pcc-network

A command-line monitor for a network of software agents, including agents that accept jobs and agents that evaluate work. It reports online status, reward periods, account balances, and reputation scores.

In plain words
What is it for?
Use it to see which agents are online, whether job-processing agents are accepting work, how rewards are being assigned, your agent balance, or another agent’s reputation.
Why use it?
It brings network activity and agent performance into one view instead of requiring separate checks.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/lamasu/physical-capability-cloud/pcc-network
Clone the repo
git clone --depth 1 https://github.com/LamaSu/physical-capability-cloud

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 762 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00762
Opus 5 $0.00000 $0.00381
Sonnet 5 $0.00000 $0.00152
Haiku 4.5 $0.00000 $0.00076

Measured yesterday against content hash e2bcf1eb287b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pcc-network 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.

Origin

This is a copy

100% identical to pcc-network — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/pcc-network.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PCC Network — CLI

Monitor live network status: who's online, DePIN reward state, agent balances, and reputation scores.

When to use

  • "Show me the network status"
  • "What's the DePIN state / reward epoch?"
  • "Who's online on PCC?"
  • "Check my agent balance"
  • "What's the reputation of agent X?"
  • "Show network overview"
  • "How many kernels are active?"

Prerequisites

Commands

Agent Status — Who's Online

node packages/mcp-server/dist/cli.js agents status

Lists all registered agents with their online/offline status, type (user/broker/kernel/evaluator), last heartbeat, and endpoint. Use this to see which shop kernels are accepting jobs right now.

DePIN Stats — Reward Epochs & Kernel Scores

node packages/mcp-server/dist/cli.js depin stats

Shows the current reward epoch number, total distributed rewards, per-kernel scores, and top earners. Kernel scores are computed from job completion rate, evidence quality, and uptime. Use this to understand who's winning DePIN rewards.

Wallet Balance — Agent USDC Balance

node packages/mcp-server/dist/cli.js wallet balance

Returns the USDC balance held by your agent wallet on Base Sepolia. Also shows any locked-in-escrow amount and available-to-spend balance. Run this before submitting jobs to confirm you have sufficient funds.

Reputation — Get Agent or Kernel Reputation

node packages/mcp-server/dist/cli.js reputation get <agentId>

Fetches ERC-8004 reputation scores for a given agent or kernel ID. Output includes:

  • Overall reputation score (0-100)
  • Jobs completed / jobs failed
  • Evidence quality average
  • Challenge history (disputes won/lost)
  • Staleness indicator (when last updated on-chain)

Replace <agentId> with the DID or on-chain address of the agent (e.g., did:pcc:kernel-01 or 0xAbCd...).

Workflow: Full Network Health Check

Read the full file on GitHub · 75 lines

Changes

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.

  1. yesterday First seen · 75 lines · 0 tokens per session scan A e2bcf1eb287b

Subscribe to this mod's changes

pcc-network is a command published in the GitHub repository LamaSu/physical-capability-cloud (1 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 762 tokens. A static security scan graded it A with 0 findings. It is 100% identical to pcc-network, differing in 0 lines, and is treated as a copy.