skill-test

skill-test is a skill for Claude Code, Codex from hxy91819/mason-skills. It costs 24 tokens per session (1,478 once invoked), scanned A, original, MIT.

A workflow for testing a coding-agent skill in an isolated run with a fresh subagent. It compares the result with predefined success criteria and can use blind A/B tests to evaluate behavior.

In plain words
What is it for?
Use it to test a skill against a real task, record its environment and evidence, and distinguish instruction problems from model limitations.
Why use it?
It helps reveal whether a skill works reliably, separately from the main agent's prior context or expectations.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: mentions subagents; mentions Codex; $skill-name invocation.

Good fit Use it to test a skill against a real task, record its environment and evidence, and distinguish instruction problems from model limitations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hxy91819/mason-skills/skill-test
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 hxy91819/mason-skills --skill skill-test
Clone the repo
git clone --depth 1 https://github.com/hxy91819/mason-skills

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 skill-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/hxy91819/mason-skills/skill-test/github.svg)](https://agentmods.dev/skills/hxy91819/mason-skills/skill-test)
Your own site
<a href="https://agentmods.dev/skills/hxy91819/mason-skills/skill-test"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/skill-test/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 skill-test

Your own site · 80×15
<a href="https://agentmods.dev/skills/hxy91819/mason-skills/skill-test"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/skill-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,478 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 $0.00024 $0.01478
Opus 5 $0.00012 $0.00739
Sonnet 5 $0.00005 $0.00296
Haiku 4.5 $0.00002 $0.00148

Measured today against content hash ef97899c59a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

skill-test 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 today.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/test_history.py, tests/test_test_history.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

common-skills/skill-test/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Test

这是流程类 Skill,仅在用户显式调用 $skill-test 时运行。主 Agent 设计测试、保存判定标准并复核证据;新建的原生 subagent 只接收待测 skill 与原始任务并完成任务。

建立测试契约

  1. 完整读取待测 SKILL.md 及完成测试所需的直接引用。
  2. 优先使用用户给出的原始任务;没有时,按待测 skill 的描述构造一个最小、真实、可验证的任务。
  3. 在 subagent 上下文之外记录可观察的成功标准、工作区基线、安全边界和允许的副作用。
  4. 为生成物准备临时目录、隔离夹具、mock 或只读环境。测试任务需要额外授权且无法安全等价时,报告受阻。

待测 skill、原始任务、成功标准、基线和隔离方式均明确后再派生 subagent。

选择 subagent 和模型

使用当前宿主提供的原生 subagent/delegation 工具;不要通过 ACPX 或 shell 启动另一个 coding agent。

按以下顺序选择模型:

  1. 用户指定模型时使用该模型;不可用则报告基础设施失败,不静默替换。
  2. 宿主允许选择模型时,优先选择具备任务所需工具与上下文长度的非 frontier、较低成本模型。只有模型目录或用户明确标注时才写 non-frontier,无法确认时写 unknown
  3. 宿主不允许选择模型时使用其原生默认值或继承值,并在结果中明确说明模型选择未受控。

模型较弱造成的失败是测试信号,不自动改用更强模型覆盖。需要区分 skill 缺陷和模型能力边界时,再用同一任务增加一个更强模型对照组。

保持测试上下文纯净

创建全新 subagent,不继承当前对话。Codex 使用 spawn_agentfork_turns: "none";其他宿主使用等价的 fresh/isolated context 选项。若宿主只能继承当前上下文,可以继续做探索性测试,但必须标为 context_isolated=no,不得声称是盲测。

发送给 subagent 的任务只包含:

Use $<skill-name> at <absolute-skill-path> to complete this user request:

<original-user-request>

若 subagent 可稳定发现该 skill,可省略路径,但仍显式写 $<skill-name>。不得加入成功标准、预期答案、已知缺陷、怀疑原因、拟议修复、实现计划、历史输出或主 Agent 结论。安全隔离放在环境和权限边界中,不写进任务来暗示期望行为。

保存实际发送的完整任务。删除 skill 选择行与原始任务后,不应剩余测试语义;满足此条件才派生 subagent。

执行与取证

一次测试对应一个全新 subagent。A/B 或多模型对照使用彼此独立的 subagent;环境没有共享写入时可并行执行。

subagent 完成后,由主 Agent 检查:

  • 实际模型、上下文隔离方式及其原生运行标识;
  • subagent 是否读取并使用了指定 skill;
  • 工具调用、错误、最终答复和可观察产物;
  • 工作区变化、测试结果、安全边界和完成条件;
  • 是否出现任务之外的上下文泄漏。

subagent 的自我评价不是通过证据。未成功派生、未读取 skill、模型不可用或工具基础设施失败时,结论是 infrastructure-failed,不是 skill 失败。

判定与对照

主 Agent依据预先保存的标准给出 passedpartialfailedinfrastructure-failed,每项判断都对应可复核证据。

验证一次 skill 修订时优先做盲 A/B:

  1. 将修订前后版本放入名称不泄漏版本身份的隔离目录。
  2. 使用相同模型、原始任务、权限和夹具;唯一变量是 skill 内容。
  3. 每组使用全新 subagent,不向任一组提供另一组结果。
  4. 比较可观察行为。结果含糊时增加独立重复,不污染任务提示。

只有差异可归因于 skill 版本时,才声称修订有效。用户要求迭代 skill 时,只修复证据支持的问题;每次修订后用新 subagent 复测,最多两轮,然后报告剩余不确定性。

运行历史

使用 scripts/test_history.py 保存最小事实。默认历史位于 ${XDG_CACHE_HOME:-~/.cache}/skill-test/history.json,只包含 engine、model、model class、耗时、outcome、上下文隔离状态、稳定 test ID 和主 Agent disposition;不保存任务、回复、diff、日志、路径或密钥。

Read the full file on GitHub · 103 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today Changed · +2 lines ef97899c59a7
  2. 8d ago First seen · 101 lines · 24 tokens per session scan A da8590c6ddac

Subscribe to this mod's changes

skill-test is a skill published in the GitHub repository hxy91819/mason-skills (2 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,478 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 2026-09-04.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens