Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/trumb/claude-nginx-hardeningnpx agentmods add commands/trumb/claude-nginx-hardening/audit-nginxWrote 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/trumb/claude-nginx-hardening/audit-nginx)<a href="https://agentmods.dev/commands/trumb/claude-nginx-hardening/audit-nginx"><img src="https://agentmods.dev/badge/commands/trumb/claude-nginx-hardening/audit-nginx/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/commands/trumb/claude-nginx-hardening/audit-nginx"><img src="https://agentmods.dev/badge/commands/trumb/claude-nginx-hardening/audit-nginx.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 | $0.00020 | $0.01158 |
| Opus 5 | $0.00010 | $0.00579 |
| Sonnet 5 | $0.00004 | $0.00232 |
| Haiku 4.5 | $0.00002 | $0.00116 |
Grade A, and why
audit-nginx scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Use curl to verify: How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Nginx configs: !
ls /etc/nginx/sites-enabled/ 2>/dev/null || echo "no sites-enabled found" - Security snippet: !
test -f /etc/nginx/snippets/security-hardening.conf && echo "PRESENT" || echo "MISSING" - Profile: !
echo "${NH_PROFILE:-auto-detect}"
Operating Mode
DEFAULT: R0 + R1 (Recommendation Mode)
With --apply: escalates to W1
With --deploy: escalates to W1 + W2 + X1
Read @skills/nginx-hardening/EXECUTION-POLICY.md for full policy.
Your Task
Audit nginx configuration for security compliance.
Input
The user may provide:
- A specific config path:
/audit-nginx /path/to/nginx.conf - A URL for live testing:
/audit-nginx https://example.com - Nothing (auto-detect configs in /etc/nginx/sites-enabled/)
Analysis Levels
Level 1 — Static Config Analysis (always on) Dispatch the config-auditor agent to check:
- All 6 security headers present and correct
- TLS 1.2+ only, ECDHE ciphers
- server_tokens off, autoindex off
- client_max_body_size set
- Method restriction present
- Rate limiting present
- security-hardening.conf included
- Location precedence conflicts
- Duplicate/shadowed directives
- Coverage of all 35 attack categories
Level 2 — Log Cross-Reference (if logs available) If nginx logs are found, also run the log analysis pipeline to enrich audit findings with actual traffic data.
Level 3 — Live Verification (opt-in with --live or when URL provided) Use curl to verify:
- Security headers returned correctly
- TLS protocol/cipher negotiation
- Known blocked paths return 404 (sample from each of the 35 categories)
- Health endpoint responds
- Do NOT perform intrusive testing (no fuzzing, no brute-force, no high-rate)
Output
Generate artifacts in outputs/<run-id>/:
audit-report.md— Human-readable compliance reportfindings.json— Machine-readable findingsproposed-rules/— Any recommended new rules
Present a summary to the user showing:
- PASS/FAIL/WARN for each check category
- Total findings by severity
- Recommended next steps
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.
- 10d ago First seen · 110 lines · 20 tokens per session scan A 07577744dffe
audit-nginx is a command published in the GitHub repository trumb/claude-nginx-hardening (2 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 1,158 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 2026-08-31.
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.