sec-review

sec-review is a command for coding agents from JuliusBrussee/caveman-code. It costs 19 tokens per session (385 once invoked), scanned A, original, MIT.

A command that checks code changes, or the whole repository when requested, for common security problems. It looks for exposed secrets, unsafe input handling, access-control mistakes, weak cryptography, risky dependencies, and privacy issues in logs.

In plain words
What is it for?
Use it to review a diff or repository for vulnerabilities such as SQL injection, cross-site scripting, leaked credentials, broken permissions, and unsafe file or network access. It reports problems but does not fix them.
Why use it?
It helps find ways an attacker could misuse the code before changes are released. It reports each issue with its severity, location, possible attack, and a suggested fix.

Command

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.

agentmods
npx agentmods add commands/juliusbrussee/caveman-code/sec-review
Clone the repo
git clone --depth 1 https://github.com/JuliusBrussee/caveman-code

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 sec-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/juliusbrussee/caveman-code/sec-review.svg)](https://agentmods.dev/commands/juliusbrussee/caveman-code/sec-review)
Your own site
<a href="https://agentmods.dev/commands/juliusbrussee/caveman-code/sec-review"><img src="https://agentmods.dev/badge/commands/juliusbrussee/caveman-code/sec-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 385 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00019 $0.00385
Opus 5 $0.00010 $0.00192
Sonnet 5 $0.00004 $0.00077
Haiku 4.5 $0.00002 $0.00038

Measured 4d ago against content hash 3352a6c414a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sec-review 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 4d 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.

packages/coding-agent/commands/sec-review.md · 39 lines

What it actually says

Perform a security review of $ARGUMENTS (defaults to the diff vs. main).

Checklist:

  1. Secrets / credentials — leaked API keys, passwords, JWTs, private keys, OAuth tokens. Search both code and committed config.
  2. Injection — SQL, shell, template, prototype-pollution, XSS, SSRF, path-traversal. Look at every exec, system, raw query string, dangerouslySetInnerHTML, dynamic require/import, and fs.readFile path that is built from user input.
  3. AuthN / AuthZ — every privileged endpoint must check authentication and authorization. Flag broken object-level authorization (BOLA) and IDOR patterns.
  4. Crypto — no MD5/SHA-1 for security; no static IVs; no homemade crypto. Token expiry must be enforced server-side.
  5. Dependencies — anything pinned to an outdated major with known CVEs.
  6. Network surface — overly permissive CORS, missing CSRF protection, leaky error messages.
  7. Logging / telemetry — no PII, no secrets, no tokens.

For each finding produce:

  • Severity: Critical / High / Medium / Low / Info.
  • File:line.
  • Concrete exploitation scenario in one sentence.
  • Recommended remediation (specific, copy-pasteable when possible).

Do not fix anything during review. Conclude with a short "Areas left unreviewed" section so the user knows the boundary.

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. 4d ago First seen · 39 lines · 19 tokens per session scan A 3352a6c414a7

Subscribe to this mod's changes

sec-review is a command published in the GitHub repository JuliusBrussee/caveman-code (930 stars, last pushed 20d ago), licensed MIT. It adds 19 tokens to every session and 385 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 2026-08-30.