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-messengergit 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-messenger)<a href="https://agentmods.dev/skills/byte5ai/palaia/palaia-messenger"><img src="https://agentmods.dev/badge/skills/byte5ai/palaia/palaia-messenger/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-messenger"><img src="https://agentmods.dev/badge/skills/byte5ai/palaia/palaia-messenger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00082 | $0.02116 |
| Opus 5 | $0.00041 | $0.01058 |
| Sonnet 5 | $0.00016 | $0.00423 |
| Haiku 4.5 | $0.00008 | $0.00212 |
Grade A, and why
palaia-messenger 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 10d 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.
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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working alongside other sessions
This person often has more than one AI session going at once — another window, another machine, a different tool entirely — sometimes on the same piece of work. The directory is how sessions find each other; the messenger is how they talk once found. Both are ordinary parts of doing the work, not something to ask permission for.
Do this without being asked
Three moments, every time:
- Starting a task. Register with the directory, describing what you are about to do in your own words. Anyone else working nearby can now find you.
- Picking up a task, especially one that sounds like a continuation. Check for anything waiting for you before you start — a handoff, a question, a heads-up. Acting on stale information because you never looked is the failure this exists to prevent.
- A message asks you for a reply. Answer it, or say plainly that you will not — in the same turn you notice it, not later. A message marked as needing an answer that never gets one leaves the sender waiting on nothing.
None of this is a favour to the person watching. It is the same habit as checking a shared document before editing it.
The tools
| Tool | Use it for |
|---|---|
directory_register |
Announce this session: what you're doing, at the start of a task. |
directory_heartbeat |
Keep your registration alive during a long task. |
directory_update |
Change what you're doing, or mark yourself idle. |
directory_list / directory_query |
Find another live session — by what it's doing, or by a tag it offers. |
directory_deregister |
Leave the directory when a task wraps up. |
messenger_send |
Send one message to a session, or to several at once. |
messenger_check |
Collect whatever has arrived for you. |
messenger_ack |
Close a message once you've dealt with it. |
messenger_thread |
Read a whole back-and-forth, not just the latest message. |
These names are fixed — they do not carry a per-person prefix the way the memory tools do. Use the ones your client actually lists.
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.
- 10d ago First seen · 188 lines · 82 tokens per session scan A 5fc054a9bcf9
palaia-messenger is a skill published in the GitHub repository byte5ai/palaia (19 stars, last pushed 3d ago), licensed MIT. It adds 82 tokens to every session and 2,116 once invoked, about $0.0004 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 2026-08-30.
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.
memx
Use when an agent needs to recall, save, inspect, or audit memX memories through the bundled MCP tools.
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…
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.
memory-to-skill
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…
create-ex
A guided assistant for turning chat records and personal details about a former partner into a digital persona skill that imitates their communication style. The instructions are in Chinese and describe importing WeChat or iMessage records, analysing them, previewing conversations, and writing a skill file.