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 instructions/khaosans/operator-etl/agents-mdgit 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/instructions/khaosans/operator-etl/agents-md)<a href="https://agentmods.dev/instructions/khaosans/operator-etl/agents-md"><img src="https://agentmods.dev/badge/instructions/khaosans/operator-etl/agents-md.svg" alt="Measured on agentmods" 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 | $0.00836 | $0.00836 |
| Opus 5 | $0.00418 | $0.00418 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
operator-etl AGENTS.md 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 today.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions — Operator ETL
You are operating on Operator ETL — agentic data intake for FOIA and public comments.
Human adopters: docs/QUICKSTART.md → ./scripts/verify.sh
Fast verify (do this first)
Before loading OKF or task skills:
- Run
./scripts/verify.sh(ormake verify) - Confirm output contains
OPERATOR_ETL_VERIFY=PASS - Report exit code + demo metrics (
silver=10,quarantined=2,status=complete)
Optional: ./scripts/verify.sh --json for machine-readable result.
Skill: skills/operator-verify/SKILL.md · Full guide: docs/QUICKSTART.md
Human wiki (after verify): docs/index.md (published: https://khaosans.github.io/operator-etl/)
Only after verify passes → continue below.
Load order (extended work)
- Read this file fully.
- Read
okf/index.md— progressive disclosure of the OKF bundle. - Open the skill that matches the task:
- Verify / bootstrap →
skills/operator-verify/SKILL.md - Local MVP / pytest / dashboard →
skills/operator-run/SKILL.md
- Verify / bootstrap →
- GCP Terraform / Cloud Run / BigQuery →
skills/operator-ship-gcp/SKILL.md - AWS Terraform / ECS / S3 →
skills/operator-ship-aws/SKILL.md - Azure Terraform / Container Apps / Blob →
skills/operator-ship-azure/SKILL.md - Any-cloud container deploy →
skills/operator-ship-portable/SKILL.md - New source / domain / gold SQL →
skills/operator-extend/SKILL.md - Security review / hardening / audit →
skills/operator-security/SKILL.md - Discord / chat adapter →
skills/operator-chat/SKILL.md - Finish PRs / cut a release →
skills/operator-release/SKILL.md - Edit OKF bundle →
skills/okf-maintain/SKILL.md
- Follow linked OKF concepts (
okf/playbooks/,okf/models/,okf/decisions/) before improvising.
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.
- today Changed · +8 lines · +216 tokens per session 11e93c17a714
- 4d ago First seen · 53 lines · 620 tokens per session scan A 999c5d1a6ef1
operator-etl AGENTS.md is an instructions file published in the GitHub repository khaosans/operator-etl (0 stars, last pushed today), licensed Apache-2.0. It adds 836 tokens to every session, about $0.0042 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 instructions, from other repositories
goldenflow copilot-instructions.md
Copilot instructions for benseverndev-oss/goldenflow, covering goldenflow, related projects, branch & merge sop (all golden suite repos), environment and commands.
goldenflow CLAUDE.md
Claude Code instructions for benseverndev-oss/goldenflow, covering goldenflow, related projects, branch & merge sop (all golden suite repos), environment and commands.
goldenflow AGENTS.md
AGENTS.md instructions for benseverndev-oss/goldenflow, covering goldenflow, related projects, branch & merge sop (all golden suite repos), environment and commands.
goldenmatch AGENTS.md
AGENTS.md instructions for benseverndev-oss/goldenmatch, covering golden suite monorepo — agent guide, what this is, layout, build & test and landmines to know before you touch anything.
goldenmatch CLAUDE.md
Claude Code instructions for benseverndev-oss/goldenmatch, covering golden suite monorepo, typescript: pnpm + turborepo (post-2026-05-02 fold), ci (.github/workflows/ci.yml), ci path filters (post-2026-05-06, pr #89) and merge queue: main serializes merges fifo (since 2026-06-15).
qwery-core AGENTS.md
Instructions for Guepard-Corp/qwery-core, covering agents.md — strict rules for ai contributors, 1. non-negotiable invariants, 2. code quality rules, 3. hexagonal layout (target after restructure) and use cases (adr #33).