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 thermiteau/maverick --skill mav-bp-operabilitygit clone --depth 1 https://github.com/thermiteau/maverickWrote 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/thermiteau/maverick/mav-bp-operability)<a href="https://agentmods.dev/skills/thermiteau/maverick/mav-bp-operability"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-bp-operability/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/thermiteau/maverick/mav-bp-operability"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-bp-operability.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 | $0.00070 | $0.01173 |
| Opus 5 | $0.00035 | $0.00587 |
| Sonnet 5 | $0.00014 | $0.00235 |
| Haiku 4.5 | $0.00007 | $0.00117 |
Grade A, and why
mav-bp-operability 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 10d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operability Standards
Logging, alerting, and observability as one discipline: record what happened, demand attention when it matters, and make internal state diagnosable from outside. Logs record; alerts interrupt; metrics and traces correlate.
Maverick's Rules
Logging
- No
infolevel. If it matters in production it iswarnorerror; if it only helps during development it isdebug. Info-level logging is a noise dumping ground — this is Maverick's most-fought deviation from default LLM behaviour; hold the line. - Structured JSON only, to an aggregation service (stdout is fine when
the platform ships it — container log drivers, CloudWatch agents).
Required fields:
timestamp,level,message,service,context(putcorrelationIdand error details insidecontext). - Log errors once, at the boundary — never log-and-rethrow at every layer. Never log PII, tokens, or secrets.
- One logger module per service;
console.lognever ships.
Alerting
- Alert only on unrecoverable failures and threshold breaches, from the outermost error boundary (global handlers, health checks) — never inside low-level functions, loops, or retries.
- Severities are
critical(wake someone) /high(within the hour) /warning(next business day). Alert severities are not log levels — do not map one onto the other. - Every alert carries: severity, service, environment, impact-stating message ("checkout is down", not "error occurred"), scope, and a log pointer. Always log first, then alert.
- Deduplicate: first alert wins, cooldown window suppresses repeats.
- Frontend code never calls alerting services directly — report to an error-reporting service or a backend endpoint.
Observability
- Three pillars share identifiers: the trace/correlation id in a metric spike must find the requests and their logs.
- Request-driven services expose RED metrics (rate, errors, duration); no high-cardinality metric labels (user ids belong in traces/logs).
- Liveness checks the process only; readiness checks dependencies — conflating them causes cascading restarts.
- Use a standard instrumentation library (OpenTelemetry or equivalent), never hand-rolled collection.
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.
- 10d ago First seen · 87 lines · 70 tokens per session scan A a531e86a7eef
mav-bp-operability is a skill published in the GitHub repository thermiteau/maverick (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,173 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…