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 Augustas11/macprovider --skill agent-onboardinggit clone --depth 1 https://github.com/Augustas11/macproviderWrote 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/augustas11/macprovider/agent-onboarding)<a href="https://agentmods.dev/skills/augustas11/macprovider/agent-onboarding"><img src="https://agentmods.dev/badge/skills/augustas11/macprovider/agent-onboarding/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/augustas11/macprovider/agent-onboarding"><img src="https://agentmods.dev/badge/skills/augustas11/macprovider/agent-onboarding.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 | $0.00050 | $0.03860 |
| Opus 5.5 | $0.00020 | $0.01544 |
| Sonnet 5.5 | $0.00010 | $0.00772 |
| Haiku 4.5 | $0.00005 | $0.00386 |
Grade C, and why
malibu-provider-api-onboarding scanned grade C with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 "$tmp_install" Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Codex CLI: add a custom provider in `~/.codex/config.toml`: Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL --proto '=https' --tlsv1.2 --remove-on-error https://get.malibu.tech/install.sh -o "$tmp_install" How it starts
The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Malibu Provider And API Onboarding
Canonical publication URL: https://get.malibu.tech/skill.md
Discovery index publication URL: https://get.malibu.tech/.well-known/skills/index.json
Last updated: 2026-09-23
Use this skill for two jobs only:
- Help a new invited Apple Silicon provider install Malibu, get admitted, serve a paid catalog model, verify serving, operate safely, recover, update, or uninstall.
- Help a buyer configure Malibu as an OpenAI-compatible or Anthropic-compatible backend for a coding-agent harness or SDK.
Safety Rules
- Never print secrets. Redact provider tokens, buyer API keys, Keychain values, signing keys, SSH keys, environment files, raw prompts, raw logs, and release material.
- Default to non-production local smoke checks. Production publication, billing, payout, auth, coordinator, release, and deployment work require explicit operator approval.
- Do not run destructive commands such as real install, update, uninstall, credential rotation, model switch, or service replacement unless the user asked for that exact action.
- Never pipe a network fetch into a shell. Fetch scripts to a mode-0600 file, preview and syntax-check them, dry-run when supported, then run the same local bytes only after approval.
- Do not inspect
d-inferencesource. It is outside the clean-room boundary. - Use public
malibu.techURLs. Do not introduce legacy internal hosts.
Provider Decision Tree
- GUI owner at the Mac: prefer Malibu.app from
https://malibu.tech/host. - Terminal or SSH fleet setup: use
https://get.malibu.tech/install.sh. - SSH/headless mode must use
MACPROVIDER_HEADLESS=1and a non-rootMACPROVIDER_HEADLESS_USER. Headless setup needs workingsudo; Keychain prompts cannot be completed over a blind SSH session. - The installed user-facing command is
malibu-cli. Some on-disk paths and process names remainmacprovider-cli; those are wire names, not product names.
Provider Prerequisites
What ships with it
1 file 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.
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 · +6 lines 049f93be4238
- 1mo ago Changed · +170 lines · +13 tokens per session scan D → C 2f88254e917b
- 1mo ago Changed · +11 lines 93169a3e861e
- 2mo ago Changed a5f94a4ef3d1
- 2mo ago First seen · 174 lines · 37 tokens per session scan D 7aa3b6ab5c05
malibu-provider-api-onboarding is a skill published in the GitHub repository Augustas11/macprovider (10 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 3,860 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 3 findings (asks for root, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
holoscan-install-wheel
Install Holoscan SDK 5.x CUDA 13 Python wheels in an isolated environment, choosing the full stack or version-matched components.
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…