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 joao-aires/agent-skills-public --skill security-and-privacy-designgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/security-and-privacy-design)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/security-and-privacy-design"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/security-and-privacy-design/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/joao-aires/agent-skills-public/security-and-privacy-design"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/security-and-privacy-design.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 | $0.00050 | $0.01001 |
| Opus 5.5 | $0.00020 | $0.00400 |
| Sonnet 5.5 | $0.00010 | $0.00200 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
security-and-privacy-design 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 yesterday.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design secure features
Start with the changed boundary
Read the feature, architecture and existing security decisions. Identify valuable data/actions, actors, entrypoints and trust boundaries; examine how the change can expose data, bypass authority, exhaust resources or produce unwanted side effects. Keep this proportional: a few documented abuse cases often suffice for a small feature. Use OWASP threat modeling and relevant cheat sheets for the actual risk. Do not turn every change into an exhaustive audit or claim one was performed.
- Derive identity and tenant context from verified authentication; enforce authorization on server-side reads and writes, including background jobs, exports and MCP/AI tools.
- Validate inputs at boundaries, use parameterized queries and appropriate browser protections, and fail closed when required security configuration is absent.
- Avoid fallback secrets and permissive production defaults.
- Keep privileges narrow and separate environments.
- Bound uploads, expensive queries, external calls and retries to prevent trivial abuse.
Check meaningful resource operations
Trace an operation across the trust boundary rather than treating every route as an interchangeable read or write. Identify the actor and exact resource, the state in which the action is allowed, the permission required, and the effect that must be recorded. Include what happens when the request conflicts with another change or is repeated after an uncertain result.
Use a small operation matrix when several actions need comparison: actor, exact resource, lifecycle conditions, authority, effect, transaction/history, conflict/retry and user-visible outcome. The purpose is to expose differences in authority and consequences that a generic endpoint checklist would miss.
- Do not assume every resource permits generic CRUD.
- Publishing, finalizing, amending, revoking and correcting can have different authority and retention rules.
- Keep intended state, observed records and authorized transitions distinct.
- Keep business requirements separate from API implementation choices; scope the analysis to affected resources rather than invent a universal workflow engine.
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.
- yesterday Changed · +19 lines 21b832da969c
- 2d ago Changed b957fb8e6601
- 5d ago Changed · +4 lines ea8283db5761
- 7d ago First seen · 41 lines · 50 tokens per session scan A 0bf90c444dff
security-and-privacy-design is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,001 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-15.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…