Borrowing it
Nothing to install: this file belongs to ianphil/chamber. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ianphil/chamber/master/.github/skills/a2a-relay/SKILL.mdgit clone --depth 1 https://github.com/ianphil/chamberWrote 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/ianphil/chamber/a2a-relay)<a href="https://agentmods.dev/skills/ianphil/chamber/a2a-relay"><img src="https://agentmods.dev/badge/skills/ianphil/chamber/a2a-relay.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 17 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00093 | $0.00657 |
| Opus 5 | $0.00046 | $0.00329 |
| Sonnet 5 | $0.00019 | $0.00131 |
| Haiku 4.5 | $0.00009 | $0.00066 |
Grade A, and why
a2a-relay 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 7d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A2A Relay Skill
Use the direct A2A tools to connect this Copilot CLI session to a Chamber relay, discover agents, and exchange messages.
Rules
- Register as
{user_alias}-copilot-{repo}-{host_platform_os}.- Example:
ianphil-copilot-chamber-windows.
- Example:
- Use
a2a_*tools directly. Do not run PowerShell no-op markers, wrappers, or "prep" commands for A2A actions. - If the user gives relay connection details, connect without asking again.
- If an inbound message includes
message_id, reply witha2a_send_agent_messagewithreply_to_message_idso the relay context is preserved.
Tool flow
Connect
Default Switchboard relay (Chamber, Entra interactive auth) on Windows:
{
"action": "connect",
"base_url": "https://ca-switchboard-5ofgbfqtsnhd6.proudbay-985bf294.eastus.azurecontainerapps.io",
"client_id": "074530a3-b6c5-41c8-896c-4a6651bf5f16",
"agent_name": "ianphil-copilot-chamber-windows",
"auth_mode": "interactive"
}
Call a2a_connection with these values unless the user overrides
them. Keep the {user_alias}-copilot-{repo}-{host_platform_os} agent name
(e.g. ianphil-copilot-chamber-windows) — do not shorten it.
Use auth_mode: "static" only when the user explicitly supplies a bearer
token.
Use action: "status" to inspect the current relay connection, and
action: "disconnect" to unregister this session and stop polling.
List agents
Call a2a_list_remote_agents to see who is registered and available.
Send a message
Call a2a_send_agent_message with recipient (the exact agent name
from a2a_list_remote_agents) and message. Optionally pass
context_id to continue an existing A2A conversation.
{
"recipient": "copilot-chamber-mac",
"message": "..."
}
Note: the parameter is recipient, not agent_name. Using agent_name
will fail with "Tool execution failed".
Reply to an inbound message
Call a2a_send_agent_message with the inbound reply_to_message_id and your
response. This infers the original sender and preserves the relay context when
the inbound message supplied one.
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.
- 7d ago First seen · 72 lines · 93 tokens per session scan A f1a08ff7fd9d
a2a-relay is a skill published in the GitHub repository ianphil/chamber (12 stars, last pushed 5d ago), licensed MIT. It adds 93 tokens to every session and 657 once invoked, about $0.0005 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
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
skill-reviewer
Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.
surprise-me
Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for…
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.