agentmods.dev

ztx-exp-manager

ztx-exp-manager is a skill for Codex from ztxtech/ztxexp. It costs 42 tokens per session (530 once invoked), scanned A, original, MIT.

An experiment workflow helper for machine-learning and large-language-model tests, using ztxexp to set configurations, run experiments, check outputs, and inspect results.

In plain words
What is it for?
Use it to create parameter variations, execute experiment pipelines, record metrics and output files, combine results, and troubleshoot failed runs.
Why use it?
It keeps experiment runs and their files organized, making it easier to tell whether a run succeeded and diagnose failures.

Skill for Codex

Written for Codex: agents/openai.yaml present.

not rated 4repo 3d ago A scan 42 tokens original MIT

Good fit Use it to create parameter variations, execute experiment pipelines, record metrics and output files, combine results, and troubleshoot failed runs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ztxtech/ztxexp/ztx-exp-manager
View source ↗ ztxtech/ztxexp ztxexp.readthedocs.io
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 ztxtech/ztxexp --skill ztx-exp-manager
Clone the repo
git clone --depth 1 https://github.com/ztxtech/ztxexp

Made for: 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 ztx-exp-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/ztxtech/ztxexp/ztx-exp-manager/github.svg)](https://agentmods.dev/skills/ztxtech/ztxexp/ztx-exp-manager)
Your own site
<a href="https://agentmods.dev/skills/ztxtech/ztxexp/ztx-exp-manager"><img src="https://agentmods.dev/badge/skills/ztxtech/ztxexp/ztx-exp-manager/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 ztx-exp-manager

Your own site · 80×15
<a href="https://agentmods.dev/skills/ztxtech/ztxexp/ztx-exp-manager"><img src="https://agentmods.dev/badge/skills/ztxtech/ztxexp/ztx-exp-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 530 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 $0.00042 $0.00530
Opus 5.5 $0.00017 $0.00212
Sonnet 5.5 $0.00008 $0.00106
Haiku 4.5 $0.00004 $0.00053

Measured 2mo ago against content hash e86f101b1cf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ztx-exp-manager 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/ztx-exp-manager/SKILL.md · 67 lines

What it actually says

ztx-exp-manager Skill（中文）

核心规则

  1. 优先使用 ExperimentPipeline 组织实验，不手写零散调度脚本。
  2. 实验函数契约固定为：exp_fn(ctx: RunContext) -> dict | None。
  3. 成功判定必须使用：run.json.status == "succeeded"。
  4. 产物分工：
    • 最终指标：return dict -> metrics.json
    • 过程指标：ctx.log_metric(...) -> metrics.jsonl
    • 业务文件：写入 artifacts/

常用流程

  1. 先用 grid/variants/random_search 构建配置。
  2. 再执行 pipeline.run(exp_fn, mode=...)。
  3. 用 ResultAnalyzer 聚合、导出和清理。

常用命令

  • pip install -U ztxexp
  • ztxexp init-vibe
  • python -m pytest

排障清单

  1. 先看 run.json.status。
  2. 失败时查看 error.log。
  3. 曲线缺失时检查 ctx.log_metric(...) 是否调用。

ztx-exp-manager Skill (English)

Core Rules

  1. Prefer ExperimentPipeline for workflow orchestration.
  2. Keep experiment contract: exp_fn(ctx: RunContext) -> dict | None.
  3. Determine success strictly by run.json.status == "succeeded".
  4. Artifact responsibilities:
    • Final metrics: return dict -> metrics.json
    • Step metrics: ctx.log_metric(...) -> metrics.jsonl
    • Business outputs: write into artifacts/

Typical Workflow

  1. Build configs via grid/variants/random_search.
  2. Execute with pipeline.run(exp_fn, mode=...).
  3. Aggregate and clean results using ResultAnalyzer.

Common Commands

  • pip install -U ztxexp
  • ztxexp init-vibe
  • python -m pytest

Troubleshooting

  1. Check run.json.status first.
  2. Read error.log on failure.
  3. Verify ctx.log_metric(...) for missing curves.
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 · 67 lines · 42 tokens per session scan A e86f101b1cf9

Subscribe to this mod's changes

ztx-exp-manager is a skill published in the GitHub repository ztxtech/ztxexp (4 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 530 once invoked, about $0.0002 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 2026-08-31.

Data and AIScientific
Related

ztx-exp-manager compared with skills from other repositories

ztx-exp-manager next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ztx-exp-managerztxtech/ztxexpSkill43d agoMITA42Codex
arboretoK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA55Claude Code, Codex
deepspot-mK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA70Claude Code
torchdrugK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA64Claude Code
pyhealthK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA84Claude Code, Codex
nemo-mbridge-perf-expert-parallel-overlapNVIDIA/skillsSkill3.9kyesterdayApache-2.0A56Claude Code
ml-training-recipesOrchestra-Research/AI-Research-SKILLsSkill14k27d agoMITA88Claude Code