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 andrewsrigom/agent-skills --skill security-default-review-for-web-appsgit clone --depth 1 https://github.com/andrewsrigom/agent-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/andrewsrigom/agent-skills/security-default-review-for-web-apps)<a href="https://agentmods.dev/skills/andrewsrigom/agent-skills/security-default-review-for-web-apps"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/security-default-review-for-web-apps/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/andrewsrigom/agent-skills/security-default-review-for-web-apps"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/security-default-review-for-web-apps.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 | $0.00054 | $0.00590 |
| Opus 5 | $0.00027 | $0.00295 |
| Sonnet 5 | $0.00011 | $0.00118 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
security-default-review-for-web-apps 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 12d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Default Review For Web Apps
Use this skill when the task is to find the highest-risk web security boundary before the team starts patching randomly.
Scope
- high-level security review for web apps
- deciding whether the main risk is secrets, authorization, or input handling
- identifying public input and privileged actions
- routing to narrower security skills
Routing cues
- security review, secure by default, trust boundary, secret exposure, authz review, dangerous sink, or “what is the main risk here” -> use this skill
- if the core issue is client vs server boundary or secret handling -> use
security-client-server-boundary-and-secret-exposure - if the core issue is permissions, actor trust, or multi-tenant access -> use
security-authz-and-trust-boundaries - if the core issue is untrusted input reaching dangerous sinks -> use
security-input-validation-and-dangerous-sinks
Default path
- List the public inputs, authenticated actors, and privileged actions.
- Identify where secrets or sensitive data live.
- Mark the trust boundaries:
- browser vs server
- unauthenticated vs authenticated
- authenticated vs authorized
- internal service vs external caller
- Pick the highest-risk boundary.
- Route the fix through the narrower security skill that owns that boundary.
When to deviate
- Stay at the overview level only when the user truly needs a triage map rather than a fix.
- Escalate beyond these skills when the issue is infrastructure, cryptography, or compliance-specific rather than app-boundary specific.
Guardrails
- Do not call this a full security audit.
- Prioritize exploitable trust-boundary mistakes over broad best-practice checklists.
- Treat the browser as untrusted by default.
- Separate authentication, authorization, and input safety clearly.
Avoid
- giving equal weight to every theoretical issue
- focusing only on XSS and SQL injection while missing authz failures or secret leaks
- trusting UI checks as a security boundary
- calling a review complete without naming the highest-risk surface
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.
- 12d ago First seen · 75 lines · 54 tokens per session scan A 496fef4b2e9e
security-default-review-for-web-apps is a skill published in the GitHub repository andrewsrigom/agent-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 54 tokens to every session and 590 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 2026-08-31.
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…
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…