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.
git clone --depth 1 https://github.com/khaosans/operator-etlnpx agentmods add skills/khaosans/operator-etl/okf-maintainWrote 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/khaosans/operator-etl/okf-maintain)<a href="https://agentmods.dev/skills/khaosans/operator-etl/okf-maintain"><img src="https://agentmods.dev/badge/skills/khaosans/operator-etl/okf-maintain/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/khaosans/operator-etl/okf-maintain"><img src="https://agentmods.dev/badge/skills/khaosans/operator-etl/okf-maintain.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 | $0.00040 | $0.00275 |
| Opus 5 | $0.00020 | $0.00138 |
| Sonnet 5 | $0.00008 | $0.00055 |
| Haiku 4.5 | $0.00004 | $0.00028 |
Grade A, and why
okf-maintain 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 5d 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.
What it actually says
Maintain the OKF bundle
Load: okf-spec.md and docs/LEVERAGE.md
Rules
- Every concept file needs YAML frontmatter with non-empty
type. - Update directory listings in okf/index.md when adding concepts.
- Append dated entries to okf/log.md.
- Sync implementation-status.md when code status changes.
- When the pytest suite size changes, update together: README badge, TESTING.md, implementation-status, QUICKSTART examples, and the fallback count in scripts/verify.sh.
Validate
python3 scripts/okf_validate.py okf --strict
./harness/e2e.sh
Conventional types
Publication, OperatingModel, Decision, Playbook, Reference
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.
- 5d ago Changed · +1 lines 714f03d41cc4
- 8d ago First seen · 29 lines · 40 tokens per session scan A ef2a54ca46c6
okf-maintain is a skill published in the GitHub repository khaosans/operator-etl (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 275 once invoked, about $0.0002 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 skills, from other repositories
runtime-copilot
Use when the user wants to operate, diagnose, or validate the Mini Data Engine MCP runtime from Codex; prefer the MCP surface over raw shell commands, start with projecttoolcatalog and projectgetdefaults, then use healthcheck, projectrunregression, explainrun, projectcomparebaseline, and related runtime tools.
polars
Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.
ray-data
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
Data Pipeline Engineering
Guide for designing, building, and maintaining reliable data pipelines.
data-engineer
Builds data infrastructure — ETL/ELT pipelines, data warehousing, stream processing, data quality, orchestration (Airflow/Dagster), and analytics engineering (dbt). Use when the user asks to build data pipelines, set up ETL/ELT workflows, design a data warehouse, configure stream processing, or implement analytics…
datahub-verified-remediation
Use this skill when a source schema change has broken, or is about to break, a downstream transformation and the user wants a fix they can merge — not a summary. Triggers on: "a column was renamed, fix the dbt model", "this field is gone downstream", "schema drift", "our model still selects the old column", "generate…