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.
npx agentmods add commands/zayne-sprague/dr-claude-code/experiment-preflightgit clone --depth 1 https://github.com/Zayne-sprague/Dr-Claude-CodeWrote 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/commands/zayne-sprague/dr-claude-code/experiment-preflight)<a href="https://agentmods.dev/commands/zayne-sprague/dr-claude-code/experiment-preflight"><img src="https://agentmods.dev/badge/commands/zayne-sprague/dr-claude-code/experiment-preflight.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.01001 |
| Opus 5 | $0.00011 | $0.00500 |
| Sonnet 5 | $0.00004 | $0.00200 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
experiment-preflight scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experiment Pre-flight
Run this before submitting any job that uses compute. It ensures the experiment won't waste GPU hours on bugs, bad configs, or flawed designs.
The experiment name is provided as the argument. If not provided, ask for it.
Step 1: Locate experiment files
Read:
notes/experiments/$EXPERIMENT/experiment.yamlnotes/experiments/$EXPERIMENT/red_team_brief.md(may not exist yet)- The experiment code referenced in experiment.yaml
If experiment.yaml doesn't exist, create the experiment folder first (use the experiment-management skill).
Step 2: Red Team Brief
If red_team_brief.md doesn't exist, create it now by reviewing the experiment design. The brief should cover:
- What could go wrong (truncation, wrong eval metric, bad prompt format, OOM, etc.)
- How to validate that results are real
- What a canary job should check
If it already exists and the experiment has changed since it was written, update it.
Step 3: Adversarial review
Dispatch a fresh red-team-reviewer subagent. It must NOT receive the design conversation — only the files. This prevents sunk-cost bias.
The reviewer checks:
- Every concern in the Red Team Brief — does the code actually handle it?
- max_tokens, temperature, n_samples — will they produce meaningful results?
- Checkpointing enabled for long jobs?
- Evaluator/reward function matches what the hypothesis needs?
- Output format compatible with HF upload and the dashboard?
- No
python -c "import X" || pip installpatterns in sbatch scripts — these hang on GPU nodes due to CUDA init. Usepip install --quietdirectly. - vLLM jobs must set
VLLM_WORKER_MULTIPROC_METHOD=spawnbefore any Python runs — prevents "Cannot re-initialize CUDA in forked subprocess" crash. - No HF uploads in the same process as vLLM — push_dataset_to_hub kills EngineCore. Must use subprocess isolation.
HF_ORGin sbatch must be the upload org, not the source org — if the experiment downloads models from org A but uploads results to org B, these must be separate variables.
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.
- 4d ago First seen · 88 lines · 22 tokens per session scan A 1897d52fb681
experiment-preflight is a command published in the GitHub repository Zayne-sprague/Dr-Claude-Code (5 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 1,001 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 2026-08-31.
Other commands, from other repositories
master_analysis
Run comprehensive 5-phase analysis across labs, genetics, and protocols.
render-figures
Compile all .tex and .typ figure files in a directory.
diff
Quantitative volume comparison between a CadQuery model and a reference STEP file.
arg-diagram
ARG academic-paper diagram mode — standalone structural & conceptual diagram generation.
Icon Data & AI Review
Intelligent AI/ML analysis that automatically selects the most relevant legendary data science and AI experts for your project.
replication-package
Scaffold or audit a social-science replication package at a target directory, and audit the manuscript and its archived research objects against FAIR principles.