SAM, or Sovereign Agent Mesh, is a peer-to-peer network that lets autonomous AI agents discover one another, connect securely, communicate, and invoke tools. It is intended for operators building decentralized, zero-trust agent networks across cloud, local, and edge environments. The catalogue skill and instruction help agents join or work with the mesh.
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 google/sam --skill sam-a2a-bridgegit clone --depth 1 https://github.com/google/samWrote 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/google/sam/sam-a2a-bridge)<a href="https://agentmods.dev/skills/google/sam/sam-a2a-bridge"><img src="https://agentmods.dev/badge/skills/google/sam/sam-a2a-bridge/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/google/sam/sam-a2a-bridge"><img src="https://agentmods.dev/badge/skills/google/sam/sam-a2a-bridge.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 | $0.00104 | $0.01428 |
| Opus 5 | $0.00052 | $0.00714 |
| Sonnet 5 | $0.00021 | $0.00286 |
| Haiku 4.5 | $0.00010 | $0.00143 |
Grade A, and why
sam-a2a-bridge 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 yesterday.
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAM A2A Bridge Skill
Use this skill to delegate work to A2A agents hosted by SAM mesh peers. The
bridge exposes three tools; everything else (auth, routing, the labels
gate) happens inside the local sam-node.
Pick the path that matches the need:
- The tools are not callable yet: Set Up The Bridge.
- Before sending data or files, check what the agent accepts: Check Agent Capabilities.
- The task needs a remote agent to do something: Send A Task.
- A previous send returned a non-terminal state: Poll A Task.
- The conversation with the agent continues: Multi-Turn.
- A call failed: Interpret Errors.
Set Up The Bridge
The bridge is a stdio MCP server that talks to the local sam-node sidecar.
Propose each shell command and let the user approve it before running anything.
- A running, enrolled
sam-nodeis required first. If its sidecar does not answer onhttp://localhost:8080, use thesam-meshskill's bootstrap path before continuing. - Build the bridge (own Go module; the Makefile pins the Go toolchain the
module needs, so a stale system Go still works):
make -C <sam-repo>/cmd/sam-a2a-bridge build - Register it with the harness, passing the sidecar URL and its API token:
claude mcp add sam-a2a-bridge -- <sam-repo>/bin/sam-a2a-bridge -url http://localhost:8080 -token <sidecar-token>(Agent-returned files land in~/.sam/a2a-downloadsby default, auto-created; pass-download-dirto change it — you must create that directory yourself. No auto-cleanup; prune manually.) - Restart the harness session; the three tools appear.
Check Agent Capabilities
get_agent_card(peer, service)
Call this before composing structured data or file attachments to verify what the agent accepts. Returns a trimmed card including:
- Registered skills with examples
default_input_modes— accepted MIME types for structured data (e.g.,application/json)default_output_modes— MIME types the agent can return- Whether the agent supports streaming
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.
- yesterday First seen · 110 lines · 104 tokens per session scan A 12c58d55f690
sam-a2a-bridge is a skill published in the GitHub repository google/sam (826 stars, last pushed today), licensed Apache-2.0. It adds 104 tokens to every session and 1,428 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 2026-09-07.
Other skills, from other repositories
detecting-beaconing-patterns-with-zeek
Performs statistical analysis of Zeek conn.log connection intervals to detect C2 beaconing patterns. Uses the ZAT library to load Zeek logs into Pandas DataFrames, calculates inter-arrival time standard deviation, and flags periodic connections with low jitter. Use when hunting for command-and-control callbacks in…
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.