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 agentmods add skills/robconery/cassini-workshop/security-webnpx skills add robconery/cassini-workshop --skill security-webgit clone --depth 1 https://github.com/robconery/cassini-workshopWhat 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 | $0.00207 | $0.03019 |
| Opus 5 | $0.00103 | $0.01510 |
| Sonnet 5 | $0.00041 | $0.00604 |
| Haiku 4.5 | $0.00021 | $0.00302 |
Grade A, and why
security-web 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 2d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- security-web — 100% identical, 0 lines differ
- security-web — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Application Security Review
Treat every byte that crossed a network boundary as hostile until proven
otherwise, and prove it on the server. The client is an untrusted rendering
surface you do not control. Frameworks add convenience (Server Actions,
Nitro routes, Bun.serve, Hono middleware) that hides the trust boundary
— this skill's job is to make the reviewer see the boundary the framework
obscured.
🎯 Why: Design for Change
The goal of writing software is to be able to change it safely. Secure-by-default config (CSP, cookie flags, parameterized queries, authz-at-the-edge) means the next feature ships without re-litigating the threat model. Every insecure default you accept becomes a foothold the next change has to step around.
This skill is for security review and secure implementation. For general
TypeScript correctness use typescript-best-practices; for schema-level
integrity use postgres-dba. This skill never assumes another layer will
catch it.
How to use this skill (review workflow)
- Map the attack surface first. Identify every trust boundary: HTTP
handlers, Server Actions, form posts, websocket frames, file uploads,
outbound fetches,
postMessage,process.envreaching the client, third-party script tags. A vuln you didn't enumerate is a vuln you didn't find. - Triage each input against the decision guide below; open the matching
references/*.mdfor the exploit, the vulnerable pattern, the fix, and the false-positive caveat. - Apply the framework reference (
references/nextjs.md,nuxt.md,bun.md,hono.md) — the generic finding almost always has a framework-specific trap or a framework-specific fix. - Report findings in the standard format (
templates/finding.md): severity, location (file:line), a concrete exploit walkthrough, and the minimal fix. No exploit path stated → it is an observation, not a finding; say which. - Recommend the secure default, not a bespoke patch. The
templates/configs (CSP, security headers, cookies, CORS) are the target state; a one-off escape is a stopgap.
What ships with it
12 files 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.
- .DS_Store 6.0 KB
- references/backend.md 13 KB
- references/bun.md 4.1 KB
- references/frontend.md 8.9 KB
- references/hono.md 4.4 KB
- references/nextjs.md 4.2 KB
- references/nuxt.md 3.6 KB
- templates/cors.md 1.8 KB
- templates/finding.md 1.9 KB
- templates/input-validation.ts 2.1 KB runs code
- templates/review-checklist.md 2.4 KB
- templates/security-headers.md 3.4 KB
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.
- 2d ago First seen · 208 lines · 207 tokens per session scan A e9026350da7e
security-web is a skill published in the GitHub repository robconery/cassini-workshop (1 stars, last pushed 2mo ago), licensed MIT. It adds 207 tokens to every session and 3,019 once invoked, about $0.0010 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
agent-teams
How to orchestrate Claude Code's experimental Agent Teams — spawning teammates as separate sessions, delegating work to them, and waiting for results instead of doing the work yourself in the main thread. Use whenever a task should run as parallel/independent workstreams: multi-file refactors, reviewing or auditing…
bdd-specs
Behavior-driven design: write executable specifications BEFORE any implementation code. Reads /docs/PLAN.md for the build plan and /docs/STORIES.md for user stories, and stops to ask for either if it is missing. Generates TypeScript spec files in nested blocks — Feature > Scenario > Specification — where each Scenario…
github
GitHub workflow conventions: writing clear conventional commits, opening detailed issues and PRs via the gh CLI, and choosing trunk-based vs short-lived branch flow based on the size of the change. Use whenever the user wants to commit, branch, push, open an issue, open a PR, or asks how to structure any of those.…
user-stories
Write, split, and refine agile/scrum user stories and acceptance criteria. Produces /docs/STORIES.md as the canonical backlog, formatted to feed directly into the bdd-specs skill (Story → Feature, Given/When/Then acceptance criteria → Scenario/Specification). Use this whenever the user wants to write a user story…
tdd
Test-driven development with bun:test, written for clarity. Produces failing tests FIRST — before any implementation — that read as the executable spec a builder agent implements against. Each test names a single behavior in plain language, follows Arrange–Act–Assert, asserts one thing, and uses real types with no…
security-web
Web application security review for TypeScript/JavaScript stacks, frontend and backend: XSS and output encoding, CSRF, clickjacking, secrets leaking into client bundles, authn/authz and IDOR, injection (SQL/command/NoSQL/ template), SSRF, mass assignment, insecure deserialization, file upload, path traversal, security…