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 skills/khaosans/operator-etl/operator-releasenpx skills add khaosans/operator-etl --skill operator-releasegit 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-release)<a href="https://agentmods.dev/skills/khaosans/operator-etl/operator-release"><img src="https://agentmods.dev/badge/skills/khaosans/operator-etl/operator-release.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 5.1 | $0.00042 | $0.00395 |
| Opus 5 | $0.00021 | $0.00198 |
| Sonnet 5 | $0.00008 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
operator-release 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 yesterday.
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
Release — Operator ETL
Load: merge-feature-pr.md → cut-release.md · Humans: RELEASING.md · VERSIONING.md
Rules
- Run
./scripts/verify.shbefore claiming green. - Feature PRs:
[Unreleased]CHANGELOG only — never bumppyproject.tomlversion. - Do not merge while required CI is red or pending.
- Prefer squash-merge.
- Release = dedicated freeze PR → merge → annotated
v*tag push → watchrelease.yml. - Never retag / move a published tag.
- Software release ≠ FOIA publish (agents-never-publish-prod).
- Skip
make shareunless the user asked for external PDF share.
Agent workflow
verify → finish open feature PRs (Unreleased + CI) → merge
→ release branch (freeze CHANGELOG + bump versions)
→ verify → merge release PR
→ git tag -a vX.Y.Z && git push origin vX.Y.Z
→ confirm Release / GHCR / Packages
→ append okf/log.md
After a freeze
Update implementation-status.md if status changed; append okf/log.md.
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.
- yesterday First seen · 38 lines · 42 tokens per session scan A 856fd5764176
operator-release is a skill published in the GitHub repository khaosans/operator-etl (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 395 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 2026-09-04.
Other skills, from other repositories
datacoolie-release
Plan, preflight, deploy, promote, roll back, or author consume-only release automation for an exact verified DataCoolie build. Use for explicit deployment-lifecycle work; read-only planning may precede authorization, while target mutation requires exact authorization. This skill consumes immutable build artifacts and…
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.
ship-release
Drive a Telepresence release from a prepared branch all the way through CI, docs, the Releases workflow, and PR merges. Assumes make prepare-release has already been run locally and the branch with that commit was pushed and a PR opened. Use when the user says "ship the release", or "complete the release". User-only.
changelog-entry
Add a new entry to CHANGELOG.yml under the current unreleased version (or create the version block if needed), then regenerate documentation. Use when the user says things like "add a changelog entry", "log this fix in the changelog", or "/changelog-entry".
prepare-release
Create the local release commit and tags by setting TELEPRESENCEVERSION and running make prepare-release. Stops at the local commit+tags - pushing is the ship-release skill's job. Use when the user explicitly asks to prepare a release, RC, or test build. User-only.