Apache Magpie is a framework of agent-assisted workflows for maintaining Apache software projects, including issue triage, pull-request review, contributor mentoring, and security-report handling. Apache maintainers and developers use it to delegate repetitive project work to coding agents while retaining human review. Its catalogue entries are the skills, instructions, plugin, and settings that implement these workflows.
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 apache/magpie --skill privacy-llmgit clone --depth 1 https://github.com/apache/magpieWrote 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/apache/magpie/privacy-llm)<a href="https://agentmods.dev/skills/apache/magpie/privacy-llm"><img src="https://agentmods.dev/badge/skills/apache/magpie/privacy-llm/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/apache/magpie/privacy-llm"><img src="https://agentmods.dev/badge/skills/apache/magpie/privacy-llm.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 | $0.00067 | $0.02202 |
| Opus 5.5 | $0.00027 | $0.00881 |
| Sonnet 5.5 | $0.00013 | $0.00440 |
| Haiku 4.5 | $0.00007 | $0.00220 |
Grade A, and why
privacy-llm 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
setup-privacy-llm
Decide which LLMs this project's skills may send private foundation content to, record that decision where the skills look for it, and prove it holds.
Two mechanisms, and this skill configures one of them:
- The approved-LLM gate — applies to
<private-list>mail and any other private foundation list. A skill refuses to fetch unless every LLM in the active stack is approved. This is what the skill configures, by picking a variant. - PII redaction — applies to
<security-list>mail. Third parties the reporter names are replaced with hash-prefixed identifiers before any LLM sees them. It runs under every variant and needs no per-variant configuration; this skill only verifies it works.
The recipes are docs/setup/privacy-llm.md;
the contract behind them is
tools/privacy-llm/tool.md.
This skill walks the recipe rather than restating it — read the
variant you land on before writing anything.
[!IMPORTANT] This is a project decision, not a personal preference. What goes in the committed copy says what the project permits for everyone's sessions. Configure locally for yourself freely; see Step 5 before promoting anything to the committed half.
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 2e36b66cce61
- 12d ago Changed a32c8ac4239c
- 22d ago Changed · +11 lines 1b05394c781b
- 1mo ago Changed · +1 lines 17a7756ca0ac
- 1mo ago Changed · -5 tokens per session daf38d584939
- 1mo ago Changed · -7 lines · -25 tokens per session b89f1f5e421d
- 1mo ago First seen · 208 lines · 97 tokens per session scan A 0e27b542a165
privacy-llm is a skill published in the GitHub repository apache/magpie (128 stars, last pushed yesterday), licensed Apache-2.0. It adds 67 tokens to every session and 2,202 once invoked, about $0.0003 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 2026-09-14.
Other skills, from other repositories
airflow-dag-patterns-v3
Apache Airflow DAG Patterns workflow skill. Use this skill when the user needs Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs and the operator should preserve the upstream…
airflow-dag-patterns
Apache Airflow DAG Patterns workflow skill. Use this skill when the user needs Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs and the operator should preserve the upstream…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.