manage-recipes

manage-recipes is a command for Claude Code from trumb/claude-nginx-hardening. It costs 17 tokens per session (970 once invoked), scanned A, original, MIT.

A command for managing reusable nginx hardening workflows, called recipes. A recipe is a saved sequence of steps that can be run, edited, listed, installed, or exported.

In plain words
What is it for?
Use it to create workflows for log analysis, configuration audits, threat-feed checks, deployment, learning cleanup, or repository synchronization, with optional schedules and approval thresholds.
Why use it?
It avoids rebuilding the same security procedure each time and gives repeated tasks a consistent sequence and schedule.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-nginx-hardening plugin — 1 skill, 8 commands, 3 agents shipped together

Good fit Use it to create workflows for log analysis, configuration audits, threat-feed checks, deployment, learning cleanup, or repository synchronization, with optional schedules and approval thresholds.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/trumb/claude-nginx-hardening/manage-recipes
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.

Clone the repo
git clone --depth 1 https://github.com/trumb/claude-nginx-hardening

Made for: Claude Code.

Or install claude-nginx-hardening, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 3 agents.

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 manage-recipes

README.md
[![agentmods](https://agentmods.dev/badge/commands/trumb/claude-nginx-hardening/manage-recipes/github.svg)](https://agentmods.dev/commands/trumb/claude-nginx-hardening/manage-recipes)
Your own site
<a href="https://agentmods.dev/commands/trumb/claude-nginx-hardening/manage-recipes"><img src="https://agentmods.dev/badge/commands/trumb/claude-nginx-hardening/manage-recipes/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.

agentmods 80×15 button for manage-recipes

Your own site · 80×15
<a href="https://agentmods.dev/commands/trumb/claude-nginx-hardening/manage-recipes"><img src="https://agentmods.dev/badge/commands/trumb/claude-nginx-hardening/manage-recipes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 970 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00017 $0.00970
Opus 5 $0.00009 $0.00485
Sonnet 5 $0.00003 $0.00194
Haiku 4.5 $0.00002 $0.00097

Measured 11d ago against content hash 1f2c07ef5e5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

manage-recipes 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 11d 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.

commands/manage-recipes.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

  • Saved recipes: !ls learnings/recipes/*.md 2>/dev/null | wc -l recipes found
  • Recent runs: !ls -d outputs/run-* 2>/dev/null | wc -l runs in outputs

Operating Mode

DEFAULT: R0 + R1 (create, list, show, export) With run: escalates per recipe's execution_class With install: W1 (local) or X1 (remote)

Read @skills/nginx-hardening/RECIPES-SCHEMA.md for recipe format.

Subcommands

create

Interactive recipe builder:

  1. Name — Prompt for kebab-case name (validate: ^[a-z0-9]+(-[a-z0-9]+)*$)
  2. Description — What this recipe does
  3. Profile — Select: edge-public, internal-only, api-gateway, static-site, reverse-proxy-app, high-risk-lockdown
  4. Steps — Add steps one at a time:
    • analyze-logs — params: log paths, lookback days, include rotated
    • audit-config — params: config targets, analysis level (1/2/3)
    • check-ioc-feeds — params: feed names, advisory/stage mode
    • deploy — params: target configs, sync repos, auto-push
    • compact-learnings — params: threshold lines
    • sync-repos — params: repo paths
  5. Schedule — manual, cron expression, or systemd timer
  6. Auto-approve threshold — auto-accept findings at or below this severity (low, medium, or none)
  7. Confirmation checkpoints — which steps pause for approval
  8. Max privilege level — highest action class allowed (R0, R1, W1, W2, X1)
  9. Validate — Run schema-validator.py
  10. Save — Write to learnings/recipes/.md

run <recipe-name>

Execute a saved recipe:

  1. Load recipe from learnings/recipes/
  2. Verify all required_env_vars are set
  3. First execution: always show privilege summary and require confirmation
  4. Execute steps in order
  5. Pause at confirmation_checkpoints
  6. Auto-approve findings <= auto_approve severity threshold
  7. Write run results to outputs/run-/

list

Show all recipes: | Name | Description | Profile | Schedule | Last Run | Steps |

edit <recipe-name>

Load existing recipe, present current values, allow modification. Re-validate and save.

Read the full file on GitHub · 102 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. 11d ago First seen · 102 lines · 17 tokens per session scan A 1f2c07ef5e5b

Subscribe to this mod's changes

manage-recipes is a command published in the GitHub repository trumb/claude-nginx-hardening (3 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 970 once invoked, about $0.0001 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.