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 byte5ai/palaia --skill palaia-installgit clone --depth 1 https://github.com/byte5ai/palaiaWrote 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/byte5ai/palaia/palaia-install)<a href="https://agentmods.dev/skills/byte5ai/palaia/palaia-install"><img src="https://agentmods.dev/badge/skills/byte5ai/palaia/palaia-install/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/byte5ai/palaia/palaia-install"><img src="https://agentmods.dev/badge/skills/byte5ai/palaia/palaia-install.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 | $0.00136 | $0.03906 |
| Opus 5.5 | $0.00054 | $0.01562 |
| Sonnet 5.5 | $0.00027 | $0.00781 |
| Haiku 4.5 | $0.00014 | $0.00391 |
Grade F, and why
palaia-install scanned grade F with 4 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 12d 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.
`sudo tail -n 50 /var/log/cloud-init-output.log`. Every line palaia's own setup Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://get.palaia.ai | sh Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.palaia-setup Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://get.palaia.ai | sh How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Get palaia running
You are setting palaia up for someone who may not be technical. Your job is to ask a few plain questions, then do the work — run the commands yourself if you can reach their machine, otherwise give them exactly one line to paste. Never show them a wall of Docker commands and never assume they know what any of this means. One step at a time; wait for each to finish before the next.
palaia runs on a machine they own and is reached in a browser. It is almost always a separate always-on box (a rented server, a NAS, a small Pi), because a hub that only serves the laptop it lives on gives up the point of it. Keep that in mind when they are unsure where to put it.
Before you start — read the real files
The setup file and the install command change between releases, so never write them from memory, and never from this page alone. Read them from the files palaia actually ships, every time:
| What | File | Address |
|---|---|---|
| The setup file pasted in when a server is created | v3/deploy/cloud-init.yaml |
https://get.palaia.ai/cloud-init |
| The installer for a server that already exists | v3/deploy/get-palaia.sh |
https://get.palaia.ai/install |
| Notes on reboots, updates and backups | v3/deploy/README.md |
https://get.palaia.ai/deploy-notes |
| Which release this is | v3/VERSION |
https://get.palaia.ai/version |
If you are working inside a copy of the palaia repository, read the files there. Otherwise open each address — those are the only addresses to use or show; never point the person at any other place to download from. Read all four from the same place, so they belong to the same release. If you cannot open files or web pages at all, say so plainly and do not make the commands up.
Which image this release uses
Read v3/VERSION. If it contains a hyphen (like 3.0.0-rc2), this is a test
release: palaia's image is published only under the beta name, and the
everyday stable name does not exist yet. With no hyphen (like 3.0.0), it is
a full release and stable is right.
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.
- 12d ago Changed · +64 lines scan D → F 6ca31abf51e2
- 19d ago Changed · +105 lines scan C → D 162d0fd36697
- 24d ago First seen · 135 lines · 136 tokens per session scan C d30efc1694fd
palaia-install is a skill published in the GitHub repository byte5ai/palaia (20 stars, last pushed 3d ago), licensed MIT. It adds 136 tokens to every session and 3,906 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-22.
Other skills, from other repositories
setup
A setup guide for session-recall, a tool that lets an agent search and reuse information from earlier conversations. It covers installation, language, local or cloud processing, and optional team sharing.
session-recall
Search the unified local history of past Claude Code, Codex, and Cursor sessions at the START of a task when the user references a prior bug, feature, decision, file, or piece of work. Use before assuming fresh context for prompts such as "remember when…", "we worked on…", "the X bug", "back to…", "what did we decide…
memx
Use when an agent needs to recall, save, inspect, or audit memX memories through the bundled MCP tools.
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
service-publishing
Expose worker HTTP services via Higress gateway. Use when admin asks to publish a worker's web app or API to make it externally accessible.