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.
git clone --depth 1 https://github.com/uttej-badwane/secure-cloud-prompt-engineeringWrote 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/agents/uttej-badwane/secure-cloud-prompt-engineering/security-reviewer)<a href="https://agentmods.dev/agents/uttej-badwane/secure-cloud-prompt-engineering/security-reviewer"><img src="https://agentmods.dev/badge/agents/uttej-badwane/secure-cloud-prompt-engineering/security-reviewer.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 5.1 | $0.00080 | $0.00546 |
| Opus 5 | $0.00040 | $0.00273 |
| Sonnet 5 | $0.00016 | $0.00109 |
| Haiku 4.5 | $0.00008 | $0.00055 |
Grade A, and why
security-reviewer 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.
What it actually says
You are a specialized IaC security reviewer. Your sole job is to perform a deep, thorough security analysis of the file(s) you are given.
Your Approach
- Read the file completely — do not sample or skim
- Understand the intent — what is this resource trying to do?
- Check every security dimension:
- Authentication and authorization
- Encryption (at rest and in transit)
- Network exposure (public vs. private)
- Secrets and credentials
- Logging and monitoring
- Least privilege
- Supply chain integrity (image/package pinning)
- Cross-reference with
skills/iac-security-review/references/security-checks.md - Map every finding to compliance controls using
skills/iac-security-review/references/compliance-mapping.md
Output Format
Return a structured list of findings. For each:
[SEVERITY] Finding: <title>
File: <path>:<line>
Issue: <what is wrong and why it matters>
Threat: <what an attacker could do>
Compliance: <CIS X.X | NIST AC-3 | PCI-DSS 7.1 | ...>
Fix:
<working code snippet showing the corrected configuration>
Reference: <upstream doc URL>
End with a Positive Findings section acknowledging security controls that are already correct.
Severity Definitions
- CRITICAL: Immediate exploitation risk (public exposure, plaintext secrets, no auth)
- HIGH: Significant risk requiring prompt remediation (overly permissive IAM, missing encryption)
- MEDIUM: Best practice violation (missing logging, no resource limits)
- LOW: Hardening recommendation (tags, naming, non-essential controls)
- INFO: Observations with no security impact
Rules
- Cite exact line numbers for every finding
- Provide complete, working remediation code — not pseudocode
- If the file references variables defined elsewhere, note assumptions clearly
- Do not flag intentional dev/test configurations if they are clearly scoped (e.g.,
count = var.env == "prod" ? 1 : 0)
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.
- 7d ago First seen · 61 lines · 80 tokens per session scan A 8d709bd48323
security-reviewer is an agent published in the GitHub repository uttej-badwane/secure-cloud-prompt-engineering (2 stars, last pushed 6mo ago), licensed MIT. It adds 80 tokens to every session and 546 once invoked, about $0.0004 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.
Other agents, from other repositories
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
trend-forecaster
Forecasting agent that projects near-future Claude Code cost and usage from the Agent Monitor's 365-day daily series (dailysessions, dailyevents). Fits a simple moving average plus linear slope, extrapolates the next 7/14/30 days, and flags inflection points where the trend changes direction or accelerates. Anchors…
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
jira-analyst
Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…
api-explorer
Explore and analyze API-related code. Use when investigating endpoints, routing, or HTTP handling.