ax-comparison

ax-comparison is a skill for Claude Code, Codex from shenli/devtool-ax-kit. It costs 16 tokens per session (163 once invoked), scanned A, original, Apache-2.0.

A method for comparing how coding agents perform the same task through different tool interfaces, such as command-line documentation, a Skill, an MCP server, or a plugin.

In plain words
What is it for?
Use it to run controlled comparisons and record completion, time, retries, repeated side effects, recovery, transcript safety, human attention, and verifier disagreements.
Why use it?
It helps show whether a difference comes from the tool interface or from the task, model, test setup, or outside services. It also prevents broad conclusions from one lucky or failed run.

Skill for Claude CodeCodex

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/shenli/devtool-ax-kit/ax-comparison
Any agent
npx skills add shenli/devtool-ax-kit --skill ax-comparison
Clone the repo
git clone --depth 1 https://github.com/shenli/devtool-ax-kit

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 ax-comparison

README.md
[![agentmods](https://agentmods.dev/badge/skills/shenli/devtool-ax-kit/ax-comparison.svg)](https://agentmods.dev/skills/shenli/devtool-ax-kit/ax-comparison)
Your own site
<a href="https://agentmods.dev/skills/shenli/devtool-ax-kit/ax-comparison"><img src="https://agentmods.dev/badge/skills/shenli/devtool-ax-kit/ax-comparison.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 163 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 $0.00016 $0.00163
Opus 5 $0.00008 $0.00081
Sonnet 5 $0.00003 $0.00033
Haiku 4.5 $0.00002 $0.00016

Measured 3d ago against content hash 6beac822f53b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ax-comparison 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 3d 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/ax-comparison/SKILL.md · 19 lines

What it actually says

Compare one controlled task under clearly named conditions, such as public docs/CLI versus an official Skill, MCP server, or plugin. Hold the fixture, verifier, resource limits, and prompt intent constant. Randomize or repeat runs when practical, and record timing, retries, duplicate effects, recovery, and transcript safety.

Treat differences as agent-usability evidence unless the protocol isolates a vendor defect. Report non-reproductions and alternative explanations. Do not generalize from a single successful run.

Attribute each failure to one layer where possible: task/model, harness/session, tool interface, or external infrastructure. Track human attention and verifier disagreement alongside completion and wall-clock time.

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. 3d ago First seen · 19 lines · 16 tokens per session scan A 6beac822f53b

Subscribe to this mod's changes

ax-comparison is a skill published in the GitHub repository shenli/devtool-ax-kit (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 16 tokens to every session and 163 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

coder-agents-review

Use this skill when a repository already has an open pull request and you need to run the Coder Agents Review loop: request review with /coder-agents-review when needed, wait for feedback from the coder-agents-review GitHub app, fix issues, and repeat until the app comments approved.

coder/coder · 68 tokens

write-docs

Authoring workflow and guardrails for writing, moving, or restructuring Coder documentation under docs/. Points at the canonical content guidelines and prose style guide, then walks research, routing, Diátaxis mode, structure, pedagogy, and validation. Counterpart to the doc-check skill, which reviews changes for…

coder/coder · 68 tokens

dogfood

Run a Coder PR dogfood instance: inspect PR context, check out the right branch or stack, start Coder with scripts/develop.sh using agent-safe dev-instance practices, validate the changed functionality with UI evidence when needed, and report findings.

coder/coder · 53 tokens

refine-plan

Iteratively refine development plans using TDD methodology. Ensures plans are clear, actionable, and include red-green-refactor cycles with proper test coverage.

coder/coder · 34 tokens

pull-requests

Guide for creating, updating, and following up on pull requests in the Coder repository. Use when asked to open a PR, update a PR, rewrite a PR description, or follow up on CI/check failures.

coder/coder · 47 tokens

tinte

Agent-native design system infrastructure. Browse, install, and preview design systems from tinte.dev. Use when user asks about themes, design systems, presets, color palettes, or says "tinte". Works with shadcn/cli v4 presets and registries.

Railly/tinte · 57 tokens