experiment-execution

experiment-execution is a skill for Claude Code, Codex from TenureAI/PhD-Zero. It costs 101 tokens per session (1,830 once invoked), scanned A, original, MIT.

A procedure for starting and managing machine-learning experiments, such as training runs, evaluations, or benchmarks, on a local or remote computer. It defines the information, logging locations, runtime modes, and checks needed for a run.

In plain words
What is it for?
Use it to prepare, start, monitor, resume, or rerun local and remote experiments while recording their settings and outputs.
Why use it?
It makes experiments safer to launch, easier to repeat, and easier to trace when they fail or need recovery.

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/tenureai/phd-zero/experiment-execution
Any agent
npx skills add TenureAI/PhD-Zero --skill experiment-execution
Clone the repo
git clone --depth 1 https://github.com/TenureAI/PhD-Zero

Made for: Claude Code, Codex.

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,830 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 $0.00101 $0.01830
Opus 5 $0.00051 $0.00915
Sonnet 5 $0.00020 $0.00366
Haiku 4.5 $0.00010 $0.00183

Measured 3d ago against content hash f569aaa4e851, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

experiment-execution 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.

.agents/skills/experiment-execution/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Experiment Execution

Mission

Run experiments safely, reproducibly, and mode-aware, with clear run paths and traceable evidence.

References

Read when needed:

  1. references/experiment-launch-checklist.md
  2. references/remote-info-template.md

Required Inputs

Collect minimum safe inputs:

  1. execution target (local|remote)
  2. local project root
  3. runtime project root (required when remote)
  4. single-node or multi-node
  5. proxy requirement
  6. tracker/login requirement

Ask only missing questions.

Run Path Policy

Use shared run_id from run-governor:

  1. control logs and stage reports: <codex-cwd>/logs/runs/<run_id>/
  2. experiment outputs: <runtime_project_root>/runs/<run_id>/
  3. project-context snapshots and secrets: <local_project_root>/.project_local/<project_slug>/

In local execution, runtime_project_root can be equal to local_project_root.

Mode-Aware Interaction

  1. full-auto: proceed without confirmation unless hard blocker or major safety risk.
  2. moderate: confirm before high-resource actions.
  3. detailed: confirm for unclear plans and high-resource actions.

Smoke Validation Policy

Use smoke validation only when needed:

  1. when launch details are incomplete
  2. when environment readiness is uncertain
  3. when cost/risk of full run is high

If setup is clear and safe, direct execution is allowed.

Execution Policy

  1. Confirm real execution vs dry-run.
  2. Confirm required inputs.
  3. Inspect scripts/configs/logs as needed.
  4. Resolve only blocking gaps.
  5. Launch smallest valid step first when uncertainty is high.
  6. Record commands, node assignments, log paths, run IDs.
  7. If the launched action is long-running, immediately enter watch mode instead of treating launch as completion.
  8. After each poll, continue with monitoring, diagnosis, recovery, or result collection; do not default to "job started, come back later."
  9. Replan on major failures.

Watch Mode Policy

Long-running experiment execution is an active responsibility, not a fire-and-forget step.

Read the full file on GitHub · 224 lines

Files

What ships with it

3 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. 3d ago First seen · 224 lines · 101 tokens per session scan A f569aaa4e851

Subscribe to this mod's changes

experiment-execution is a skill published in the GitHub repository TenureAI/PhD-Zero (52 stars, last pushed 5mo ago), licensed MIT. It adds 101 tokens to every session and 1,830 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

experiment-pipeline

Guides structured 4-stage experiment execution with attempt budgets and gate conditions: Stage 1 initial implementation (reproduce baseline), Stage 2 hyperparameter tuning, Stage 3 proposed method validation, Stage 4 ablation study. Integrates with evo-memory (load prior strategies, trigger IVE/ESE) and…

AI4Scientist/nano-scientist · 129 tokens

aris-run-experiment

Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.

OpenLAIR/dr-claw · 48 tokens

auto-paper-improvement-loop

Autonomously improve a generated paper via GPT-5.4 xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.

AI4Scientist/nano-scientist · 67 tokens

paper-illustration

Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.

AI4Scientist/nano-scientist · 67 tokens

paper-navigator

Find and read academic papers: disambiguate queries, discover papers (search, citation traversal, recommendations, arXiv monitoring, trending, GitHub search), evaluate (TLDR, citations, code, SOTA), and read with structured analysis (3-level strategy). Use when: finding papers, reading a paper, related work, citation…

AI4Scientist/nano-scientist · 141 tokens

paper-write

Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.

AI4Scientist/nano-scientist · 50 tokens