generate-report

generate-report is a command for Claude Code from uttej-badwane/secure-cloud-prompt-engineering. It costs 14 tokens per session (372 once invoked), scanned A, original, MIT.

A command that creates a security review report from infrastructure-as-code findings. Infrastructure as code means configuration files that define cloud or deployment resources.

In plain words
What is it for?
Use it to produce Markdown reports for people or JSON reports for ticketing-system integration, including risks, affected files, compliance controls, and fixes.
Why use it?
It turns review results into a consistent document that people can read or systems can process. It can use an existing review or start a fresh scan when none is available.

Command for Claude Code

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 skills/iac-security-review/scripts/generate_report.py \.

Part of the secure-cloud-prompt-engineering plugin — 1 skill, 5 commands, 3 agents, 3 hooks shipped together

Good fit Use it to produce Markdown reports for people or JSON reports for ticketing-system integration, including risks, affected files, compliance controls, and fixes.

Compare 6 commands from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/uttej-badwane/secure-cloud-prompt-engineering
agentmods
npx agentmods add commands/uttej-badwane/secure-cloud-prompt-engineering/generate-report

Made for: Claude Code.

Or install secure-cloud-prompt-engineering, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 3 agents, 3 hooks.

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 generate-report

README.md
[![agentmods](https://agentmods.dev/badge/commands/uttej-badwane/secure-cloud-prompt-engineering/generate-report.svg)](https://agentmods.dev/commands/uttej-badwane/secure-cloud-prompt-engineering/generate-report)
Your own site
<a href="https://agentmods.dev/commands/uttej-badwane/secure-cloud-prompt-engineering/generate-report"><img src="https://agentmods.dev/badge/commands/uttej-badwane/secure-cloud-prompt-engineering/generate-report.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 372 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 $0.00014 $0.00372
Opus 5 $0.00007 $0.00186
Sonnet 5 $0.00003 $0.00074
Haiku 4.5 $0.00001 $0.00037

Measured 7d ago against content hash 6a2f52468db0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

generate-report 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 7d 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/generate-report.md · 67 lines

What it actually says

Generate a formatted security report from an existing review or by running a fresh scan.

Steps

  1. Check if a review has already been performed in this session. If yes, use those findings. If no prior review exists, run /iac-security-review first.

  2. Determine output format from argument:

    • markdown (default) — human-readable report with tables and code blocks
    • json — machine-readable format for ticketing system integration
  3. Run the report generator:

python3 skills/iac-security-review/scripts/generate_report.py \
  --format <format> \
  --scope <scope> \
  --output <output-file>
  1. If the script is unavailable, generate the report directly using this structure:
# IaC Security Review Report
Date: [date]
Scope: [files reviewed]
Reviewer: Claude IaC Security Review Skill

## Executive Summary
[total counts by severity, overall risk rating: CRITICAL/HIGH/MEDIUM/LOW]

## Findings

### [SEVERITY] #N — [Title]
- File: [path:line]
- Description: [what's wrong]
- Risk: [impact if exploited]
- Compliance: [framework controls violated]
- Remediation: [code snippet]
- Reference: [link]

## Compliance Summary
[framework × control pass/fail matrix]

## Positive Findings
[things done well]

## Recommended Next Steps
[prioritized action items]
  1. Save the report and tell the user the output file path.

Usage

/generate-report
/generate-report markdown
/generate-report json
/generate-report json --output findings.json
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. 7d ago First seen · 67 lines · 14 tokens per session scan A 6a2f52468db0

Subscribe to this mod's changes

generate-report is a command published in the GitHub repository uttej-badwane/secure-cloud-prompt-engineering (2 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 372 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.