gsd-loop-engineering

gsd-loop-engineering is a skill for Claude Code, Codex from topprismdata/cultivating-ml-agent. It costs 136 tokens per session (2,264 once invoked), scanned A, original, MIT.

A way to organise machine-learning work as repeated plan, build, check, and fix-or-submit stages. It is designed for multi-step data pipelines, such as preparing data, training models, checking results, and creating a competition submission.

In plain words
What is it for?
Use it for end-to-end Kaggle work and other multi-stage ML pipelines that need fresh working context, shared memory, and evidence at each stage.
Why use it?
It reduces mistakes caused by long sessions, missing checks, forgotten decisions, or steps being accepted without proof.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node bin/install.js.

Good fit Use it for end-to-end Kaggle work and other multi-stage ML pipelines that…

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/topprismdata/cultivating-ml-agent
agentmods
npx agentmods add skills/topprismdata/cultivating-ml-agent/gsd-loop-engineering

Made for: Claude Code, 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 gsd-loop-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/gsd-loop-engineering.svg)](https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/gsd-loop-engineering)
Your own site
<a href="https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/gsd-loop-engineering"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/gsd-loop-engineering.svg" alt="Measured on agentmods" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,264 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 $0.00136 $0.02264
Opus 5 $0.00068 $0.01132
Sonnet 5 $0.00027 $0.00453
Haiku 4.5 $0.00014 $0.00226

Measured 7d ago against content hash 3f82a272b62c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

gsd-loop-engineering 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 7d 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/examples/gsd-loop-engineering/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GSD Loop Engineering for ML Tasks

Problem

ML pipelines are naturally multi-stage loops:

  1. Plan → 2. Execute (data prep / train / generate submission) → 3. Verify (format / CV-LB gap / sanity) → 4. Fix or Ship.

Most agentic ML workflows fail because:

  • Context rot: long sessions degrade model output (e.g., 0/1 submission bug in S6E2 was partly due to loss of focus)
  • No verification: tasks accepted as done without adversarial checking (S6E4 submission would have been caught by a verifier)
  • No shared memory: each step reinvents context from scratch
  • Drift on style: best practices from start of session get forgotten by end

GSD Core (open-gsd/gsd-core) is the canonical loop-engineering framework solving exactly this. This skill adapts its patterns to ML.

Context / Trigger Conditions

Use this skill when:

  • Working on a Kaggle competition end-to-end
  • Designing a multi-stage ML pipeline (data → features → train → ensemble → submit)
  • Session has > 50 turns and quality is degrading
  • You want auditable proof each step worked (not just "looks right")
  • You're tempted to use --dangerously-skip-permissions (don't)

Don't use:

  • Single-file one-off scripts
  • Pure EDA with no downstream work
  • Research tasks where you're just reading papers

Solution: 5-Phase ML Loop

┌────────────────────────────────────────────────────────────┐
│  Phase 1: DISCUSS (gsd-discuss-phase)                      │
│  - Resolve ambiguities in the task brief                   │
│  - Output: .planning/phases/<N>-DISCUSS.md                  │
├────────────────────────────────────────────────────────────┤
│  Phase 2: PLAN (gsd-plan-phase)                             │
│  - Research + plan, but in fresh-context subagent          │
│  - Plans declare wave dependencies (DAG)                   │
│  - Output: .planning/phases/<N>/RESEARCH.md + PLAN-<M>.md  │
├────────────────────────────────────────────────────────────┤
│  Phase 3: EXECUTE (gsd-execute-phase)                       │
│  - Run plans in waves (parallel where independent)         │
│  - Each plan is a fresh-context subagent                   │
│  - Output: artifacts (models, submissions, logs)          │
├────────────────────────────────────────────────────────────┤
│  Phase 4: VERIFY (gsd-verify)                              │
│  - Adversarial check: assume goal NOT achieved             │
│  - Findings classified BLOCKER / WARNING / VERIFIED        │
│  - Output: .planning/phases/<N>/VERIFICATION.md            │
├────────────────────────────────────────────────────────────┤
│  Phase 5: SHIP or FIX                                      │
│  - VERIFIED → ship submission, archive artefacts           │
│  - BLOCKER → generate fix plan, re-enter Phase 2           │
│  - WARNING → decide case-by-case                           │
└────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 199 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.

  1. 7d ago First seen · 199 lines · 136 tokens per session scan A 3f82a272b62c

Subscribe to this mod's changes

gsd-loop-engineering is a skill published in the GitHub repository topprismdata/cultivating-ml-agent (5 stars, last pushed 9d ago), licensed MIT. It adds 136 tokens to every session and 2,264 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

huggingface-hub

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

braxtonROSE4/zorro-agent · 43 tokens

tensorboard

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit.

davila7/claude-code-templates · 32 tokens

mlflow

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.

davila7/claude-code-templates · 33 tokens

datachain-knowledge

Use whenever datasets, cloud storage buckets, or data pipelines are mentioned — creating, saving, querying, listing, exploring, deleting, or processing data in S3, GCS, Azure Blob, or local storage. Also use when running any script that may create datasets as a side effect. Maintains a knowledge base at dc-knowledge/…

datachain-ai/datachain · 104 tokens

prompt-scanner

A scanner for text sent to an AI agent, looking for prompt injection and jailbreak attempts. Prompt injection is text that tries to override an agent's instructions; a jailbreak tries to bypass its safety limits.

alibaba/anolisa · 103 tokens

install-openviking-memory

Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…

volcengine/OpenViking · 191 tokens