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 do-cybersecurity-reviewgit 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/do-cybersecurity-review)<a href="https://agentmods.dev/skills/thermiteau/maverick/do-cybersecurity-review"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/do-cybersecurity-review/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/do-cybersecurity-review"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/do-cybersecurity-review.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 | $0.00117 | $0.03255 |
| Opus 5 | $0.00059 | $0.01628 |
| Sonnet 5 | $0.00023 | $0.00651 |
| Haiku 4.5 | $0.00012 | $0.00326 |
Grade A, and why
do-cybersecurity-review 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cybersecurity Review
Audit a codebase for security risks. Operates in two modes:
- full-audit — scan the entire codebase. Used by
do-initat adoption time and on demand. Producesdocs/security-audit.md. Flipscybersecurity_reviewedmilestone. - update — scoped to a diff, plus the code that could be impacted by the diff. Used by
do-issue-soloanddo-issue-guidedas a mandatory pre-push gate before opening a PR. Returns a structured findings list to the orchestrator; does not flip the milestone (it's per-PR work, not a one-time milestone).
Refer to mav-bp-application-security for the standards each finding should be measured against. The skill surfaces risks; it does not modify code.
Preflight (mandatory)
Run this first. If it exits non-zero, halt and report the stderr output to the user verbatim. Do not proceed.
uv run maverick preflight do-cybersecurity-review
The check verifies the project is initialised and uv is on PATH.
Mode Selection
If $ARGUMENTS specifies a mode (full-audit or update), use it. If update is selected the caller must also pass a diff (via stdin or a file path); halt and ask for one if missing.
If no mode is specified, default to full-audit.
Full Audit Mode
1. Detect the project stack
Identify language, framework, and runtime so subsequent checks know what to look for. Use the same detectors as do-maverick-alignment: package.json, pyproject.toml, Dockerfile, etc.
2. Walk the audit categories
For each category below, search the codebase and assign one of:
- PASS — no concerns surfaced
- WARN — partial coverage or non-critical issues
- FAIL — material risk; needs human attention
- N/A — category does not apply to this project
2.1 Secret exposure
Scan tracked files for committed credentials, tokens, private keys, and connection strings. Patterns to check (extend per stack):
AKIA[0-9A-Z]{16}(AWS access key id),aws_secret_access_key\s*=-----BEGIN (RSA |EC |OPENSSH )?PRIVATE KEY-----ghp_,gho_,ghs_,github_pat_(GitHub tokens)xox[baprs]-(Slack tokens),sk-followed by 20+ alphanumerics (OpenAI/Anthropic-style)- Generic
password\s*=\s*['"][^'"]+['"],api[_-]?key\s*=\s*['"][^'"]+['"]
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 · 277 lines · 117 tokens per session scan A da4e8dd58d02
do-cybersecurity-review is a skill published in the GitHub repository thermiteau/maverick (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 117 tokens to every session and 3,255 once invoked, about $0.0006 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…