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-application-securitygit 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-application-security)<a href="https://agentmods.dev/skills/thermiteau/maverick/mav-bp-application-security"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-bp-application-security/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-application-security"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-bp-application-security.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 | $0.00051 | $0.01170 |
| Opus 5 | $0.00026 | $0.00585 |
| Sonnet 5 | $0.00010 | $0.00234 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
mav-bp-application-security 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 9d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| `shell=True` or `os.system()` with user input | Command injection | Use subprocess with argument list; avoid shell execution | How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Application Security Standards
Ensure all code is written with security as a first-class design constraint, and that changes to the security surface stay within authorized scope.
Maverick's Rules
- Actively consider the current OWASP Top 10 on every change you write or review — do not enumerate from memory of an old list; check whether each current risk applies.
- Secrets — hard rules: never in source code, committed
.envfiles, logs, error messages, or Docker image layers (ENV/COPY)..env.exampledocuments variable names without values. If a secret is ever committed, rotate it immediately — removing it from git history is insufficient. - Secret scanning is mandatory: pre-commit hooks (gitleaks, trufflehog, git-secrets) plus a CI gate on every PR and push.
- SAST on every PR, with critical/high findings build-breaking; tune rules — a noisy scanner gets ignored. DAST against staging at minimum on every deployment there, with findings tracked as issues.
- Dependency scanning on every build, failing on critical/high with an explicit exceptions process — see mav-bp-dependency-management.
- Mask or redact sensitive data before logging — see mav-bp-operability.
- Secure defaults are non-negotiable: TLS 1.2+ everywhere, parameterised queries as the default data-access method,
Secure/HttpOnly/SameSiteon all auth cookies, debug mode and verbose errors off in production, framework auto-escaping and CSRF middleware never disabled. - CSP: start from
default-src 'self'; avoidunsafe-inline/unsafe-eval(use nonces or hashes); deploy report-only before enforcing. - API security: authenticate every endpoint unless explicitly public; always verify JWT signature, issuer, audience, and expiry; rate limit auth endpoints. See mav-bp-api-design.
Scope authorization for security-surface work: implementing or changing security headers, CORS policy, CSRF middleware, cookie flags, or password policy is allowed only when the issue explicitly authorizes it, and must always be flagged per mav-scope-boundaries — auth and security-surface changes are never silent drive-bys.
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.
- 9d ago First seen · 55 lines · 51 tokens per session scan A 571d3e738686
mav-bp-application-security is a skill published in the GitHub repository thermiteau/maverick (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,170 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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…