A pre-flight checklist for starting, restarting, or stopping long machine-learning training jobs, including checks for settings, names, paths, monitoring, and cleanup.

Use it before commands such as python train.py, accelerate launch, torchrun, deepspeed, sbatch, or Weights & Biases sweeps, and when reviewing or stopping a training run.

It helps catch configuration or file-path mistakes before an expensive job runs for hours or days and fails.

launch — Skill for Claude Code and Codex by fcakyon: A pre-flight checklist for starting, restarting, or stopping long…

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/fcakyon/phd-skills/launch

Any agent

npx skills add fcakyon/phd-skills --skill launch

Clone the repo

git clone --depth 1 https://github.com/fcakyon/phd-skills

Made for: Claude Code, Codex.

Or install phd-skills, the plugin that ships this one along with the rest of its 12 skills, 6 commands, 2 agents, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fcakyon/phd-skills/launch.svg)](https://agentmods.dev/skills/fcakyon/phd-skills/launch)

Your own site

<a href="https://agentmods.dev/skills/fcakyon/phd-skills/launch"><img src="https://agentmods.dev/badge/skills/fcakyon/phd-skills/launch.svg" alt="Measured on agentmods" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,422 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.00082	$0.01422
Opus 5	$0.00041	$0.00711
Sonnet 5	$0.00016	$0.00284
Haiku 4.5	$0.00008	$0.00142

Measured 3d ago against content hash cc02e367103d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

launch scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

1. **Local checkpoint dir** on the launching machine: `rm -rf /local/runs/<run-name>` (verify path first; the `destructive_path_guard.sh` will warn).

plugin/skills/launch/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Launch: pre-flight checklist for long ML training jobs

Long training jobs are expensive to fail. A 12-hour run that crashes on epoch 3 from a missing dataset path or a default workers=8 against an NFS mount is a full day lost. This skill walks five quick checks before you commit the GPUs.

The agentic Stop hook in this plugin will route here from reason when an assistant tries to launch a run without going through the checklist.

When to run

The user just asked to:

launch / kick off / start / fire up a training run
restart a run that died
kill a current run (also runs the cleanup half of the checklist)
review a launch command before submitting

Or the user is about to run any of: python train.py, accelerate launch, torchrun, deepspeed, sbatch train.sh, tmux new-session ... python ... train, wandb sweep.

The checklist

1. Config diff against a reference run

The most expensive failure is launching with the wrong knobs. Before starting:

find configs/ recipes/ experiments/ -maxdepth 3 \( -name '*.yaml' -o -name '*.yml' -o -name '*.json' -o -name '*.toml' \) -mtime -30 2> /dev/null | head

Pick the most-recently-modified config that resembles the intended run (same model family, same task). Diff against the intended config:

diff -u configs/baseline_v1.yaml configs/intended.yaml

Walk every diff line. For each, ask: is this difference intentional and motivated, or is it a stale default I forgot to set? Common silent regressors:

num_workers / dataloader workers (default in many repos is 8: wrong on NFS)
batch_size (per-device vs global mismatch under DDP)
learning_rate (linearly scaled with batch size; if batch changed, lr should too)
optimizer betas / weight decay (paper-default vs framework-default)
mixed_precision (fp16 vs bf16 matters for some models)
gradient_accumulation_steps
seed (still set if you care about reproducibility)

If no reference exists in this project, ask the user to point at one. Do not launch with framework defaults alone.

Read the full file on GitHub · 112 lines

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.

3d ago First seen · 112 lines · 82 tokens per session scan C cc02e367103d

Subscribe to this mod's changes

launch is a skill published in the GitHub repository fcakyon/phd-skills (382 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 1,422 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI Languages academic agents ai claude claude-code claude-code-plugin

ax-go-flow

Use when writing Go code with github.com/ax-llm/ax/packages/go for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.

ax-llm/ax · 43 tokens

ax-go-gen

Use when writing Go code with github.com/ax-llm/ax/packages/go for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.

ax-llm/ax · 54 tokens

ax-go-signature

Use when writing Go code with github.com/ax-llm/ax/packages/go for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.

ax-llm/ax · 43 tokens

ax-go-agent

Use when writing Go code with github.com/ax-llm/ax/packages/go for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.

ax-llm/ax · 57 tokens

ax-go-agent-optimize

Use when writing Go code with github.com/ax-llm/ax/packages/go for agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA.

ax-llm/ax · 51 tokens

fenic-mechanics

Use when writing, editing, or debugging code that uses fenic (the fenic Python library, imported as import fenic as fc) — the semantic-DataFrame engine with LLM operators (semantic.map/extract/classify/predicate/reduce, embeddings), jq/markdown/transcript processing, chunking, and fuzzy matching. Covers fenic's import…

typedef-ai/fenic · 114 tokens

launch