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 commands/samibs/skillfoundry/web-security-checkgit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/commands/samibs/skillfoundry/web-security-check)<a href="https://agentmods.dev/commands/samibs/skillfoundry/web-security-check"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/web-security-check.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02887 |
| Opus 5 | $0.00000 | $0.01443 |
| Sonnet 5 | $0.00000 | $0.00577 |
| Haiku 4.5 | $0.00000 | $0.00289 |
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 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.
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 | How it starts
The opening of the file, as written. The whole thing — 247 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 |
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 First seen · 247 lines · 0 tokens per session scan A 55af001b31d7
web-security-check is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,887 tokens. 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.