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/deploy-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/deploy-nginx)<a href="https://agentmods.dev/commands/trumb/claude-nginx-hardening/deploy-nginx"><img src="https://agentmods.dev/badge/commands/trumb/claude-nginx-hardening/deploy-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/deploy-nginx"><img src="https://agentmods.dev/badge/commands/trumb/claude-nginx-hardening/deploy-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 | $0.00022 | $0.02083 |
| Opus 5 | $0.00011 | $0.01042 |
| Sonnet 5 | $0.00004 | $0.00417 |
| Haiku 4.5 | $0.00002 | $0.00208 |
Grade A, and why
deploy-nginx scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo cp /etc/nginx/snippets/security-hardening.conf /etc/nginx/snippets/security-hardening.conf.bak.$(date +%Y%m%d-%H%M%S) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Staged outputs: !
ls -d outputs/run-* 2>/dev/null | tail -1 || echo "no staged runs found" - Nginx status: !
systemctl is-active nginx 2>/dev/null || echo "unknown"
Operating Mode
This command performs WRITES. Explicit approval required.
Default: W1 (local write)
With --push: W1 + W2 (local + git push)
With --remote: W1 + W2 + X1 (local + git push + remote deploy)
Read @skills/nginx-hardening/EXECUTION-POLICY.md for full policy. Read @skills/nginx-hardening/INVARIANTS.md — ALL invariants enforced.
Your Task
Deploy previously staged and accepted changes from a run's output directory.
Prerequisites
Before deploying, verify:
- A staged run exists in
outputs/<run-id>/ - The run has accepted proposed rules
- User has explicitly confirmed they want to deploy
Deployment Steps
Step 1: Identify Changes
Read outputs/<run-id>/proposed-rules/ and show the user exactly what will change.
Step 2: Validate (Deterministic)
# Run invariant checker against proposed changes
python3 scripts/invariant-checker.py --proposed <proposed-config> --backup <current-config> --require-backup
# Validate any new exceptions or learnings
python3 scripts/schema-validator.py --type <type> --file <file>
If ANY validation fails → abort deploy, show errors.
Step 2b: Compatibility Check
# Run all 9 compatibility checks against proposed config
python3 scripts/compatibility-checker.py --proposed <proposed-config> --current <current-config> --profile <profile>
- If any check returns critical severity → abort deploy, show the failing checks
- If checks return warning severity → display warnings, require explicit user confirmation to proceed
- See @skills/nginx-hardening/COMPATIBILITY-CHECKS.md for the full check reference
Step 2c: Blast-Radius Analysis
# Analyze which sites/upstreams are affected by the proposed changes
python3 scripts/blast-radius.py --proposed <proposed-config> --current <current-config>
- Present the blast-radius summary to the user before proceeding:
- Number of server blocks affected
- List of affected domains/listen directives
- Upstream dependencies impacted
- Estimated traffic scope (if log data available)
- Pause for user confirmation — user must explicitly approve after reviewing blast radius
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.
- 8d ago First seen · 212 lines · 22 tokens per session scan A cc4671d2531f
deploy-nginx is a command published in the GitHub repository trumb/claude-nginx-hardening (2 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 2,083 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). 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.