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 mzf11125/midnight_agent_skills --skill midnight-networkgit clone --depth 1 https://github.com/mzf11125/midnight_agent_skillsWrote 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/mzf11125/midnight_agent_skills/midnight-network)<a href="https://agentmods.dev/skills/mzf11125/midnight_agent_skills/midnight-network"><img src="https://agentmods.dev/badge/skills/mzf11125/midnight_agent_skills/midnight-network/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/mzf11125/midnight_agent_skills/midnight-network"><img src="https://agentmods.dev/badge/skills/mzf11125/midnight_agent_skills/midnight-network.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 | $0.00080 | $0.03168 |
| Opus 5.5 | $0.00032 | $0.01267 |
| Sonnet 5.5 | $0.00016 | $0.00634 |
| Haiku 4.5 | $0.00008 | $0.00317 |
Grade A, and why
midnight-network scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://localhost:9933 -H "Content-Type: application/json" \ How it starts
The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Midnight Network Infrastructure
Complete guide to running and managing Midnight Network infrastructure.
Infrastructure Overview
| Component | Purpose | Requirements |
|---|---|---|
| Full Node | Validate transactions, relay blocks | 4+ CPU, 8GB RAM, 100GB SSD |
| Archive Node | Full history storage | 4+ CPU, 16GB RAM, 1TB SSD |
| Validator | Produce blocks, consensus | 8+ CPU, 16GB RAM, 100GB SSD, stake |
| Indexer | Query API for DApps | 4+ CPU, 8GB RAM, 500GB SSD, v4.3.3 |
| Proof Server | Generate ZK proofs | 8+ CPU, 32GB RAM, GPU recommended |
Quick Start
Local Development (Recommended for DApps)
Option 1: midnight-local-dev (Full Local Network)
Provides complete local network with Node, Indexer, Proof Server:
git clone https://github.com/midnightntwrk/midnight-local-dev
cd midnight-local-dev
npm install
npm start
Network ID: undeployed
Services & Ports:
| Service | Port | URL |
|---|---|---|
| Node | 9944 | http://localhost:9944 |
| Indexer GraphQL | 8088 | http://localhost:8088/api/v4/graphql |
| Indexer WS | 8088 | ws://localhost:8088/api/v4/graphql/ws |
| Proof Server | 6300 | http://localhost:6300 |
Docker Images: node 0.24.0, indexer 4.3.3, proof-server 8.0.3
Funding: Use interactive menu to fund wallets with 50,000 tNIGHT each.
Standalone Mode (No Menu)
docker compose -f standalone.yml up -d
Option 2: midnight-wallet-cli
npx midnight-wallet-cli serve
Option 3: midnight-playground
Full Node Setup
# Using Docker (recommended)
docker run -d \
--name midnight-node \
-p 9933:9933 \
-p 9944:9944 \
-v midnight-data:/data \
midnightnetwork/node:v0.24.0 \
--network testnet-02 \
--pruning archive
Validator Setup
# See detailed guide below
# Requires staking tokens
docker run -d \
--name midnight-validator \
-p 9933:9933 \
-p 9944:9944 \
--restart unless-stopped \
-v validator-data:/data \
midnightnetwork/node:v0.24.0 \
--validator \
--staking <stake-address>
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/configs/indexer-config.yaml 363 B
- assets/configs/node-config.yaml 437 B
- assets/configs/validator-config.yaml 562 B
- references/api-reference.md 7.3 KB
- references/diagnostics.md 4.9 KB
- references/docker-deployment.md 13 KB
- references/indexer-setup.md 5.2 KB
- references/local-devnet.md 4.5 KB
- references/monitoring.md 13 KB
- references/network-config.md 1.8 KB
- references/node-architecture.md 6.0 KB
- references/node-releases.md 1.3 KB
- references/node-setup.md 5.8 KB
- references/operations.md 9.7 KB
- references/validator-guide.md 6.6 KB
- scripts/monitor-validator.py 517 B runs code
- scripts/network-health-check.py 1.6 KB runs code
- scripts/setup-indexer.py 1.4 KB runs code
- scripts/setup-validator.py 1.4 KB runs code
- skill.json 184 B
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.
- 2mo ago First seen · 466 lines · 80 tokens per session scan A f54c23715170
midnight-network is a skill published in the GitHub repository mzf11125/midnight_agent_skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 80 tokens to every session and 3,168 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
midnight-network compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| midnight-networkmzf11125/midnight_agent_skills | Skill | 5 | 4mo ago | MIT | A | 80 | Claude Code, Codex |
| blockchain-infrastructurej4flmao/agent-skills | Skill | 38 | 3d ago | MIT | A | 213 | Claude Code, Codex |
| chainstackchainstacklabs/mcp-server | Skill | 5 | 11d ago | MIT | A | 76 | Claude Code, Codex |
| indexer-setuplidonation/Cardano-mcp | Skill | 2 | 1mo ago | MIT | A | 59 | Claude Code |
| midnight-deployUvRoxx/midnight-agent-skills | Skill | 9 | 7mo ago | MIT | A | 61 | Claude Code, Codex |
| devloopx-cmd/x-cmd | Skill | 4.7k | 6d ago | Apache-2.0 | A | 25 | Claude Code, Codex |
| official-sui-skillsMystenLabs/sui | Skill | 7.8k | today | Apache-2.0 | A | 116 | Claude Code, Codex |