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 isolated-setup-doctorgit 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/isolated-setup-doctor)<a href="https://agentmods.dev/skills/apache/magpie/isolated-setup-doctor"><img src="https://agentmods.dev/badge/skills/apache/magpie/isolated-setup-doctor/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/isolated-setup-doctor"><img src="https://agentmods.dev/badge/skills/apache/magpie/isolated-setup-doctor.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 | $0.00073 | $0.06837 |
| Opus 5.5 | $0.00029 | $0.02735 |
| Sonnet 5.5 | $0.00015 | $0.01367 |
| Haiku 4.5 | $0.00007 | $0.00684 |
Grade B, and why
isolated-setup-doctor scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude/settings.json` is usually unreadable from inside the sandbox, so the exclusion check may see only the project-scope files. How it starts
The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
setup-isolated-setup-doctor
Runtime routing (run before the Claude-specific probes)
Use the operator's explicitly requested runtime when supplied; otherwise use the active session's runtime. An installed executable or configuration directory alone does not select a runtime. For the routing below, treat that selection as the active harness.
When the active harness is Codex, first require the static verification in docs/adapters/codex.md, then run the shared live environment probes inside the active Codex sandbox.
Attribute failures separately to native sandbox/network denial, approval policy, or the POSIX agent-iso layer.
Do not prescribe a .claude settings change for a Codex failure.
Then stop before the Claude-specific branch below.
When the selected runtime is Antigravity, follow docs/adapters/antigravity.md: verify the user-scope profile first, then diagnose the actual tool result in the active Antigravity session. Distinguish sandbox limits, permission-rule denials, guard-hook failures, and wrapper or authentication problems. Do not require Claude configuration or prescribe Claude settings changes; then stop before the Claude-specific probes below.
When the selected runtime is Pi, follow docs/adapters/pi.md: verify the package install first, then diagnose the actual tool result in the active Pi session. Distinguish sandbox limits or a sandbox that could not start, permission-rule denials, guard denials, and wrapper or authentication problems. Do not require Claude configuration or prescribe Claude settings changes; then stop before the Claude-specific probes below.
When the selected runtime is Copilot CLI, follow docs/adapters/copilot.md: verify the hook first, then diagnose the actual tool result in the live session.
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/probe-1-ssh-agent.sh 1.7 KB runs code
- scripts/probe-2-localhost-bind.sh 1.8 KB runs code
- scripts/probe-3-container-gateway.sh 6.8 KB runs code
- scripts/probe-4-scratch-dir.sh 1.4 KB runs code
- scripts/probe-5-signing-key.sh 2.1 KB runs code
- scripts/probe-6-gh-outside-sandbox.sh 2.2 KB runs code
- scripts/probe-7-dev-tools.sh 2.3 KB runs code
- scripts/probe-8-git-hooks.sh 2.2 KB runs code
- scripts/probe-9-working-dirs.sh 3.7 KB runs code
- scripts/README.md 1.7 KB
- tests/helpers.py 3.1 KB runs code
- tests/test_probe_1_ssh_agent.py 4.2 KB runs code
- tests/test_probe_3_container_gateway.py 9.4 KB runs code
- tests/test_probe_5_signing_key.py 4.5 KB runs code
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 fd560249d2e1
- yesterday Changed · +4 lines e75714dd759b
- 3d ago Changed 74d1e95843c7
- 10d ago Changed · +2 lines ddeb1d4342f8
- 12d ago Changed · +2 lines 7fd384fba037
- 19d ago Changed · +2 lines 986064173e10
- 22d ago Changed b8a54010bcab
- 1mo ago Changed · +26 lines 1c94e4f71032
- 1mo ago Changed · +1 lines 7ff29448a482
- 1mo ago First seen · 347 lines · 73 tokens per session scan B ba5d0773615f
isolated-setup-doctor is a skill published in the GitHub repository apache/magpie (128 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 6,837 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-14.
Other skills, from other repositories
omv-repro
Guides a researcher through local reproduction of a vulnerability finding. Use when the user has an omv-audit result with evidence.reproducer filled but evidence.observedresult still unknown, wants to confirm a finding by running it locally, or invokes /omv-repro. Reads .omv/findings/ .yaml and guides step-by-step…
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.
report-issue-local
File a bug or feature request against this MCP server's own repo. Use for server-specific issues — tool logic, service integrations, config problems, or domain bugs that aren't caused by the framework.
python-performance-optimization
Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving application performance.
python-error-handling
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.