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 johnku2011/boilerplates-with-ai-skills --skill project-securitygit clone --depth 1 https://github.com/johnku2011/boilerplates-with-ai-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/johnku2011/boilerplates-with-ai-skills/project-security)<a href="https://agentmods.dev/skills/johnku2011/boilerplates-with-ai-skills/project-security"><img src="https://agentmods.dev/badge/skills/johnku2011/boilerplates-with-ai-skills/project-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/johnku2011/boilerplates-with-ai-skills/project-security"><img src="https://agentmods.dev/badge/skills/johnku2011/boilerplates-with-ai-skills/project-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 72 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00028 | $0.00580 |
| Opus 5 | $0.00014 | $0.00290 |
| Sonnet 5 | $0.00006 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
project-security 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 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.
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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Security
Overview
Apply a practical security review to changes in this project. Focus on real exploitable issues, not generic checklists.
Core principle: Assume all external input is hostile. Assume secrets will leak unless kept server-side.
When to Use
- New or changed HTTP routes, API handlers, or auth flows
- File upload, subprocess, or shell execution
- Environment variable or config changes
- Dependency additions or version bumps
- Anything touching user data, tokens, or payments
Process
- Map trust boundaries — user input, network, filesystem, subprocesses, third-party APIs, client vs server.
- Authentication & authorization — every new route/action must declare who can call it and what they can access.
- Secrets — no keys/tokens in source, logs, client bundles, or error responses; env vars on server only.
- Input validation — validate query, body, headers, filenames, and IDs; reject early with safe error messages.
- Output encoding — prevent injection (HTML, SQL, shell, template).
- Dependencies — prefer existing libs; note new supply-chain surface.
- Data exposure — server-only data must not reach client, logs, or analytics.
Stack-Specific Checks
When the stack matters, read references/stack-checks.md
for web/API and mobile notes (progressive disclosure — load only if needed).
Severity Guide
| Severity | Examples |
|---|---|
| Blocking | Missing auth on privileged route, SQL/command injection, secret in client |
| High | Weak session handling, verbose errors leaking internals |
| Medium | Missing rate limit, overly broad CORS |
| Low | Defense-in-depth hardening, logging improvements |
Output Format
## Blocking
- [scenario] Issue — exploit path — fix
## Hardening
- Non-blocking improvements
## Verdict
safe to ship | ship with fixes | do not ship
Anti-patterns
- Rubber-stamping without checking auth on new endpoints.
- Ignoring client-visible env vars or API responses that expose internals.
- Security theater (extra complexity without reduced risk).
- "We will add auth later" on production-bound code.
What ships with it
1 file 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 · 80 lines · 28 tokens per session scan A 895400ef4423
project-security is a skill published in the GitHub repository johnku2011/boilerplates-with-ai-skills (240 stars, last pushed 17d ago), licensed MIT. It adds 28 tokens to every session and 580 once invoked, about $0.0001 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…