent-compare is a skill published in the GitHub repository leviuszen/meaning-assurance (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 149 once invoked, about $0.0001 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

hatch-pet

Create, repair, validate, preview, and package Codex-compatible animated pet spritesheets from character art, screenshots, generated images, or visual references. Use when a user wants to hatch a Codex pet, create a custom animated pet, or build a built-in pet asset with an 8x9 atlas, transparent unused cells…

nexu-io/open-design · 114 tokens

clinical-case-report

Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…

nexu-io/open-design · 73 tokens

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

github-dashboard

GitHub repository analytics dashboard — stars, forks, contributors, issues, pull requests, recent activity, and top contributors. Use when the brief asks for a GitHub repo dashboard, open-source growth report, repository health page, or GitHub analytics view.

nexu-io/open-design · 55 tokens

dcf-valuation

Discounted cash flow valuation and intrinsic value analysis for public companies. Use when the brief asks for DCF, fair value, intrinsic value, price target, undervalued or overvalued analysis, or "what is this company worth?".

nexu-io/open-design · 55 tokens

last30days

Recent community and social trend research over the last 30 days. Use when the brief asks what people are saying now, recent sentiment, community reactions, social proof, launch reaction, trend scan, or last-30-days context.

nexu-io/open-design · 53 tokens