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 gke-labs/kube-agents --skill a2a-topicsgit clone --depth 1 https://github.com/gke-labs/kube-agentsWrote 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/gke-labs/kube-agents/a2a-topics)<a href="https://agentmods.dev/skills/gke-labs/kube-agents/a2a-topics"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/a2a-topics/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/gke-labs/kube-agents/a2a-topics"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/a2a-topics.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 | $0.00117 | $0.01407 |
| Opus 5 | $0.00059 | $0.00704 |
| Sonnet 5 | $0.00023 | $0.00281 |
| Haiku 4.5 | $0.00012 | $0.00141 |
Grade A, and why
a2a-topics 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A2A topics: the standing state other agents left you
A topic is a durable, named place on the bus where one agent publishes what it currently knows, so the next question starts from standing state instead of a cold diagnosis. Tasks are conversations; topics are the blackboard.
Two things this skill exists to prevent. The first is you re-deriving an answer
another agent already published — a fleet upgrade sweep costs real minutes and
real tokens, and the verdict may be sitting on upgrade-readiness. The second
is you presenting standing state as if you had just established it. Every entry
carries who wrote it and when, and you relay both.
Prerequisites
The bus address and credentials come from the environment: NATS_URL,
NATS_USER, NATS_PASSWORD. If they are unset, this install is not running
the A2A bus — say so plainly and answer the question another way. Do not
attempt to guess an address.
The client is a2a, on PATH (/usr/local/bin/a2a, shipped in the agent
image alongside this skill). Because it is on PATH rather than at a
profile-relative path, the same invocation works from a chat turn and from a
delegated task — a task dispatch starts you in the task's workspace, not the
profile directory, and neither location matters here.
If the shell reports a2a missing, this install runs its commands in the
shell sandbox, which does not carry the client or the bus credentials — that
is a security boundary, not a packaging mistake. Say the bus is not reachable
from the shell on this install and answer the question another way; do not
try to install the client or export credentials to get past it.
Workflows
1. Find out what exists
a2a topics list
Topics are provisioned configuration — the set is rendered by the operator, and
nothing you do invents a new one. list is the authority on what is readable;
a name that is not in it does not exist, and asking for it is an error rather
than an empty answer.
The CLASS column matters when you read:
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 First seen · 142 lines · 117 tokens per session scan A d399cde59f97
a2a-topics is a skill published in the GitHub repository gke-labs/kube-agents (54 stars, last pushed today), licensed Apache-2.0. It adds 117 tokens to every session and 1,407 once invoked, about $0.0006 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 2026-09-12.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.