agentmods.dev

compare

compare is a command for Claude Code from JuanMarchetto/agent-skills. It costs 22 tokens per session (594 once invoked), scanned A, original, MIT.

A command for comparing two recorded runs side by side using run numbers or labels such as latest and best.

In plain words
What is it for?
It is for evaluating changes between runs and determining which run performed better.
Why use it?
It makes differences in duration, results, errors, and other measurements easier to identify.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the post-run-analysis plugin — 1 skill, 3 commands shipped together

not rated 5repo 7mo ago A scan 22 tokens original MIT

Good fit It is for evaluating changes between runs and determining which run performed better.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/juanmarchetto/agent-skills/compare
View source ↗ JuanMarchetto/agent-skills
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.

Clone the repo
git clone --depth 1 https://github.com/JuanMarchetto/agent-skills

Made for: Claude Code.

Or install post-run-analysis, the plugin that ships this one along with the rest of its 1 skill, 3 commands.

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 compare

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/compare"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/compare.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 594 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 $0.00022 $0.00594
Opus 5.5 $0.00009 $0.00238
Sonnet 5.5 $0.00004 $0.00119
Haiku 4.5 $0.00002 $0.00059

Measured 2mo ago against content hash 44fd3ebac04c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo 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/post-run-analysis/commands/compare.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/compare -- Side-by-Side Run Comparison

You are the Post-Run Analysis skill's comparison engine. The user has triggered /compare to compare two specific runs.

Instructions

  1. Parse the arguments. Expect two run identifiers:

    • Run numbers: /compare 3 7
    • Run numbers with target: /compare test-suite#3 test-suite#7
    • "last" keyword: /compare last last-1 (most recent and second most recent)
    • "best" keyword: /compare best last (best historical run vs most recent)

  2. If arguments are missing or invalid, show usage:

    Usage: /compare <run1> <run2>

Examples:
  /compare 3 7            -- Compare run #3 with run #7
  /compare last last-1    -- Compare the two most recent runs
  /compare best last      -- Compare the best run with the latest
  /compare best worst     -- Compare the best and worst runs

  3. Load both runs from the run history. If either run is not found, report which one is missing.

  4. Present the side-by-side comparison:

    ## Comparison: Run #X vs Run #Y

| Dimension | Run #X ([date]) | Run #Y ([date]) | Winner |
|-----------|----------------|----------------|--------|
| Duration  | ...            | ...            | ...    |
| Pass/Fail | ...            | ...            | ...    |
| Key Metric| ...            | ...            | ...    |
| Errors    | ...            | ...            | ...    |

### What Changed Between Runs
- [List of differences: config changes, code changes, environment changes if known]

### Error Diff
| Error Type | Run #X | Run #Y | Change |
|------------|--------|--------|--------|
| ...        | ...    | ...    | +N/-N  |

### Verdict
[Which run was better and why. What drove the improvement or regression.]

  5. If detailed logs exist for both runs, dig deeper:

    • Which specific errors were fixed between runs?
    • Which new errors appeared?
    • Were any "fixed" errors actually regressions from earlier runs?

Read the full file on GitHub · 65 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. 2mo ago First seen · 65 lines · 22 tokens per session scan A 44fd3ebac04c

Subscribe to this mod's changes

compare is a command published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 22 tokens to every session and 594 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 2026-09-03.

Analytics and metricsClaude CodeEvaluationai-agentsai-toolsautomationbrowser-automation
Related

compare compared with commands from other repositories

compare next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
compareJuanMarchetto/agent-skillsCommand57mo agoMITA22Claude Code
phase-reviewolo-dot-io/Uni-CLICommand2282d agoApache-2.0A0Claude Code
unicli-searcholo-dot-io/Uni-CLICommand2282d agoApache-2.0A0Claude Code
qaDevZonayed/MochiCommand38d agoMITA49Claude Code
checkpointDevZonayed/MochiCommand38d agoMITA17Claude Code
dreamDevZonayed/MochiCommand38d agoMITA25Claude Code
design-qaDevZonayed/MochiCommand38d agoMITA52Claude Code