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 agents/kid-sid/codex-spellbook/data-pipeline.agentsgit clone --depth 1 https://github.com/kid-sid/codex-spellbookWhat 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 | $0.00000 | $0.00534 |
| Opus 5 | $0.00000 | $0.00267 |
| Sonnet 5 | $0.00000 | $0.00107 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
data-pipeline.agents 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Pipeline Agent Template
Purpose
Use this template for Python data pipelines that extract, transform, and load data while preserving schema clarity, idempotency, and observable failure modes.
Environment Setup
Run these commands before starting work:
set -euo pipefail
bash setup-scripts/python.sh
python --version
pytest --version
python -c "import pandas" >/dev/null 2>&1 || true
python -c "import polars" >/dev/null 2>&1 || true
Working Style
- Prefer explicit pipeline stages over giant notebooks or monolithic scripts.
- Make transformations deterministic and idempotent.
- Fail loudly on schema drift, nullability surprises, and row drops.
- Keep side effects isolated to extract and load boundaries.
Python and Data Conventions
- Add type hints to stage functions and helpers.
- Use pandas or polars intentionally; do not mix both in one module without cause.
- Validate external records and config at boundaries.
- Use immutable or append-only intermediate data where practical.
Pipeline Design
- Split work into extract, validate, transform, and load phases.
- Make load steps idempotent through merge keys, partition replacement, or checkpoints.
- Track row counts and critical aggregates between stages.
- Reject silent coercions that hide data loss.
Logging and Observability
- Use
structlogor the project logger for structured events. - Log dataset identifiers, batch windows, input counts, output counts, and error reasons.
- Emit warnings for dropped or quarantined records with enough context to debug safely.
Testing
- Use pytest for stage-level unit tests.
- Build fixtures from small realistic datasets, not giant snapshots.
- Assert row counts, schema expectations, and transformation invariants.
- Add regression tests for previously corrupted or malformed inputs.
Storage and Performance
- Avoid row-by-row loops when vectorized or batch operations exist.
- Keep memory growth visible when processing large datasets.
- Push filters and projections down to extract queries when possible.
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 · 75 lines · 0 tokens per session scan A f75c4eb93b63
data-pipeline.agents is an agent published in the GitHub repository kid-sid/codex-spellbook (21 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 534 tokens. 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 agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
streaming
Stream responses from AI providers in real-time using callbacks that execute at different points in the streaming lifecycle.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
mlops-reviewer
MLOps / model lifecycle pre-implementation reviewer. Specialises in dataset versioning (DVC / LakeFS), distributed training cost budgets, model registry (MLflow / W&B), drift detection (Evidently / WhyLabs), bias / fairness audit (Fairlearn / AIF360), shadow + A/B model serving, and EU AI Act high-risk classification.…
by-epitope
Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.
prompt_engineer
Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…