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 skills add khaosans/operator-etl --skill operator-securitygit clone --depth 1 https://github.com/khaosans/operator-etlWrote 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/operator-security)<a href="https://agentmods.dev/skills/khaosans/operator-etl/operator-security"><img src="https://agentmods.dev/badge/skills/khaosans/operator-etl/operator-security/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/operator-security"><img src="https://agentmods.dev/badge/skills/khaosans/operator-etl/operator-security.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 | $0.00024 | $0.00994 |
| Opus 5.5 | $0.00010 | $0.00398 |
| Sonnet 5.5 | $0.00005 | $0.00199 |
| Haiku 4.5 | $0.00002 | $0.00099 |
Grade A, and why
operator-security 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 1mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security hardening — Operator ETL
Load: SECURITY.md · SECURITY-HARDENING.md · FINAL-REVIEW.md · okf/decisions/pii-fail-closed.md
When to use this skill
- Any change touching
vault.py,pii.py,secrets.tf,iam.tf, or auth middleware - Adding new HTTP endpoints or MCP tools
- Reviewing PRs that modify data extraction, transformation, or loading
- Before any GCP deploy or production-readiness claim
Security checklist for every PR
- Path safety — file URL handlers must resolve + guard against traversal (
is_relative_to) - Input validation — Pydantic models with
max_length; body size middleware enforced - No secrets in code — Terraform uses
sensitivevars with validation; no inline placeholders - Vault permissions — key and vault JSON created with
0o600; warn on permissive existing files - Rate limiting — all non-health endpoints protected by per-client sliding window
- Error sanitization — no tracebacks or internal data in HTTP responses; log type + message only
- PII boundary — raw PII never in insight text, MCP responses, or LLM context
- MCP allowlist — only 3 tools; no vault decrypt; no raw SQL
- CODEOWNERS — security-sensitive paths require review (
.github/CODEOWNERS)
CI security gates
| Gate | Tool | Config |
|---|---|---|
| SAST | bandit | .bandit.yml — scans src/, skips B101 (assert in tests); other hits need a fix or # nosec; CI job in .github/workflows/ci.yml → ci-gate |
| SCA | pip-audit | .github/workflows/ci.yml (pip-audit → ci-gate) — dependency CVE check |
| Secret scan | gitleaks | .github/workflows/ci.yml (gitleaks → ci-gate) |
| CodeQL | codeql-action | .github/workflows/codeql.yml — Python security-extended |
| Container CVE | Trivy | .github/workflows/ci.yml docker job — HIGH/CRITICAL |
| IaC | Checkov | .github/workflows/ci.yml terraform job + .checkov.yml |
| Dependency updates | Dependabot | .github/dependabot.yml — pip, Actions, Docker, Terraform |
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.
- 1mo ago Changed 27166567f3bf
- 1mo ago First seen · 74 lines · 24 tokens per session scan A 8ddb303fc5a6
operator-security is a skill published in the GitHub repository khaosans/operator-etl (0 stars, last pushed 8d ago), licensed Apache-2.0. It adds 24 tokens to every session and 994 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
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.
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.
aegis-dq
Agentic data quality validation across warehouses (DuckDB, BigQuery, Athena, Databricks, Postgres) with LLM diagnosis, root cause analysis, and audit trail.
tianji-worker
Use when creating, testing, deploying, invoking, debugging, scheduling, pausing, or rolling back Tianji Workers, or managing their environment variables and shared modules.
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.
airflow-state-store
Persists task and asset state across retries and DAG runs using Airflow 3.3's AIP-103 key/value stores (taskstatestore, assetstatestore) and the crash-safe ResumableJobMixin. Use when the user asks about task state store, checkpointing in tasks, persisting state across retries, job IDs surviving worker crashes…