Borrowing it
Nothing to install: this file belongs to TenureAI/PhD-Zero. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TenureAI/PhD-Zero/main/.agents/skills/experiment-execution/SKILL.mdgit clone --depth 1 https://github.com/TenureAI/PhD-ZeroWrote 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.
[](https://agentmods.dev/skills/tenureai/phd-zero/experiment-execution)<a href="https://agentmods.dev/skills/tenureai/phd-zero/experiment-execution"><img src="https://agentmods.dev/badge/skills/tenureai/phd-zero/experiment-execution/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.
<a href="https://agentmods.dev/skills/tenureai/phd-zero/experiment-execution"><img src="https://agentmods.dev/badge/skills/tenureai/phd-zero/experiment-execution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00101 | $0.01830 |
| Opus 5.5 | $0.00040 | $0.00732 |
| Sonnet 5.5 | $0.00020 | $0.00366 |
| Haiku 4.5 | $0.00010 | $0.00183 |
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 1mo 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.
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:
references/experiment-launch-checklist.mdreferences/remote-info-template.md
Required Inputs
Collect minimum safe inputs:
- execution target (
local|remote) - local project root
- runtime project root (required when remote)
- single-node or multi-node
- proxy requirement
- tracker/login requirement
Ask only missing questions.
Run Path Policy
Use shared run_id from run-governor:
- control logs and stage reports:
<codex-cwd>/logs/runs/<run_id>/ - experiment outputs:
<runtime_project_root>/runs/<run_id>/ - 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
full-auto: proceed without confirmation unless hard blocker or major safety risk.moderate: confirm before high-resource actions.detailed: confirm for unclear plans and high-resource actions.
Smoke Validation Policy
Use smoke validation only when needed:
- when launch details are incomplete
- when environment readiness is uncertain
- when cost/risk of full run is high
If setup is clear and safe, direct execution is allowed.
Execution Policy
- Confirm real execution vs dry-run.
- Confirm required inputs.
- Inspect scripts/configs/logs as needed.
- Resolve only blocking gaps.
- Launch smallest valid step first when uncertainty is high.
- Record commands, node assignments, log paths, run IDs.
- If the launched action is long-running, immediately enter watch mode instead of treating launch as completion.
- After each poll, continue with monitoring, diagnosis, recovery, or result collection; do not default to "job started, come back later."
- Replan on major failures.
Watch Mode Policy
Long-running experiment execution is an active responsibility, not a fire-and-forget step.
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.
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.
- 1mo ago First seen · 224 lines · 101 tokens per session scan A f569aaa4e851
experiment-execution is a skill published in the GitHub repository TenureAI/PhD-Zero (53 stars, last pushed 7mo ago), licensed MIT. It adds 101 tokens to every session and 1,830 once invoked, about $0.0004 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.
Other skills, from other repositories
experiment-bridge
A workflow that connects a written experiment plan to its first implementation and test run on a graphics processor.
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…
proof-writer
A mathematical proof-writing skill for machine-learning and artificial-intelligence theory. It helps turn proof requests or incomplete proof sketches into rigorous arguments.
nnsight-remote-interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
pyvene-interventions
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.