agentmods.dev

accutest

accutest is a skill for Claude Code from syy12335/Environment-Runtime. It costs 27 tokens per session (317 once invoked), scanned A, original, MIT.

A workflow-task generator for checking the accuracy, quality, or score of an output. It takes an evaluation goal and returns a task result with a success or failure status.

In plain words
What is it for?
It is for running accuracy tests, reviewing output quality, assigning scores, and checking how well a model or result performs.
Why use it?
It turns a broad request to assess something into a clearly stated evaluation task with defined quality or accuracy concerns.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

not rated 128repo 5mo ago A scan 27 tokens original MIT

Good fit It is for running accuracy tests, reviewing output quality, assigning scores, and checking how well a model or result performs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/syy12335/environment-runtime/accutest
View source ↗ syy12335/Environment-Runtime
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 syy12335/Environment-Runtime --skill accutest
Clone the repo
git clone --depth 1 https://github.com/syy12335/Environment-Runtime

Made for: Claude Code.

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 accutest

README.md
[![agentmods](https://agentmods.dev/badge/skills/syy12335/environment-runtime/accutest/github.svg)](https://agentmods.dev/skills/syy12335/environment-runtime/accutest)
Your own site
<a href="https://agentmods.dev/skills/syy12335/environment-runtime/accutest"><img src="https://agentmods.dev/badge/skills/syy12335/environment-runtime/accutest/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 accutest

Your own site · 80×15
<a href="https://agentmods.dev/skills/syy12335/environment-runtime/accutest"><img src="https://agentmods.dev/badge/skills/syy12335/environment-runtime/accutest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 317 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 $0.00027 $0.00317
Opus 5.5 $0.00011 $0.00127
Sonnet 5.5 $0.00005 $0.00063
Haiku 4.5 $0.00003 $0.00032

Measured 2mo ago against content hash b5d4aa30faeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

accutest 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run.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.

src/task_router_graph/skills/controller/accutest/SKILL.md · 41 lines

What it actually says

Accutest Workflow Type

定位：accutest 用于精度、质量、评分、效果评估。

常见情况

  • 做一次精度测试
  • 评估这版输出质量
  • 给这个结果打分
  • 看一下模型效果

路由边界

  • 若用户要“解释上一轮 accutest 含义”，通常应路由到 executor。
  • 若用户要“执行评估”，应路由到 accutest。

task_content 生成要点

  • 明确评估对象
  • 明确核心评估维度（准确性/质量/评分）
  • 用简洁可执行语言描述本轮评估目标

Workflow I/O

  • 入口：scripts/run.py
  • 调用：run(*, task_content: str) -> dict
  • 返回：{"task_status": "done|failed", "task_result": "..."}
Files

What ships with it

1 file 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. 2mo ago First seen · 41 lines · 27 tokens per session scan A b5d4aa30faeb

Subscribe to this mod's changes

accutest is a skill published in the GitHub repository syy12335/Environment-Runtime (128 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 317 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 2026-08-30.

Testingagent
Related

accutest compared with skills from other repositories

accutest next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
accutestsyy12335/Environment-RuntimeSkill1285mo agoMITA27Claude Code
eval-dataset-designbojieli/ai-agent-bookSkill57k29d agoApache-2.0A138Claude Code, Codex
aatmf-t10-confidentiality-breachPurpleAILAB/DecepticonSkill6.5k8d agoApache-2.0A39Claude Code, Codex
mochi-remindkirodotdev/KiroCrewSkill4.8kyesterdayApache-2.0A20Claude Code, Codex
ensembl-databasesynthetic-sciences/openscienceSkill4.3k2d agoApache-2.0A45Claude Code, Codex
ai-musicZJU-REAL/EaselSkill4.5k4d agoApache-2.0A161Claude Code, Codex
skill-news-intelligenceZJU-REAL/EaselSkill4.5k4d agoApache-2.0A104Claude Code, Codex