web-security-check

web-security-check is a skill for Claude Code, Codex from samibs/skillfoundry. It costs 21 tokens per session (2,917 once invoked), scanned A, original, MIT.

A checker for the security of a live web application, focusing on the deployed server rather than the source code alone.

In plain words
What is it for?
Use it to inspect a staging or production URL, or to check only its HTTP security headers.
Why use it?
It can reveal deployment problems such as missing security headers, certificate issues, or forgotten DNS settings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Install

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.

agentmods
npx agentmods add skills/samibs/skillfoundry/web-security-check
Any agent
npx skills add samibs/skillfoundry --skill web-security-check
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for web-security-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/samibs/skillfoundry/web-security-check.svg)](https://agentmods.dev/skills/samibs/skillfoundry/web-security-check)
Your own site
<a href="https://agentmods.dev/skills/samibs/skillfoundry/web-security-check"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/web-security-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,917 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.02917
Opus 5 $0.00010 $0.01458
Sonnet 5 $0.00004 $0.00583
Haiku 4.5 $0.00002 $0.00292

Measured 2d ago against content hash af3dce3f8919, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

web-security-check scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| TLS version | `curl --tlsv1.3` / `openssl` | TLS 1.0 or 1.1 active | TLS 1.2 only (1.3 not offered) | TLS 1.3 active |
.agents/skills/web-security-check/SKILL.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Security Checker

You are a rigorous web infrastructure security specialist. You validate the live deployed surface of web applications against real-world attack vectors. You do not trust developer assertions — you verify everything against the actual running server.

Persona: See agents/web-security-checker.md for full persona definition.

Operational Philosophy: A clean codebase can still expose a broken server. Headers lie by omission. Certificates expire silently. DNS is forgotten until it fails. Find the gaps before attackers do.

Known Deviations: See agents/_known-deviations.md for LLM failure patterns to prevent.

Scope: This agent operates on live deployed URLs only (staging minimum). It does NOT replace /security (code-level static analysis) or /security pentest (adversarial exploitation). It validates infrastructure configuration.

OPERATING MODES

/web-security-check <url>

Full check — all 10 groups. Produces complete report with BLOCKER/WARN/INFO findings and closing block.

/web-security-check <url> --headers

HTTP security headers only (group 2). Fast check for header misconfiguration.

/web-security-check <url> --tls

TLS/certificate only (group 1). Use for cert rotation verification or cipher audit.

/web-security-check <url> --dns

DNS + mail security only (group 4). Use for SPF/DKIM/DMARC validation.

/web-security-check <url> --quick

BLOCKER-severity checks only across all groups. Fastest gate — use in CI/CD pipelines where timeout is a constraint.

/web-security-check <url> --report

Full check + writes a signed JSON report to logs/web-security/[timestamp]-[domain].json. Required for compliance audit trails.

CHECK CATALOGUE

Run checks in this order. Collect all findings before generating the report — do not short-circuit on first BLOCKER.

Group 1 — TLS / Certificates

Check Tool BLOCKER WARN INFO
Certificate validity openssl s_client Invalid or untrusted cert Expiry <30 days Expiry >30 days
Certificate chain openssl s_client Chain incomplete Self-signed (non-internal)
TLS version curl --tlsv1.3 / openssl TLS 1.0 or 1.1 active TLS 1.2 only (1.3 not offered) TLS 1.3 active
Cipher suites openssl s_client -cipher NULL, EXPORT, RC4, DES 3DES, CBC without AEAD AEAD ciphers only
HSTS (production) Response headers HSTS header absent max-age <31536000 max-age ≥31536000

Read the full file on GitHub · 253 lines

Changes

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.

  1. 2d ago First seen · 253 lines · 21 tokens per session scan A af3dce3f8919

Subscribe to this mod's changes

web-security-check is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 2,917 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

azure-sweep

Runs the full 8-layer Azure governance sweep using the Azure Sweeper agent.

srnichols/plan-forge · 0 tokens

staging-deploy

Build, push, migrate, and deploy to staging environment with health check verification. Use when deploying a completed phase to staging.

srnichols/plan-forge · 30 tokens

ring:creating-grafana-dashboards

Authoring Grafana dashboards for Go services instrumented with lib-observability telemetry (tracing, metrics, log), plus a reference mode for RED/USE panel patterns and Grafonnet templates. Sweep mode inventories telemetry, runs PM deliberation on themes/SLIs/alerts, authors Grafonnet libsonnet compiled to JSON, and…

LerianStudio/ring · 103 tokens

ring:migrating-to-lib-systemplane

Migrating Lerian Go services from .env/YAML operational knobs (log levels, feature flags, rate limits, timeouts) to the lib-systemplane hot-reloadable runtime config client, wiring the migration-only make systemplane-ddl pipeline (runtime DDL forbidden in v1.6.0+). Orchestrates an 11-gate cycle dispatching…

LerianStudio/ring · 113 tokens

forge-quench

Systematically reduce .NET/C# code complexity while preserving exact behavior — measure, understand, propose, prove, report. Use after a feature is complete and tests pass, when code works but is harder to maintain than it should be.

srnichols/plan-forge · 51 tokens

bug-fix

Guided end-to-end bug-fix workflow for Plan Forge tempering bugs — load → pre-fix review → write failing test → fix → validate → post-fix sweep → close. Composes /code-review, /clean-code-review, /forge-quench, and /test-sweep around the forgebug tool surface so a fix never closes without a regression check.

srnichols/plan-forge · 80 tokens