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-expertgit 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-expert)<a href="https://agentmods.dev/skills/mzf11125/midnight_agent_skills/midnight-expert"><img src="https://agentmods.dev/badge/skills/mzf11125/midnight_agent_skills/midnight-expert/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-expert"><img src="https://agentmods.dev/badge/skills/mzf11125/midnight_agent_skills/midnight-expert.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 | $0.00061 | $0.07473 |
| Opus 5 | $0.00030 | $0.03736 |
| Sonnet 5 | $0.00012 | $0.01495 |
| Haiku 4.5 | $0.00006 | $0.00747 |
Grade B, and why
midnight-expert scanned grade B 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 11d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Missing Docker permissions cause Docker commands to fail with permission denied. The resolution is to add the user to the docker group with `sudo usermod -aG docker $USER` and log out and back in. How it starts
The opening of the file, as written. The whole thing — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Midnight Expert
Midnight Expert Overview
Midnight Expert is the meta plugin for ecosystem diagnostics across all Midnight development tooling. It coordinates health checks, version compatibility verification, dependency scanning, and environment validation across the entire Midnight stack. When a developer encounters issues that span multiple components, Midnight Expert provides a unified diagnostic view that identifies root causes and recommends resolutions.
The meta plugin design means that Midnight Expert does not directly implement diagnostic logic. Instead, it orchestrates the diagnostic capabilities of each specialized plugin. It queries the proof server plugin for proof generation health, the indexer plugin for data pipeline health, the tooling plugin for development environment health, and other plugins for their respective domains.
Midnight Expert is activated through the doctor command which runs a full diagnostic sweep. The doctor command produces a summary report, a detailed JSON report, and actionable recommendations. It can be run interactively in the terminal or integrated into CI pipelines for automated health checks.
Version matrix management is a core responsibility. Midnight Expert maintains a comprehensive mapping of which versions of each component are compatible with each other. This matrix is consulted during health checks to detect version mismatches that could cause subtle runtime errors.
Network diagnostics verify that all required network endpoints are reachable. This includes the node JSON-RPC endpoint, the indexer GraphQL endpoint, the proof server HTTP endpoint, and any faucet endpoints. Each endpoint is tested for connectivity, response time, and health status.
Health Check System
The health check system runs a series of checks against each plugin and aggregates the results. Each check returns a status of healthy, degraded, or unhealthy, along with a human-readable message and diagnostic data. The system categorizes checks by severity so that critical issues that prevent development are highlighted while informational issues are noted but do not block the report.
What ships with it
3 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.
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.
- 11d ago First seen · 485 lines · 61 tokens per session scan B b67a1c51ea0f
midnight-expert is a skill published in the GitHub repository mzf11125/midnight_agent_skills (6 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 7,473 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
vial
Vial self-healing runtime — 8 protocols covering technical failures, behavioral failures, and agent role enforcement.
pipes-sdk
Build, configure, deploy, and troubleshoot durable blockchain indexers with the Subsquid Pipes SDK (EVM, Solana, Tron, Bitcoin, Hyperliquid) when Portal MCP or curl previews are insufficient for backfills, recurring syncs, joins, app-owned data, or production analytics.
shell-scripts
Shell script development workflow. Use when modifying files in scripts/ directory or any .sh files.
alchemy-cli
Use the Alchemy CLI (@alchemy/cli) for live blockchain data, transaction lookups, NFT/token/portfolio queries, simulation, tracing/debugging, account abstraction (bundler + gas manager), webhook management, Solana RPC/DAS, and Alchemy app administration. Preferred runtime path for live agent work (querying, admin…
audit-verify-explain-grade-5
Audit work, verify claims with concrete evidence, and explain the result in simple grade-5 language. Use when the user asks to review, audit, check, verify, explain a change, explain a fix, summarize test results, validate whether something works, or translate technical findings into plain language for non-technical…
onesource-report-bug
Report a bug or unexpected error in OneSource MCP to the OneSource team using the 1sreportbug tool. Use when a 1s blockchain tool returns an unexpected error, or when the user explicitly asks to report a problem. Free, no payment required. Do NOT report 402 (payment/auth) or 403 (subscription) responses — those are…